From 6c21b8ca4e48bc81a4f931d8fa7012e519ec746d Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 21 Jul 2020 18:28:45 -0400
Subject: [PATCH 001/253] Use 0 to numClasses - 1, not 1 to numClasses.

---
 .../negative_log_likelihood_impl.hpp          | 10 ++--
 src/mlpack/tests/ann_layer_test.cpp           | 50 +++++++++----------
 src/mlpack/tests/callback_test.cpp            |  4 +-
 .../tests/convolutional_network_test.cpp      | 10 ++--
 src/mlpack/tests/feedforward_network_test.cpp | 30 +++++++----
 src/mlpack/tests/recurrent_network_test.cpp   | 14 +++---
 6 files changed, 63 insertions(+), 55 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp b/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
index f9020a582f..2b7dcb9fe3 100644
--- a/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
+++ b/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
@@ -35,11 +35,10 @@ NegativeLogLikelihood<InputDataType, OutputDataType>::Forward(
   ElemType output = 0;
   for (size_t i = 0; i < input.n_cols; ++i)
   {
-    size_t currentTarget = target(i) - 1;
-    Log::Assert(currentTarget >= 0 && currentTarget < input.n_rows,
+    Log::Assert(target(i) >= 0 && target(i) < input.n_rows,
         "Target class out of range.");
 
-    output -= input(currentTarget, i);
+    output -= input(target(i), i);
   }
 
   return output;
@@ -55,11 +54,10 @@ void NegativeLogLikelihood<InputDataType, OutputDataType>::Backward(
   output = arma::zeros<OutputType>(input.n_rows, input.n_cols);
   for (size_t i = 0; i < input.n_cols; ++i)
   {
-    size_t currentTarget = target(i) - 1;
-    Log::Assert(currentTarget >= 0 && currentTarget < input.n_rows,
+    Log::Assert(target(i) >= 0 && target(i) < input.n_rows,
         "Target class out of range.");
 
-    output(currentTarget, i) = -1;
+    output(target(i), i) = -1;
   }
 }
 
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 8cd06e56f5..3bba999878 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -90,7 +90,7 @@ BOOST_AUTO_TEST_CASE(GradientAddLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -422,7 +422,7 @@ BOOST_AUTO_TEST_CASE(GradientLinearLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -498,7 +498,7 @@ BOOST_AUTO_TEST_CASE(GradientNoisyLinearLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -602,7 +602,7 @@ BOOST_AUTO_TEST_CASE(GradientLinearNoBiasLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -648,7 +648,7 @@ BOOST_AUTO_TEST_CASE(JacobianNegativeLogLikelihoodLayerTest)
     init.Initialize(input, inputElements, 1);
 
     arma::mat target(1, 1);
-    target(0) = math::RandInt(1, inputElements - 1);
+    target(0) = math::RandInt(0, inputElements - 2);
 
     double error = JacobianPerformanceTest(module, input, target);
     BOOST_REQUIRE_LE(error, 1e-5);
@@ -704,7 +704,7 @@ BOOST_AUTO_TEST_CASE(GradientFlexibleReLULayerTest)
     GradientFunction()
     {
       input = arma::randu(2, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, RandomInitialization>(
           NegativeLogLikelihood<>(), RandomInitialization(0.1, 0.5));
@@ -883,7 +883,7 @@ BOOST_AUTO_TEST_CASE(LSTMRrhoTest)
 {
   const size_t rho = 5;
   arma::cube input = arma::randu(1, 1, 5);
-  arma::cube target = arma::ones(1, 1, 5);
+  arma::cube target = arma::zeros(1, 1, 5);
   RandomInitialization init(0.5, 0.5);
 
   // Create model with user defined rho parameter.
@@ -924,7 +924,7 @@ BOOST_AUTO_TEST_CASE(GradientLSTMLayerTest)
     GradientFunction()
     {
       input = arma::randu(1, 1, 5);
-      target.ones(1, 1, 5);
+      target.zeros(1, 1, 5);
       const size_t rho = 5;
 
       model = new RNN<NegativeLogLikelihood<> >(rho);
@@ -988,7 +988,7 @@ BOOST_AUTO_TEST_CASE(FastLSTMRrhoTest)
 {
   const size_t rho = 5;
   arma::cube input = arma::randu(1, 1, 5);
-  arma::cube target = arma::ones(1, 1, 5);
+  arma::cube target = arma::zeros(1, 1, 5);
   RandomInitialization init(0.5, 0.5);
 
   // Create model with user defined rho parameter.
@@ -1029,7 +1029,7 @@ BOOST_AUTO_TEST_CASE(GradientFastLSTMLayerTest)
     GradientFunction()
     {
       input = arma::randu(1, 1, 5);
-      target = arma::ones(1, 1, 5);
+      target = arma::zeros(1, 1, 5);
       const size_t rho = 5;
 
       model = new RNN<NegativeLogLikelihood<> >(rho);
@@ -1298,7 +1298,7 @@ BOOST_AUTO_TEST_CASE(GradientGRULayerTest)
     GradientFunction()
     {
       input = arma::randu(1, 1, 5);
-      target = arma::ones(1, 1, 5);
+      target = arma::zeros(1, 1, 5);
       const size_t rho = 5;
 
       model = new RNN<NegativeLogLikelihood<> >(rho);
@@ -1537,7 +1537,7 @@ BOOST_AUTO_TEST_CASE(GradientConcatLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -1606,7 +1606,7 @@ BOOST_AUTO_TEST_CASE(GradientConcatenateLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -1961,7 +1961,7 @@ BOOST_AUTO_TEST_CASE(GradientBatchNormTest)
       {
         input = arma::randn(32, 2048);
         arma::mat target;
-        target.ones(1, 2048);
+        target.zeros(1, 2048);
 
         model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
         model->Predictors() = input;
@@ -2037,7 +2037,7 @@ BOOST_AUTO_TEST_CASE(GradientVirtualBatchNormTest)
       input = arma::randn(5, 256);
       arma::mat referenceBatch = arma::mat(input.memptr(), input.n_rows, 16);
       arma::mat target;
-      target.ones(1, 256);
+      target.zeros(1, 256);
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -2099,7 +2099,7 @@ BOOST_AUTO_TEST_CASE(MiniBatchDiscriminationTest)
     {
       input = arma::randn(5, 4);
       arma::mat target;
-      target.ones(1, 4);
+      target.zeros(1, 4);
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -2278,7 +2278,7 @@ BOOST_AUTO_TEST_CASE(GradientTransposedConvolutionLayerTest)
       GradientFunction()
       {
         input = arma::linspace<arma::colvec>(0, 35, 36);
-        target = arma::mat("1");
+        target = arma::mat("0");
 
         model = new FFN<NegativeLogLikelihood<>, RandomInitialization>();
         model->Predictors() = input;
@@ -2395,7 +2395,7 @@ BOOST_AUTO_TEST_CASE(GradientAtrousConvolutionLayerTest)
     GradientFunction()
     {
       input = arma::linspace<arma::colvec>(0, 35, 36);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, RandomInitialization>();
       model->Predictors() = input;
@@ -2578,7 +2578,7 @@ BOOST_AUTO_TEST_CASE(GradientLayerNormTest)
     {
       input = arma::randn(10, 256);
       arma::mat target;
-      target.ones(1, 256);
+      target.zeros(1, 256);
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -2899,7 +2899,7 @@ BOOST_AUTO_TEST_CASE(GradientReparametrizationLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -2943,7 +2943,7 @@ BOOST_AUTO_TEST_CASE(GradientReparametrizationLayerBetaTest)
     GradientFunction()
     {
       input = arma::randu(10, 2);
-      target = arma::mat("1 1");
+      target = arma::mat("0 0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -3099,7 +3099,7 @@ BOOST_AUTO_TEST_CASE(GradientHighwayLayerTest)
     GradientFunction()
     {
       input = arma::randu(5, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -3151,7 +3151,7 @@ BOOST_AUTO_TEST_CASE(GradientSequentialLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -3202,7 +3202,7 @@ BOOST_AUTO_TEST_CASE(GradientWeightNormLayerTest)
     GradientFunction()
     {
       input = arma::randu(10, 1);
-      target = arma::mat("1");
+      target = arma::mat("0");
 
       model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
       model->Predictors() = input;
@@ -4037,7 +4037,7 @@ BOOST_AUTO_TEST_CASE(GradientBatchNormWithMiniBatchesTest)
       {
         input = arma::randn(16, 1024);
         arma::mat target;
-        target.ones(1, 1024);
+        target.zeros(1, 1024);
 
         model = new FFN<NegativeLogLikelihood<>, NguyenWidrowInitialization>();
         model->Predictors() = input;
diff --git a/src/mlpack/tests/callback_test.cpp b/src/mlpack/tests/callback_test.cpp
index a62ede95a8..6483a11890 100644
--- a/src/mlpack/tests/callback_test.cpp
+++ b/src/mlpack/tests/callback_test.cpp
@@ -92,7 +92,7 @@ BOOST_AUTO_TEST_CASE(RNNCallbackTest)
 {
   const size_t rho = 5;
   arma::cube input = arma::randu(1, 1, 5);
-  arma::cube target = arma::ones(1, 1, 5);
+  arma::cube target = arma::zeros(1, 1, 5);
   RandomInitialization init(0.5, 0.5);
 
   // Create model with user defined rho parameter.
@@ -118,7 +118,7 @@ BOOST_AUTO_TEST_CASE(RNNWithOptimizerCallbackTest)
 {
   const size_t rho = 5;
   arma::cube input = arma::randu(1, 1, 5);
-  arma::cube target = arma::ones(1, 1, 5);
+  arma::cube target = arma::zeros(1, 1, 5);
   RandomInitialization init(0.5, 0.5);
 
   // Create model with user defined rho parameter.
diff --git a/src/mlpack/tests/convolutional_network_test.cpp b/src/mlpack/tests/convolutional_network_test.cpp
index 39a7e161c3..c266e2b28b 100644
--- a/src/mlpack/tests/convolutional_network_test.cpp
+++ b/src/mlpack/tests/convolutional_network_test.cpp
@@ -47,13 +47,13 @@ BOOST_AUTO_TEST_CASE(VanillaNetworkTest)
   {
     if (i < nPoints / 2)
     {
-      // Assign label "1" to all samples with digit = 4
-      Y(i) = 1;
+      // Assign label "0" to all samples with digit = 4
+      Y(i) = 0;
     }
     else
     {
-      // Assign label "2" to all samples with digit = 9
-      Y(i) = 2;
+      // Assign label "1" to all samples with digit = 9
+      Y(i) = 1;
     }
   }
 
@@ -111,7 +111,7 @@ BOOST_AUTO_TEST_CASE(VanillaNetworkTest)
     for (size_t i = 0; i < predictionTemp.n_cols; ++i)
     {
       prediction(i) = arma::as_scalar(arma::find(
-            arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) + 1;
+            arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1));
     }
 
     size_t correct = arma::accu(prediction == Y);
diff --git a/src/mlpack/tests/feedforward_network_test.cpp b/src/mlpack/tests/feedforward_network_test.cpp
index 47842204e6..c853962f10 100644
--- a/src/mlpack/tests/feedforward_network_test.cpp
+++ b/src/mlpack/tests/feedforward_network_test.cpp
@@ -52,7 +52,7 @@ void TestNetwork(ModelType& model,
   for (size_t i = 0; i < predictionTemp.n_cols; ++i)
   {
     prediction(i) = arma::as_scalar(arma::find(
-        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) + 1;
+        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1));
   }
 
   size_t correct = arma::accu(prediction == testLabels);
@@ -71,12 +71,14 @@ BOOST_AUTO_TEST_CASE(VanillaNetworkTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // Labels should be from 0 to numClasses - 1.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // Labels should be from 0 to numClasses - 1.
 
   /*
    * Construct a feed forward network with trainData.n_rows input nodes,
@@ -120,7 +122,6 @@ BOOST_AUTO_TEST_CASE(VanillaNetworkTest)
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
   labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
-  labels += 1;
 
   FFN<NegativeLogLikelihood<> > model1;
   model1.Add<Linear<> >(dataset.n_rows, 10);
@@ -142,7 +143,6 @@ BOOST_AUTO_TEST_CASE(ForwardBackwardTest)
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
   labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
-  labels += 1;
 
   FFN<NegativeLogLikelihood<> > model;
   model.Add<Linear<> >(dataset.n_rows, 50);
@@ -189,7 +189,7 @@ BOOST_AUTO_TEST_CASE(ForwardBackwardTest)
       for (size_t i = 0; i < currentResuls.n_cols; ++i)
       {
         prediction(i) = arma::as_scalar(arma::find(
-            arma::max(currentResuls.col(i)) == currentResuls.col(i), 1)) + 1;
+            arma::max(currentResuls.col(i)) == currentResuls.col(i), 1));
       }
 
       size_t correct = arma::accu(prediction == currentLabels);
@@ -218,12 +218,14 @@ BOOST_AUTO_TEST_CASE(DropoutNetworkTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // Labels should be from 0 to numClasses - 1.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // Labels should be from 0 to numClasses - 1.
 
   /*
    * Construct a feed forward network with trainData.n_rows input nodes,
@@ -269,7 +271,6 @@ BOOST_AUTO_TEST_CASE(DropoutNetworkTest)
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
   labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
-  labels += 1;
 
   FFN<NegativeLogLikelihood<> > model1;
   model1.Add<Linear<> >(dataset.n_rows, 10);
@@ -295,7 +296,6 @@ BOOST_AUTO_TEST_CASE(HighwayNetworkTest)
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
   labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
-  labels += 1;
 
   FFN<NegativeLogLikelihood<> > model;
   model.Add<Linear<> >(dataset.n_rows, 10);
@@ -319,12 +319,14 @@ BOOST_AUTO_TEST_CASE(DropConnectNetworkTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The range should be between 0 and numClasses - 1.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The range should be between 0 and numClasses - 1.
 
  /*
   *  Construct a feed forward network with trainData.n_rows input nodes,
@@ -370,7 +372,6 @@ BOOST_AUTO_TEST_CASE(DropConnectNetworkTest)
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
   labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
-  labels += 1;
 
   FFN<NegativeLogLikelihood<> > model1;
   model1.Add<Linear<> >(dataset.n_rows, 10);
@@ -408,12 +409,14 @@ BOOST_AUTO_TEST_CASE(SerializationTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The labels should be between 0 and numClasses - 1.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The labels should be between 0 and numClasses - 1.
 
   // Vanilla neural net with logistic activation function.
   // Because 92% of the patients are not hyperthyroid the neural
@@ -457,12 +460,14 @@ BOOST_AUTO_TEST_CASE(CustomLayerTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The labels should be between 0 and numClasses - 1.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The labels should be between 0 and numClasses - 1.
 
   FFN<NegativeLogLikelihood<>, RandomInitialization, CustomLayer<> > model;
   model.Add<Linear<> >(trainData.n_rows, 8);
@@ -536,12 +541,14 @@ BOOST_AUTO_TEST_CASE(FFNTrainReturnObjective)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The labels should be between 0 and numClasses.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The labels should be between 0 and numClasses.
 
   // Vanilla neural net with logistic activation function.
   // Because 92% of the patients are not hyperthyroid the neural
@@ -606,12 +613,14 @@ BOOST_AUTO_TEST_CASE(OptimizerTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The labels should be between 0 and numClasses.
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The labels should be between 0 and numClasses.
 
   FFN<NegativeLogLikelihood<>, RandomInitialization, CustomLayer<> > model;
   model.Add<Linear<> >(trainData.n_rows, 8);
@@ -634,11 +643,12 @@ BOOST_AUTO_TEST_CASE(RBFNetworkTest)
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
+  trainLabels -= 1; // The labels should be between 0 and numClasses.
 
   arma::mat trainLabels1 = arma::zeros(3, trainData.n_cols);
   for (size_t i = 0; i < trainData.n_cols; i++)
   {
-    trainLabels1.col(i).row((trainLabels(i) - 1)) = 1;
+    trainLabels1.col(i).row(trainLabels(i)) = 1;
   }
 
   arma::mat testData;
@@ -646,6 +656,7 @@ BOOST_AUTO_TEST_CASE(RBFNetworkTest)
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
+  testLabels -= 1; // The labels should be between 0 and numClasses.
 
   /*
    * Construct a feed forward network with trainData.n_rows input nodes,
@@ -681,7 +692,7 @@ BOOST_AUTO_TEST_CASE(RBFNetworkTest)
   }
 
   arma::mat labels = arma::zeros(1, dataset.n_cols);
-  labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(1);
+  labels.submat(0, labels.n_cols / 2, 0, labels.n_cols - 1).fill(0);
 
   arma::mat labels1 = arma::zeros(2, dataset.n_cols);
 
@@ -689,7 +700,6 @@ BOOST_AUTO_TEST_CASE(RBFNetworkTest)
   {
     labels1.col(i).row(labels(i)) = 1;
   }
-  labels += 1;
 
   arma::mat centroids1;
   arma::Row<size_t> assignments;
diff --git a/src/mlpack/tests/recurrent_network_test.cpp b/src/mlpack/tests/recurrent_network_test.cpp
index 1bef406e26..4bd9fa25e1 100644
--- a/src/mlpack/tests/recurrent_network_test.cpp
+++ b/src/mlpack/tests/recurrent_network_test.cpp
@@ -93,7 +93,7 @@ BOOST_AUTO_TEST_CASE(SequenceClassificationBRNNTest)
     for (size_t i = 0; i < labelsTemp.n_cols; ++i)
     {
       const int value = arma::as_scalar(arma::find(
-          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1)) + 1;
+          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1));
       labels.tube(0, i).fill(value);
     }
 
@@ -168,7 +168,7 @@ BOOST_AUTO_TEST_CASE(SequenceClassificationTest)
     for (size_t i = 0; i < labelsTemp.n_cols; ++i)
     {
       const int value = arma::as_scalar(arma::find(
-          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1)) + 1;
+          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1));
       labels.tube(0, i).fill(value);
     }
 
@@ -212,10 +212,10 @@ BOOST_AUTO_TEST_CASE(SequenceClassificationTest)
     {
       const int predictionValue = arma::as_scalar(arma::find(
           arma::max(prediction.slice(rho - 1).col(i)) ==
-          prediction.slice(rho - 1).col(i), 1) + 1);
+          prediction.slice(rho - 1).col(i), 1));
 
       const int targetValue = arma::as_scalar(arma::find(
-          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1)) + 1;
+          arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1));
 
       if (predictionValue == targetValue)
       {
@@ -1452,15 +1452,15 @@ BOOST_AUTO_TEST_CASE(LargeRhoValueRnnTest)
   {
     const auto strLen = strlen(line);
     // Responses for NegativeLogLikelihood should be
-    // non-one-hot-encoded class IDs (from 1 to num_classes).
+    // non-one-hot-encoded class IDs (from 0 to num_classes - 1).
     MatType result(1, 1, strLen, arma::fill::zeros);
     // The response is the *next* letter in the sequence.
     for (size_t i = 0; i < strLen - 1; ++i)
     {
-      result.at(0, 0, i) = static_cast<arma::uword>(line[i + 1]) + 1.0;
+      result.at(0, 0, i) = static_cast<arma::uword>(line[i + 1]);
     }
     // The final response is empty, so we set it to class 0.
-    result.at(0, 0, strLen - 1) = 1.0;
+    result.at(0, 0, strLen - 1) = 0.0;
     return result;
   };
 

From c84a4e510b98a17d8883b928871f315cb30b4cd7 Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Tue, 11 Aug 2020 01:01:45 +0530
Subject: [PATCH 002/253] Pixel Shuffle layer. Commit 1.

---
 src/mlpack/methods/ann/layer/CMakeLists.txt   |   2 +
 src/mlpack/methods/ann/layer/layer.hpp        |   1 +
 src/mlpack/methods/ann/layer/layer_types.hpp  |   2 +
 .../methods/ann/layer/pixel_shuffle.hpp       | 179 ++++++++++++++++++
 .../methods/ann/layer/pixel_shuffle_impl.hpp  | 144 ++++++++++++++
 src/mlpack/tests/ann_layer_test.cpp           |  74 ++++++++
 6 files changed, 402 insertions(+)
 create mode 100644 src/mlpack/methods/ann/layer/pixel_shuffle.hpp
 create mode 100644 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp

diff --git a/src/mlpack/methods/ann/layer/CMakeLists.txt b/src/mlpack/methods/ann/layer/CMakeLists.txt
index c3ae086c87..b4034f580c 100644
--- a/src/mlpack/methods/ann/layer/CMakeLists.txt
+++ b/src/mlpack/methods/ann/layer/CMakeLists.txt
@@ -79,6 +79,8 @@ set(SOURCES
   noisylinear_impl.hpp
   parametric_relu.hpp
   parametric_relu_impl.hpp
+  pixel_shuffle.hpp
+  pixel_shuffle_impl.hpp
   recurrent.hpp
   recurrent_impl.hpp
   recurrent_attention.hpp
diff --git a/src/mlpack/methods/ann/layer/layer.hpp b/src/mlpack/methods/ann/layer/layer.hpp
index 8e8e00691e..6673411616 100644
--- a/src/mlpack/methods/ann/layer/layer.hpp
+++ b/src/mlpack/methods/ann/layer/layer.hpp
@@ -55,6 +55,7 @@
 #include "noisylinear.hpp"
 #include "padding.hpp"
 #include "parametric_relu.hpp"
+#include "pixel_shuffle.hpp"
 #include "recurrent_attention.hpp"
 #include "recurrent.hpp"
 #include "reinforce_normal.hpp"
diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index 0f52a24df7..9e8dd0ce36 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -40,6 +40,7 @@
 #include <mlpack/methods/ann/layer/adaptive_max_pooling.hpp>
 #include <mlpack/methods/ann/layer/adaptive_mean_pooling.hpp>
 #include <mlpack/methods/ann/layer/parametric_relu.hpp>
+#include <mlpack/methods/ann/layer/pixel_shuffle.hpp>
 #include <mlpack/methods/ann/layer/reinforce_normal.hpp>
 #include <mlpack/methods/ann/layer/reparametrization.hpp>
 #include <mlpack/methods/ann/layer/select.hpp>
@@ -272,6 +273,7 @@ using LayerTypes = boost::variant<
     NoisyLinear<arma::mat, arma::mat>*,
     Padding<arma::mat, arma::mat>*,
     PReLU<arma::mat, arma::mat>*,
+    PixelShuffle<arma::mat, arma::mat>*,
     Softmax<arma::mat, arma::mat>*,
     TransposedConvolution<NaiveConvolution<ValidConvolution>,
             NaiveConvolution<ValidConvolution>,
diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
new file mode 100644
index 0000000000..27dea9ba38
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
@@ -0,0 +1,179 @@
+/**
+ * @file methods/ann/layer/pixel_shuffle.hpp
+ * @author Anjishnu Mukherjee
+ *
+ * Definition of the PixelShuffle class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_PIXEL_SHUFFLE_HPP
+#define MLPACK_METHODS_ANN_LAYER_PIXEL_SHUFFLE_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+/**
+ * Implementation of the PixelShuffle layer.
+ *
+ * For more information, refer to the following paper,
+ *
+ * @code
+ * @article{Shi16,
+ *   author    = {Wenzhe Shi, Jose Caballero,Ferenc Huszár, Johannes Totz,
+ *               Andrew P. Aitken, Rob Bishop, Daniel Rueckert, Zehan Wang},
+ *   title     = {Real-Time Single Image and Video Super-Resolution Using an
+ *               Efficient Sub-Pixel Convolutional Neural Network},
+ *   journal   = {CoRR},
+ *   volume    = {abs/1609.05158},
+ *   year      = {2016},
+ *   url       = {https://arxiv.org/abs/1609.05158},
+ *   eprint    = {1609.05158},
+ * }
+ * @endcode
+ *
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ */
+template <
+    typename InputDataType = arma::mat,
+    typename OutputDataType = arma::mat
+>
+class PixelShuffle
+{
+ public:
+  //! Create the PixelShuffle object.
+  PixelShuffle();
+  /**
+   * Create the PixelShuffle object using the specified parameters.
+   * The number of input channels should be an integral multiple of the square
+   * of the upscale factor.
+   *
+   * @param upscaleFactor The scaling factor for Pixel Shuffle.
+   * @param height The height of each input image.
+   * @param width The width of each input image.
+   * @param size The number of channels of each input image.
+   */
+  PixelShuffle( size_t upscaleFactor,
+                size_t height,
+                size_t width,
+                size_t size);
+
+  /**
+   * Ordinary feed forward pass of the PixelShuffle layer.
+   *
+   * @param input Input data used for evaluating the specified function.
+   * @param output Resulting output activation.
+   */
+  template<typename eT>
+  void Forward(const arma::Mat<eT>& input, arma::Mat<eT>& output);
+
+  /**
+   * Ordinary feed backward pass of the PixelShuffle layer.
+   *
+   * @param * (input) The propagated input activation.
+   * @param gy The backpropagated error.
+   * @param g The calculated gradient.
+   */
+  template<typename eT>
+  void Backward(const arma::Mat<eT>& input,
+                const arma::Mat<eT>& gy,
+                arma::Mat<eT>& g);
+
+  //! Get the output parameter.
+  OutputDataType const& OutputParameter() const { return outputParameter; }
+  //! Modify the output parameter.
+  OutputDataType& OutputParameter() { return outputParameter; }
+
+  //! Get the delta.
+  OutputDataType const& Delta() const { return delta; }
+  //! Modify the delta.
+  OutputDataType& Delta() { return delta; }
+
+  //! Get the upscale factor.
+  size_t UpscaleFactor() const { return upscaleFactor; }
+
+  //! Modify the upscale factor.
+  size_t& UpscaleFactor() { return upscaleFactor; }
+
+  //! Get the input image height.
+  size_t InputHeight() const { return height; }
+
+  //! Modify the input image height.
+  size_t& InputHeight() { return height; }
+
+  //! Get the input image width.
+  size_t InputWidth() const { return width; }
+
+  //! Modify the input image width.
+  size_t& InputWidth() { return width; }
+
+  //! Get the number of input channels.
+  size_t InputChannels() const { return size; }
+
+  //! Modify the number of input channels.
+  size_t& InputChannels() { return size; }
+
+  //! Get the output image height.
+  size_t OutputHeight() const { return outputHeight; }
+
+  //! Get the output image width.
+  size_t OutputWidth() const { return outputWidth; }
+
+  //! Get the number of output channels.
+  size_t OutputChannels() const { return sizeOut; }
+
+  /**
+   * Serialize the layer.
+   */
+  template<typename Archive>
+  void serialize(Archive& ar, const unsigned int /* version */);
+
+ private:
+  //! Locally-stored delta object.
+  OutputDataType delta;
+
+  //! Locally-stored output parameter object.
+  OutputDataType outputParameter;
+
+  //! The scaling factor for Pixel Shuffle.
+  size_t upscaleFactor;
+
+  //! The height of each input image.
+  size_t height;
+
+  //! The width of each input image.
+  size_t width;
+
+  //! The number of channels of each input image.
+  size_t size;
+
+  //! The number of images in the batch.
+  size_t batchSize;
+
+  //! The height of each output image.
+  size_t outputHeight;
+
+  //! The width of each output image.
+  size_t outputWidth;
+
+  //! The number of channels of each output image.
+  size_t sizeOut;
+
+  //! A boolean used to do some internal calculations once initially.
+  bool reset;
+}; // class PixelShuffle
+
+} // namespace ann
+} // namespace mlpack
+
+// Include implementation.
+#include "pixel_shuffle_impl.hpp"
+
+#endif
diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
new file mode 100644
index 0000000000..cfbd4287b9
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -0,0 +1,144 @@
+/**
+ * @file methods/ann/layer/pixel_shuffle_impl.hpp
+ * @author Anjishnu Mukherjee
+ *
+ * Implementation of the PixelShuffle class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_PIXEL_SHUFFLE_IMPL_HPP
+#define MLPACK_METHODS_ANN_LAYER_PIXEL_SHUFFLE_IMPL_HPP
+
+// In case it hasn't yet been included.
+#include "pixel_shuffle.hpp"
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+template<typename InputDataType, typename OutputDataType>
+PixelShuffle<InputDataType, OutputDataType>::PixelShuffle() :
+    upscaleFactor(0),
+    height(0),
+    width(0),
+    size(0),
+    reset(false)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+PixelShuffle<InputDataType, OutputDataType>::PixelShuffle(
+    size_t upscaleFactor,
+    size_t height,
+    size_t width,
+    size_t size) :
+    upscaleFactor(upscaleFactor),
+    height(height),
+    width(width),
+    size(size),
+    reset(false)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void PixelShuffle<InputDataType, OutputDataType>::Forward(
+  const arma::Mat<eT>& input, arma::Mat<eT>& output)
+{
+  if(!reset)
+  {
+    batchSize = input.n_cols;
+    sizeOut = size / std::pow(upscaleFactor, 2);
+    outputHeight = height * upscaleFactor;
+    outputWidth = width * upscaleFactor;
+    reset = true;
+  }
+  output.zeros(outputHeight * outputWidth * sizeOut, batchSize);
+  for(size_t n = 0; n < batchSize; n++)
+  {
+    arma::mat inputImage = input.col(n);
+    arma::mat outputImage = output.col(n);
+    arma::cube inputTemp(const_cast<arma::mat&>(inputImage).memptr(), height,
+        width, size, false, false);
+    arma::cube outputTemp(const_cast<arma::mat&>(outputImage).memptr(),
+        outputHeight, outputWidth, sizeOut, false, false);
+
+    for (size_t c = 0; c < sizeOut ; c++)
+    {
+      for (size_t h = 0; h < outputHeight; h++)
+      {
+        for (size_t w = 0; w < outputWidth; w++)
+        {
+          size_t height_index = h / upscaleFactor;
+          size_t width_index = w / upscaleFactor;
+          size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
+              (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
+          outputTemp(w, h, c) = inputTemp(width_index, height_index,
+              channel_index);
+        }
+      }
+    }
+    output.col(n) = outputImage;
+  }
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void PixelShuffle<InputDataType, OutputDataType>::Backward(
+    const arma::Mat<eT>& input, const arma::Mat<eT>& gy, arma::Mat<eT>& g)
+{
+  g.zeros(arma::size(input));
+  for(size_t n = 0; n < batchSize; n++)
+  {
+    arma::mat gyImage = gy.col(n);
+    arma::mat gImage = g.col(n);
+    arma::cube gyTemp(const_cast<arma::mat&>(gyImage).memptr(), outputHeight,
+        outputWidth, sizeOut, false, false);
+    arma::cube gTemp(const_cast<arma::mat&>(gImage).memptr(), height, width,
+        size, false, false);
+
+    for (size_t c = 0; c < sizeOut ; c++)
+    {
+      for (size_t h = 0; h < outputHeight; h++)
+      {
+        for (size_t w = 0; w < outputWidth; w++)
+        {
+          size_t height_index = h / upscaleFactor;
+          size_t width_index = w / upscaleFactor;
+          size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
+              (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
+          gTemp(width_index, height_index, channel_index) = gyTemp(w, h, c);
+        }
+      }
+    }
+
+    g.col(n) = gImage;
+  }
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename Archive>
+void PixelShuffle<InputDataType, OutputDataType>::serialize(
+    Archive& ar,
+    const unsigned int /* version */)
+{
+  ar & BOOST_SERIALIZATION_NVP(delta);
+  ar & BOOST_SERIALIZATION_NVP(outputParameter);
+  ar & BOOST_SERIALIZATION_NVP(upscaleFactor);
+  ar & BOOST_SERIALIZATION_NVP(height);
+  ar & BOOST_SERIALIZATION_NVP(width);
+  ar & BOOST_SERIALIZATION_NVP(size);
+  ar & BOOST_SERIALIZATION_NVP(batchSize);
+  ar & BOOST_SERIALIZATION_NVP(outputHeight);
+  ar & BOOST_SERIALIZATION_NVP(outputWidth);
+  ar & BOOST_SERIALIZATION_NVP(sizeOut);
+}
+
+} // namespace ann
+} // namespace mlpack
+
+#endif
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 29e16273b8..38fec13c05 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -4186,3 +4186,77 @@ TEST_CASE("BatchNormDeterministicTest", "[ANNLayerTest]")
   // The model should switch to training mode for predicting.
   REQUIRE(boost::get<BatchNorm<>*>(module.Model()[0])->Deterministic() == 0);
 }
+
+/**
+ * Simple Test for PixelShuffle layer.
+ */
+TEST_CASE("PixelShuffleLayerTest", "[ANNLayerTest]")
+{
+  arma::mat input, output, gy, g, outputExpected, gExpected;
+  PixelShuffle<> module(2, 2, 2, 4);
+
+  // Input is a batch of 2 images, each of size (2,2) and having 4 channels.
+  input << 1 << 3 << 2 << 4 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0
+      << 0 << 0 << arma::endr << 5 << 7 << 6 << 8 << 0 << 0 << 0 << 0 << 0 << 0
+      << 0 << 0 << 0 << 0 << 0 << 0 << arma::endr;
+
+  gy << 1 << 5 << 9 << 13 << 2 << 6 << 10 << 14 << 3 << 7 << 11 << 15 << 4 << 8
+      << 12 << 16 << arma::endr << 17 << 21 << 25 << 29 << 18 << 22 << 26 << 30
+      << 19 << 23 << 27 << 31 << 20 << 24 << 28 << 32 << arma::endr;
+
+  // Calculated using torch.nn.PixelShuffle().
+  outputExpected << 1 << 0 << 3 << 0 << 0 << 0 << 0 << 0 << 2 << 0 << 4 << 0
+      << 0 << 0 << 0 << 0 << arma::endr << 5 << 0 << 7 << 0 << 0 << 0 << 0 << 0
+      << 6 << 0 << 8 << 0 << 0 << 0 << 0 << 0 << arma::endr;
+  gExpected << 1 << 9 << 3 << 11 << 5 << 13 << 7 << 15 << 2 << 10 << 4 << 12
+      << 6 << 14 << 8 << 16 << arma::endr << 17 << 25 << 19 << 27 << 21 << 29
+      << 23 << 31 << 18 << 26 << 20 << 28 << 22 << 30 << 24 << 32 << arma::endr;
+
+  input = input.t();
+  outputExpected = outputExpected.t();
+  gy = gy.t();
+  gExpected = gExpected.t();
+
+  // Check the Forward pass of the layer.
+  module.Forward(input, output);
+  CheckMatrices(output, outputExpected);
+
+  // Check the Backward pass of the layer.
+  module.Backward(input, gy, g);
+  CheckMatrices(g, gExpected);
+}
+
+/**
+ * Test that the function that can access the parameters of the
+ * PixelShuffle layer works.
+ */
+TEST_CASE("PixelShuffleLayerParametersTest", "[ANNLayerTest]")
+{
+  // Create the layer using the empty constructor.
+  PixelShuffle<> layer;
+
+  // Set the different input parameters of the layer.
+  layer.UpscaleFactor() = 2;
+  layer.InputHeight() = 2;
+  layer.InputWidth() = 2;
+  layer.InputChannels() = 4;
+
+  // Make sure we can get the parameters successfully.
+  REQUIRE(layer.UpscaleFactor() == 2);
+  REQUIRE(layer.InputHeight() == 2);
+  REQUIRE(layer.InputWidth() == 2);
+  REQUIRE(layer.InputChannels() == 4);
+
+  arma::mat input, output;
+  // Input is a batch of 2 images, each of size (2,2) and having 4 channels.
+  input << 1 << 3 << 2 << 4 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0
+      << 0 << 0 << arma::endr << 5 << 7 << 6 << 8 << 0 << 0 << 0 << 0 << 0 << 0
+      << 0 << 0 << 0 << 0 << 0 << 0 << arma::endr;
+  input = input.t();
+  layer.Forward(input, output);
+
+  // Check whether output parameters are returned correctly.
+  REQUIRE(layer.OutputHeight() == 4 );
+  REQUIRE(layer.OutputWidth() == 4);
+  REQUIRE(layer.OutputChannels() == 1);
+}

From 64dd26145a1b1c02593c105a10e2622d1aa33634 Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Fri, 14 Aug 2020 19:08:50 +0530
Subject: [PATCH 003/253] Fix style issues.

---
 src/mlpack/methods/ann/layer/pixel_shuffle.hpp      | 10 +++++-----
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp |  6 +++---
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
index 27dea9ba38..2fda7cf5f4 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
@@ -60,10 +60,10 @@ class PixelShuffle
    * @param width The width of each input image.
    * @param size The number of channels of each input image.
    */
-  PixelShuffle( size_t upscaleFactor,
-                size_t height,
-                size_t width,
-                size_t size);
+  PixelShuffle(size_t upscaleFactor,
+               size_t height,
+               size_t width,
+               size_t size);
 
   /**
    * Ordinary feed forward pass of the PixelShuffle layer.
@@ -77,7 +77,7 @@ class PixelShuffle
   /**
    * Ordinary feed backward pass of the PixelShuffle layer.
    *
-   * @param * (input) The propagated input activation.
+   * @param input The propagated input activation.
    * @param gy The backpropagated error.
    * @param g The calculated gradient.
    */
diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index cfbd4287b9..3ca2852074 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -49,7 +49,7 @@ template<typename eT>
 void PixelShuffle<InputDataType, OutputDataType>::Forward(
   const arma::Mat<eT>& input, arma::Mat<eT>& output)
 {
-  if(!reset)
+  if (!reset)
   {
     batchSize = input.n_cols;
     sizeOut = size / std::pow(upscaleFactor, 2);
@@ -58,7 +58,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
     reset = true;
   }
   output.zeros(outputHeight * outputWidth * sizeOut, batchSize);
-  for(size_t n = 0; n < batchSize; n++)
+  for (size_t n = 0; n < batchSize; n++)
   {
     arma::mat inputImage = input.col(n);
     arma::mat outputImage = output.col(n);
@@ -92,7 +92,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
     const arma::Mat<eT>& input, const arma::Mat<eT>& gy, arma::Mat<eT>& g)
 {
   g.zeros(arma::size(input));
-  for(size_t n = 0; n < batchSize; n++)
+  for (size_t n = 0; n < batchSize; n++)
   {
     arma::mat gyImage = gy.col(n);
     arma::mat gImage = g.col(n);

From 5da525cde653ee3ed2bd5c4c979bdacdbd9b7959 Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Fri, 14 Aug 2020 23:49:48 +0530
Subject: [PATCH 004/253] Fix consistency issue for constructor format.

---
 src/mlpack/methods/ann/layer/pixel_shuffle.hpp      | 8 ++++----
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
index 2fda7cf5f4..c62b0f0ecb 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
@@ -60,10 +60,10 @@ class PixelShuffle
    * @param width The width of each input image.
    * @param size The number of channels of each input image.
    */
-  PixelShuffle(size_t upscaleFactor,
-               size_t height,
-               size_t width,
-               size_t size);
+  PixelShuffle(const size_t upscaleFactor,
+               const size_t height,
+               const size_t width,
+               const size_t size);
 
   /**
    * Ordinary feed forward pass of the PixelShuffle layer.
diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 3ca2852074..d65a0c456d 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -31,10 +31,10 @@ PixelShuffle<InputDataType, OutputDataType>::PixelShuffle() :
 
 template<typename InputDataType, typename OutputDataType>
 PixelShuffle<InputDataType, OutputDataType>::PixelShuffle(
-    size_t upscaleFactor,
-    size_t height,
-    size_t width,
-    size_t size) :
+    const size_t upscaleFactor,
+    const size_t height,
+    const size_t width,
+    const size_t size) :
     upscaleFactor(upscaleFactor),
     height(height),
     width(width),

From 438cc009898dad31326636af9f3d47d908ced4af Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Tue, 25 Aug 2020 11:47:28 +0530
Subject: [PATCH 005/253] Use suggestions from code review.

---
 .../methods/ann/layer/pixel_shuffle_impl.hpp  |  1 -
 src/mlpack/tests/ann_layer_test.cpp           | 56 ++++++++++++++-----
 2 files changed, 41 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index d65a0c456d..31d137eb59 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -115,7 +115,6 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
         }
       }
     }
-
     g.col(n) = gImage;
   }
 }
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index c3c0b11edc..a1ed47db97 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -4302,38 +4302,64 @@ TEST_CASE("TransposedConvolutionWeightInitializationTest", "[ANNLayerTest]")
  */
 TEST_CASE("PixelShuffleLayerTest", "[ANNLayerTest]")
 {
-  arma::mat input, output, gy, g, outputExpected, gExpected;
-  PixelShuffle<> module(2, 2, 2, 4);
+  arma::mat input1, output1, gy1, g1, outputExpected1, gExpected1;
+  arma::mat input2, output2, gy2, g2, outputExpected2, gExpected2;
+  PixelShuffle<> module1(2, 2, 2, 4);
+  PixelShuffle<> module2(2, 2, 2, 4);
+
+  // Input is a single image, of size (2,2) and having 4 channels.
+  input1 << 1 << 3 << 2 << 4 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0
+      << 0 << 0 << arma::endr;
+  gy1 << 1 << 5 << 9 << 13 << 2 << 6 << 10 << 14 << 3 << 7 << 11 << 15 << 4 << 8
+      << 12 << 16 << arma::endr;
+
+  // Calculated using torch.nn.PixelShuffle().
+  outputExpected1 << 1 << 0 << 3 << 0 << 0 << 0 << 0 << 0 << 2 << 0 << 4 << 0
+      << 0 << 0 << 0 << 0 << arma::endr;
+  gExpected1 << 1 << 9 << 3 << 11 << 5 << 13 << 7 << 15 << 2 << 10 << 4 << 12
+      << 6 << 14 << 8 << 16 << arma::endr;
+
+  input1 = input1.t();
+  outputExpected1 = outputExpected1.t();
+  gy1 = gy1.t();
+  gExpected1 = gExpected1.t();
+
+  // Check the Forward pass of the layer.
+  module1.Forward(input1, output1);
+  CheckMatrices(output1, outputExpected1);
+
+  // Check the Backward pass of the layer.
+  module1.Backward(input1, gy1, g1);
+  CheckMatrices(g1, gExpected1);
 
   // Input is a batch of 2 images, each of size (2,2) and having 4 channels.
-  input << 1 << 3 << 2 << 4 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0
+  input2 << 1 << 3 << 2 << 4 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0 << 0
       << 0 << 0 << arma::endr << 5 << 7 << 6 << 8 << 0 << 0 << 0 << 0 << 0 << 0
       << 0 << 0 << 0 << 0 << 0 << 0 << arma::endr;
-
-  gy << 1 << 5 << 9 << 13 << 2 << 6 << 10 << 14 << 3 << 7 << 11 << 15 << 4 << 8
+  gy2 << 1 << 5 << 9 << 13 << 2 << 6 << 10 << 14 << 3 << 7 << 11 << 15 << 4 << 8
       << 12 << 16 << arma::endr << 17 << 21 << 25 << 29 << 18 << 22 << 26 << 30
       << 19 << 23 << 27 << 31 << 20 << 24 << 28 << 32 << arma::endr;
 
   // Calculated using torch.nn.PixelShuffle().
-  outputExpected << 1 << 0 << 3 << 0 << 0 << 0 << 0 << 0 << 2 << 0 << 4 << 0
+  outputExpected2 << 1 << 0 << 3 << 0 << 0 << 0 << 0 << 0 << 2 << 0 << 4 << 0
       << 0 << 0 << 0 << 0 << arma::endr << 5 << 0 << 7 << 0 << 0 << 0 << 0 << 0
       << 6 << 0 << 8 << 0 << 0 << 0 << 0 << 0 << arma::endr;
-  gExpected << 1 << 9 << 3 << 11 << 5 << 13 << 7 << 15 << 2 << 10 << 4 << 12
+  gExpected2 << 1 << 9 << 3 << 11 << 5 << 13 << 7 << 15 << 2 << 10 << 4 << 12
       << 6 << 14 << 8 << 16 << arma::endr << 17 << 25 << 19 << 27 << 21 << 29
       << 23 << 31 << 18 << 26 << 20 << 28 << 22 << 30 << 24 << 32 << arma::endr;
 
-  input = input.t();
-  outputExpected = outputExpected.t();
-  gy = gy.t();
-  gExpected = gExpected.t();
+  input2 = input2.t();
+  outputExpected2 = outputExpected2.t();
+  gy2 = gy2.t();
+  gExpected2 = gExpected2.t();
 
   // Check the Forward pass of the layer.
-  module.Forward(input, output);
-  CheckMatrices(output, outputExpected);
+  module2.Forward(input2, output2);
+  CheckMatrices(output2, outputExpected2);
 
   // Check the Backward pass of the layer.
-  module.Backward(input, gy, g);
-  CheckMatrices(g, gExpected);
+  module2.Backward(input2, gy2, g2);
+  CheckMatrices(g2, gExpected2);
 }
 
 /**

From c6cd6b860c3e56c76c2df9abe0bfe17c3bf7d1e1 Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Tue, 25 Aug 2020 16:25:52 +0530
Subject: [PATCH 006/253] FIx static analysis issue.

---
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 31d137eb59..796ee54071 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -24,6 +24,10 @@ PixelShuffle<InputDataType, OutputDataType>::PixelShuffle() :
     height(0),
     width(0),
     size(0),
+    batchSize(0),
+    outputHeight(0),
+    outputWidth(0),
+    sizeOut(0),
     reset(false)
 {
   // Nothing to do here.
@@ -39,6 +43,10 @@ PixelShuffle<InputDataType, OutputDataType>::PixelShuffle(
     height(height),
     width(width),
     size(size),
+    batchSize(0),
+    outputHeight(0),
+    outputWidth(0),
+    sizeOut(0),
     reset(false)
 {
   // Nothing to do here.

From cbb151000528700e9c57933030fc71e4c0803b70 Mon Sep 17 00:00:00 2001
From: iamshnoo <mukherjee.anjishnu@gmail.com>
Date: Wed, 26 Aug 2020 09:46:37 +0530
Subject: [PATCH 007/253] Update HISTORY.md for Pixel Shuffle layer.

---
 HISTORY.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index c04b2aeca1..ba5bb0b194 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -1,5 +1,7 @@
 ### mlpack ?.?.?
 ###### ????-??-??
+  * Added Pixel Shuffle layer (#2563).
+
   * Force CMake to show error when it didn't find Python/modules (#2568).
 
   * Refactor `ProgramInfo()` to separate out all the different

From 123635533c9daa596651e11ade8093df6f18df8f Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Mon, 30 Nov 2020 19:53:13 +0530
Subject: [PATCH 008/253] Added template to data::Split

---
 src/mlpack/core/data/split_data.hpp | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 42b7e03b3a..bbc503e385 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -169,6 +169,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  *                testData, trainLabel, testLabel, 0.3);
  * @endcode
  *
+ * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
  * @param trainData Matrix to store training data into.
@@ -179,13 +180,15 @@ void StratifiedSplit(const arma::Mat<T>& input,
  * @param shuffleData If true, the sample order is shuffled; otherwise, each
  *       sample is visited in linear order. (Default true.)
  */
-template<typename T, typename U>
+template<typename T, typename LabelsType,
+         typename = std::enable_if_t<arma::is_Row<LabelsType>::value ||
+                          arma::is_Mat_only<LabelsType>::value> >
 void Split(const arma::Mat<T>& input,
-           const arma::Row<U>& inputLabel,
+           const LabelsType& inputLabel,
            arma::Mat<T>& trainData,
            arma::Mat<T>& testData,
-           arma::Row<U>& trainLabel,
-           arma::Row<U>& testLabel,
+           LabelsType& trainLabel,
+           LabelsType& testLabel,
            const double testRatio,
            const bool shuffleData = true)
 {
@@ -295,6 +298,7 @@ void Split(const arma::Mat<T>& input,
  * auto splitResult = Split(input, label, 0.2);
  * @endcode
  *
+ * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
  * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
@@ -306,18 +310,20 @@ void Split(const arma::Mat<T>& input,
  * @return std::tuple containing trainData (arma::Mat<T>), testData
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */
-template<typename T, typename U>
-std::tuple<arma::Mat<T>, arma::Mat<T>, arma::Row<U>, arma::Row<U>>
+template<typename T, typename LabelsType,
+         typename = std::enable_if_t<arma::is_Row<LabelsType>::value ||
+                          arma::is_Mat_only<LabelsType>::value> >
+std::tuple<arma::Mat<T>, arma::Mat<T>, LabelsType, LabelsType>
 Split(const arma::Mat<T>& input,
-      const arma::Row<U>& inputLabel,
+      const LabelsType& inputLabel,
       const double testRatio,
       const bool shuffleData = true,
       const bool stratifyData = false)
 {
   arma::Mat<T> trainData;
   arma::Mat<T> testData;
-  arma::Row<U> trainLabel;
-  arma::Row<U> testLabel;
+  LabelsType trainLabel;
+  LabelsType testLabel;
 
   if (stratifyData)
   {

From cc4e5f4839a7e96e9391d40566c0cb177c3928c4 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Mon, 30 Nov 2020 21:13:31 +0530
Subject: [PATCH 009/253] Added support for field matrices

---
 src/mlpack/core/data/split_data.hpp | 222 ++++++++++++++++++++++++++++
 1 file changed, 222 insertions(+)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index bbc503e385..02395ad432 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -374,6 +374,228 @@ Split(const arma::Mat<T>& input,
                          std::move(testData));
 }
 
+/**
+ * Given an input dataset and labels, split into a training set and test set.
+ * Example usage below.  This overload places the split dataset into the four
+ * output parameters given (trainData, testData, trainLabel, and testLabel).
+ * 
+ * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
+ *
+ * @code
+ * arma::field<arma::mat> input = loadData();
+ * arma::field<arma::vec> label = loadLabel();
+ * arma::field<arma::mat> trainData;
+ * arma::field<arma::mat> testData;
+ * arma::field<arma::vec> trainLabel;
+ * arma::field<arma::vec> testLabel;
+ * math::RandomSeed(100); // Set the seed if you like.
+ *
+ * // Split the dataset into a training and test set, with 30% of the data being
+ * // held out for the test set.
+ * Split(input, label, trainData,
+ *                testData, trainLabel, testLabel, 0.3);
+ * @endcode
+ *
+ * @param input Input dataset to split.
+ * @param inputLabel Input labels to split.
+ * @param trainData FieldType to store training data into.
+ * @param testData FieldType test data into.
+ * @param trainLabel Field vector to store training labels into.
+ * @param testLabel Field vector to store test labels into.
+ * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
+ * @param shuffleData If true, the sample order is shuffled; otherwise, each
+ *       sample is visited in linear order. (Default true.)
+ */
+template <typename FieldType,
+          typename = std::enable_if_t<
+              arma::is_Col<typename FieldType::object_type>::value ||
+              arma::is_Mat_only<typename FieldType::object_type>::value>>
+void Split(FieldType& input,
+           arma::field<arma::vec>& inputLabel,
+           FieldType& trainData,
+           arma::field<arma::vec>& trainLabels,
+           FieldType& testData,
+           arma::field<arma::vec>& testLabels,
+           const double testRatio,
+           const bool shuffleData = true) 
+{
+  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
+  const size_t trainSize = input.n_cols - testSize;
+
+  trainData.set_size(1, trainSize);
+  testData.set_size(1, testSize);
+
+  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
+      input.n_cols);
+  if (shuffleData)
+    order = arma::shuffle(order);
+
+  if (trainSize > 0)
+  {
+    trainLabels.set_size(1, trainSize);
+
+    for (size_t i = 0; i < trainSize; i++)
+      trainData[i] = input(0, order(i));
+
+    for (size_t i = 0; i < trainSize; i++)
+      trainLabels(0, i) = inputLabel[i];
+  }
+
+  if (testSize <= input.n_cols)
+  {
+    for (size_t i = trainSize; i < input.n_cols - 1; i++)
+     testData[i - trainSize] = input(0, order(i));
+
+    testLabels.set_size(1, testSize);
+    for (size_t i = trainSize; i < input.n_cols; i++)
+      testLabels(0, i - trainSize) = inputLabel[i];
+  }
+}
+
+/**
+ * Given an input dataset, split into a training set and test set.
+ * Example usage below. This overload places the split dataset into the two
+ * output parameters given (trainData, testData).
+ * 
+ * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
+ *
+ * @code
+ * arma::field<arma::mat> input = loadData();
+ * arma::field<arma::mat> trainData;
+ * arma::field<arma::mat> testData;
+ * math::RandomSeed(100); // Set the seed if you like.
+ *
+ * // Split the dataset into a training and test set, with 30% of the data being
+ * // held out for the test set.
+ * Split(input, trainData, testData, 0.3);
+ * @endcode
+ *
+ * @param input Input dataset to split.
+ * @param trainData FieldType to store training data into.
+ * @param testData FieldType test data into.
+ * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
+ * @param shuffleData If true, the sample order is shuffled; otherwise, each
+ *       sample is visited in linear order. (Default true).
+ */
+template <class FieldType,
+          class = std::enable_if_t<
+              arma::is_Col<typename FieldType::object_type>::value ||
+              arma::is_Mat_only<typename FieldType::object_type>::value>>
+void Split(const FieldType& input,
+           FieldType& trainData,
+           FieldType& testData,
+           const double testRatio,
+           const bool shuffleData = true)
+{
+  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
+  const size_t trainSize = input.n_cols - testSize;
+
+  trainData.set_size(1, trainSize);
+  testData.set_size(1, testSize);
+
+  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
+      input.n_cols);
+  if (shuffleData)
+    order = arma::shuffle(order);
+
+  if (trainSize > 0)
+  {
+    for (size_t i = 0; i < trainSize; i++)
+       trainData[i] = input(0, order(i));
+  }
+
+  if (testSize <= input.n_cols)
+  {
+    for (size_t i = trainSize; i < input.n_cols - 1; i++)
+       testData[i - trainSize] = input(0, order(i));
+  }
+}
+
+/**
+ * Given an input dataset and labels, split into a training set and test set.
+ * Example usage below.  This overload returns the split dataset as a std::tuple
+ * with four elements: an FieldType containing the training data, an
+ * FieldType containing the test data, an arma::field<arma::vec> containing the
+ * training labels, and an arma::field<arma::vec> containing the test labels.
+ * 
+ * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
+ *
+ * @code
+ * arma::field<arma::mat> input = loadData();
+ * arma::field<arma::vec> label = loadLabel();
+ * auto splitResult = Split(input, label, 0.2);
+ * @endcode
+ *
+ * @param input Input dataset to split.
+ * @param inputLabel Input labels to split.
+ * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
+ * @param shuffleData If true, the sample order is shuffled; otherwise, each
+ *       sample is visited in linear order. (Default true).
+ * @return std::tuple containing trainData (FieldType), testData
+ *      (FieldType), trainLabel (arma::field<arma::vec>), and 
+ *                   testLabel (arma::field<arma::vec>).
+ */
+template <class FieldType,
+          class = std::enable_if_t<
+              arma::is_Col<typename FieldType::object_type>::value ||
+              arma::is_Mat_only<typename FieldType::object_type>::value>>
+std::tuple<FieldType, FieldType, FieldType, FieldType>
+Split(FieldType& input,
+      arma::field<arma::vec>& inputLabel,
+      const double testRatio,
+      const bool shuffleData = true)
+{
+  FieldType trainData;
+  FieldType testData;
+  arma::field<arma::vec> trainLabel;
+  arma::field<arma::vec> testLabel;
+
+  Split(input, inputLabel, trainData, testData, trainLabel, testLabel,
+    testRatio, shuffleData);
+
+  return std::make_tuple(std::move(trainData),
+                         std::move(testData),
+                         std::move(trainLabel),
+                         std::move(testLabel));
+}
+
+/**
+ * Given an input dataset, split into a training set and test set.
+ * Example usage below.  This overload returns the split dataset as a std::tuple
+ * with two elements: an FieldType containing the training data and an
+ * FieldType containing the test data.
+ * 
+ * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
+ *
+ * @code
+ * arma::field<arma::mat> input = loadData();
+ * auto splitResult = Split(input, 0.2);
+ * @endcode
+ *
+ * @param input Input dataset to split.
+ * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
+ * @param shuffleData If true, the sample order is shuffled; otherwise, each
+ *       sample is visited in linear order. (Default true).
+ * @return std::tuple containing trainData (FieldType)
+ *      and testData (FieldType).
+ */
+template <class FieldType,
+          class = std::enable_if_t<
+              arma::is_Col<typename FieldType::object_type>::value ||
+              arma::is_Mat_only<typename FieldType::object_type>::value>>
+std::tuple<FieldType, FieldType>
+Split(const FieldType& input,
+      const double testRatio,
+      const bool shuffleData = true)
+{
+  FieldType trainData;
+  FieldType testData;
+  Split(input, trainData, testData, testRatio, shuffleData);
+
+  return std::make_tuple(std::move(trainData),
+                         std::move(testData));
+}
+
 } // namespace data
 } // namespace mlpack
 

From e401c65c67a87547bed663225470875930f12693 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Mon, 30 Nov 2020 22:32:17 +0530
Subject: [PATCH 010/253] Test for field type in data::Split

---
 src/mlpack/tests/split_data_test.cpp  | 24 ++++++++++++++++++++++++
 src/mlpack/tests/test_catch_tools.hpp | 15 +++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 8de9d5f66b..996c6ccfa4 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -121,6 +121,30 @@ TEST_CASE("SplitDataResultMat", "[SplitDataTest]")
   CheckMatrices(input, concat);
 }
 
+TEST_CASE("SplitDataResultField", "[SplitDataTest]")
+{
+  field<mat> input(1, 2);
+
+  mat matA(2, 10);
+  mat matB(2, 10);
+
+  size_t count = 0; // Counter for unique sequential values.
+  matA.imbue([&count]() { return ++count; });
+  matB.imbue([&count]() { return ++count; });
+
+  input(0, 0) = matA;
+  input(0, 1) = matB;
+
+  const auto value = Split(input, 0.5, false);
+  REQUIRE(std::get<0>(value).n_cols == 1); // Train data.
+  REQUIRE(std::get<1>(value).n_cols == 1); // Test data.
+
+  field<mat> concat = {std::get<0>(value)(0), std::get<1>(value)(0)};
+  // Order matters here.
+  CheckFields(input, concat);
+}
+
+
 TEST_CASE("ZeroRatioSplitData", "[SplitDataTest]")
 {
   mat input(2, 10);
diff --git a/src/mlpack/tests/test_catch_tools.hpp b/src/mlpack/tests/test_catch_tools.hpp
index 1bac310ddc..7b34cfc150 100644
--- a/src/mlpack/tests/test_catch_tools.hpp
+++ b/src/mlpack/tests/test_catch_tools.hpp
@@ -50,6 +50,21 @@ inline void CheckMatrices(const arma::Mat<size_t>& a,
     REQUIRE(a[i] == b[i]);
 }
 
+template <typename FieldType,
+          typename = std::enable_if_t<
+              arma::is_arma_type<typename FieldType::object_type>::value>>
+// Check the values of two field types
+inline void CheckFields(const FieldType& a,
+                        const FieldType& b)
+{
+  REQUIRE(a.n_rows == b.n_rows);
+  REQUIRE(a.n_cols == b.n_cols);
+
+  for (size_t i = 0; i < a.n_slices; ++i)
+    CheckMatrices(a(i), b(i));
+}
+
+
 // Check the values of two cubes.
 inline void CheckMatrices(const arma::cube& a,
                           const arma::cube& b,

From 5b10897d762382444efa64b2dd874328e480b7a3 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 8 Dec 2020 17:04:11 -0500
Subject: [PATCH 011/253] Clean up description and use Authors@R.

---
 src/mlpack/bindings/R/mlpack/DESCRIPTION.in | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/bindings/R/mlpack/DESCRIPTION.in b/src/mlpack/bindings/R/mlpack/DESCRIPTION.in
index 9183f6bb62..dc583f0dd9 100644
--- a/src/mlpack/bindings/R/mlpack/DESCRIPTION.in
+++ b/src/mlpack/bindings/R/mlpack/DESCRIPTION.in
@@ -2,11 +2,11 @@ Package: mlpack
 Title: 'Rcpp' Integration for the 'mlpack' Library
 Version: @PACKAGE_VERSION@
 Date: @PACKAGE_DATE@
-Author: mlpack Team
-Maintainer: Ryan Curtin <ryan@ratml.org>
-Description: 'mlpack' is a fast, flexible machine learning library, written
-             in C++, that aims to provide fast, extensible implementations of
-             cutting-edge machine learning algorithms.
+Authors@R: @AUTHORS_R@
+Description: A fast, flexible machine learning library, written in C++, that
+             aims to provide fast, extensible implementations of cutting-edge
+             machine learning algorithms.  See also Curtin et al. (2018)
+             <doi:10.21105/joss.00726>.
 SystemRequirements: A C++11 compiler. Versions 4.8.*, 4.9.* or later of GCC
                     will be fine.
 License: BSD_3_clause + file LICENSE

From 724402337d43086fa3ed2b52abf6e34be218af2d Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 8 Dec 2020 17:04:26 -0500
Subject: [PATCH 012/253] Use CMake to extract Authors@R list.

---
 src/mlpack/bindings/R/CMakeLists.txt | 84 ++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index a6e8ee16e1..23a4c69139 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -87,6 +87,90 @@ if (BUILD_R_BINDINGS)
 
   string(TIMESTAMP PACKAGE_DATE "%Y-%m-%d")
 
+  # We need to generate an Authors@R list using every single contributor in
+  # COPYRIGHT.txt.  That takes a little bit of processing.
+  file(READ "${CMAKE_SOURCE_DIR}/COPYRIGHT.txt" COPYRIGHT_TXT_CONTENTS)
+  string(REGEX MATCHALL "  Copyright [0-9-]*, ([^\n]*)\n" CONTRIBUTORS_LIST
+      "${COPYRIGHT_TXT_CONTENTS}")
+
+  # These are the authors meant to be listed as 'authors' and not
+  # 'contributors'.  If you contributed specifically to the R bindings, you
+  # should probably be listed here, so if you're not, open a PR to fix it! :)
+  set(SPECIAL_AUTHORS "Yashwant Singh Parihar" "Ryan Curtin" "Dirk Eddelbuettel"
+      "James Balamuta")
+
+  string(CONCAT AUTHORS_R "c(\n"
+      "    person(\"Yashwant\", \"Singh Parihar\", "
+              "email = \"yashwantsingh.sngh@gmail.com\", "
+              "role = c(\"aut\", \"ctb\", \"cph\")),\n"
+      "    person(\"Ryan\", \"Curtin\", email = \"ryan@ratml.org\", "
+              "role = c(\"aut\", \"ctb\", \"cph\", \"cre\")),\n"
+      "    person(\"Dirk\", \"Eddelbuettel\", email = \"edd@debian.org\", "
+              "role = c(\"aut\", \"ctb\", \"cph\")),\n"
+      "    person(\"James\", \"Balamuta\", "
+              "email = \"james.balamuta@gmail.com\", "
+              "role = c(\"aut\", \"ctb\", \"cph\")),")
+  foreach (CONTRIBUTOR_LINE ${CONTRIBUTORS_LIST})
+    # Strip 'Copyright XXXX-YYYY, '.
+    string(REGEX REPLACE "^  Copyright [0-9-]*, (.*)\n$" "\\1"
+        CONTRIBUTOR_FILTERED "${CONTRIBUTOR_LINE}")
+
+    # Extract the email if it exists.
+    string(REGEX MATCH "^[^<]*<(.*)>.*$" HAS_EMAIL "${CONTRIBUTOR_FILTERED}")
+
+    # The first name is just the first space-delimited word.  (That may not
+    # always be right, but we have no way to know what is a first name and last
+    # name and therefore must assume.)
+    string(REGEX REPLACE "^([^ ]*) .*$" "\\1" CONTRIBUTOR_FIRST_NAME
+        "${CONTRIBUTOR_FILTERED}")
+
+    # Extracting the last name is just the rest of the tokens, but the regex is
+    # different depending on whether we managed to get an email.
+    if (HAS_EMAIL)
+      string(REGEX REPLACE "^[^<]*<(.*)>.*$" "\\1" CONTRIBUTOR_EMAIL
+          "${CONTRIBUTOR_FILTERED}")
+      string(REGEX MATCH "^[^ ]* (.*) <.*$" CONTRIBUTOR_LAST_NAME
+          "${CONTRIBUTOR_FILTERED}")
+      if (NOT CONTRIBUTOR_LAST_NAME)
+        set (CONTRIBUTOR_LAST_NAME "")
+      else ()
+        string(REGEX REPLACE "^[^ ]* (.*) <.*$" "\\1" CONTRIBUTOR_LAST_NAME
+            "${CONTRIBUTOR_FILTERED}")
+      endif ()
+
+      # Skip anyone already listed as an author.
+      if ("${CONTRIBUTOR_FIRST_NAME} ${CONTRIBUTOR_LAST_NAME}" IN_LIST
+          SPECIAL_AUTHORS)
+        continue()
+      endif ()
+
+      string(CONCAT AUTHORS_R "${AUTHORS_R}\n    "
+          "person(\"${CONTRIBUTOR_FIRST_NAME}\", \"${CONTRIBUTOR_LAST_NAME}\", "
+          "email = \"${CONTRIBUTOR_EMAIL}\", role = c(\"ctb\", \"cph\")),")
+
+    else ()
+      # No email is available.  So just get the last name.
+      string(REGEX MATCH "^[^ ]* (.*)$" CONTRIBUTOR_LAST_NAME
+          "${CONTRIBUTOR_FILTERED}")
+      if (NOT CONTRIBUTOR_LAST_NAME)
+        set (CONTRIBUTOR_LAST_NAME "")
+      endif ()
+
+      # Skip anyone already listed as an author.
+      if ("${CONTRIBUTOR_FIRST_NAME} ${CONTRIBUTOR_LAST_NAME}" IN_LIST
+          SPECIAL_AUTHORS)
+        continue()
+      endif ()
+
+      string(CONCAT AUTHORS_R "${AUTHORS_R}\n    "
+          "person(\"${CONTRIBUTOR_FIRST_NAME}\", \"${CONTRIBUTOR_LAST_NAME}\", "
+          "role = c(\"ctb\", \"cph\")),")
+    endif ()
+  endforeach ()
+  # We also have to remove the final comma...
+  string(REGEX REPLACE ",$" "" AUTHORS_R_OUT "${AUTHORS_R}")
+  set(AUTHORS_R "${AUTHORS_R_OUT})")
+
   configure_file(${CMAKE_SOURCE_DIR}/src/mlpack/bindings/R/mlpack/DESCRIPTION.in
                  ${CMAKE_CURRENT_BINARY_DIR}/mlpack/DESCRIPTION
                  @ONLY)

From 91a7ca1d3068456393d8073df783c2e3e386f2f5 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 8 Dec 2020 17:14:54 -0500
Subject: [PATCH 013/253] Oops, set last name correctly for no-email
 contributors.

---
 src/mlpack/bindings/R/CMakeLists.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index 23a4c69139..d2c5b46dea 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -154,6 +154,9 @@ if (BUILD_R_BINDINGS)
           "${CONTRIBUTOR_FILTERED}")
       if (NOT CONTRIBUTOR_LAST_NAME)
         set (CONTRIBUTOR_LAST_NAME "")
+      else ()
+        string(REGEX REPLACE "^[^ ]* (.*)$" "\\1" CONTRIBUTOR_LAST_NAME
+            "${CONTRIBUTOR_FILTERED}")
       endif ()
 
       # Skip anyone already listed as an author.

From 040721affc4b83adbe9cc39c1bf00e17c08ce03f Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 11 Dec 2020 17:35:51 -0500
Subject: [PATCH 014/253] floor()ing an int isn't necessary.

---
 src/mlpack/core/util/prefixedoutstream_impl.hpp | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/mlpack/core/util/prefixedoutstream_impl.hpp b/src/mlpack/core/util/prefixedoutstream_impl.hpp
index 601c81c4fc..3cb9eea353 100644
--- a/src/mlpack/core/util/prefixedoutstream_impl.hpp
+++ b/src/mlpack/core/util/prefixedoutstream_impl.hpp
@@ -178,8 +178,7 @@ PrefixedOutStream::BaseLogic(const T& val)
     if (maxVal == 0.0)
       maxVal = 1;
 
-    int maxLog = log10(maxVal);
-    maxLog = (maxLog > 0) ? floor(maxLog) + 1 : 1;
+    const int maxLog = int(log10(maxVal)) + 1;
     const int padding = 4;
     convert.width(convert.precision() + maxLog + padding);
     printVal.raw_print(convert);

From d64a0ae52bdaa1dda917f89651fea76360d39166 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 11 Dec 2020 17:36:57 -0500
Subject: [PATCH 015/253] Fix types to match available log() overloads.

---
 src/mlpack/methods/gmm/em_fit_impl.hpp | 2 +-
 src/mlpack/methods/hmm/hmm_impl.hpp    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/gmm/em_fit_impl.hpp b/src/mlpack/methods/gmm/em_fit_impl.hpp
index 6b4168bf2d..7f1a4eafd7 100644
--- a/src/mlpack/methods/gmm/em_fit_impl.hpp
+++ b/src/mlpack/methods/gmm/em_fit_impl.hpp
@@ -156,7 +156,7 @@ Estimate(const arma::mat& observations,
 
     // Calculate the new values for omega using the updated conditional
     // probabilities.
-    weights = arma::exp(probRowSums - log(observations.n_cols));
+    weights = arma::exp(probRowSums - log(1.0 * observations.n_cols));
 
     // Update values of l; calculate new log-likelihood.
     lOld = l;
diff --git a/src/mlpack/methods/hmm/hmm_impl.hpp b/src/mlpack/methods/hmm/hmm_impl.hpp
index 8e4d8a2b2f..ac75389a9e 100644
--- a/src/mlpack/methods/hmm/hmm_impl.hpp
+++ b/src/mlpack/methods/hmm/hmm_impl.hpp
@@ -193,7 +193,7 @@ double HMM<Distribution>::Train(const std::vector<arma::mat>& dataSeq)
 
     // Normalize the new initial probabilities.
     if (dataSeq.size() > 1)
-      logInitial = newLogInitial - log(dataSeq.size());
+      logInitial = newLogInitial - log(1.0 * dataSeq.size());
     else
       logInitial = newLogInitial;
 

From 2c0e1745808ddbbbfe685881ca8538b86647b29b Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 11 Dec 2020 17:37:39 -0500
Subject: [PATCH 016/253] Cleaner patch: use std::log() instead.

---
 src/mlpack/methods/gmm/em_fit_impl.hpp | 2 +-
 src/mlpack/methods/hmm/hmm_impl.hpp    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/gmm/em_fit_impl.hpp b/src/mlpack/methods/gmm/em_fit_impl.hpp
index 7f1a4eafd7..c8d8b6ca9e 100644
--- a/src/mlpack/methods/gmm/em_fit_impl.hpp
+++ b/src/mlpack/methods/gmm/em_fit_impl.hpp
@@ -156,7 +156,7 @@ Estimate(const arma::mat& observations,
 
     // Calculate the new values for omega using the updated conditional
     // probabilities.
-    weights = arma::exp(probRowSums - log(1.0 * observations.n_cols));
+    weights = arma::exp(probRowSums - std::log(observations.n_cols));
 
     // Update values of l; calculate new log-likelihood.
     lOld = l;
diff --git a/src/mlpack/methods/hmm/hmm_impl.hpp b/src/mlpack/methods/hmm/hmm_impl.hpp
index ac75389a9e..74688a1273 100644
--- a/src/mlpack/methods/hmm/hmm_impl.hpp
+++ b/src/mlpack/methods/hmm/hmm_impl.hpp
@@ -193,7 +193,7 @@ double HMM<Distribution>::Train(const std::vector<arma::mat>& dataSeq)
 
     // Normalize the new initial probabilities.
     if (dataSeq.size() > 1)
-      logInitial = newLogInitial - log(1.0 * dataSeq.size());
+      logInitial = newLogInitial - std::log(dataSeq.size());
     else
       logInitial = newLogInitial;
 

From 817ed61bb040c82a286355dceeaa3866e7ae0d27 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 11 Dec 2020 18:01:08 -0500
Subject: [PATCH 017/253] Fix duplicate names that happen to live in the same
 namespace.

---
 src/mlpack/methods/rann/ra_model.hpp      | 44 +++++++++---------
 src/mlpack/methods/rann/ra_model_impl.hpp | 54 +++++++++++------------
 src/mlpack/methods/rann/ra_search.hpp     |  2 +-
 3 files changed, 50 insertions(+), 50 deletions(-)

diff --git a/src/mlpack/methods/rann/ra_model.hpp b/src/mlpack/methods/rann/ra_model.hpp
index ed32d4a352..cadc6ad46d 100644
--- a/src/mlpack/methods/rann/ra_model.hpp
+++ b/src/mlpack/methods/rann/ra_model.hpp
@@ -37,10 +37,10 @@ using RAType = RASearch<SortPolicy,
                         TreeType>;
 
 /**
- * MonoSearchVisitor executes a monochromatic neighbor search on the given
+ * RAMonoSearchVisitor executes a monochromatic neighbor search on the given
  * RAType. We don't make any difference for different instantiation of RAType.
  */
-class MonoSearchVisitor : public boost::static_visitor<void>
+class RAMonoSearchVisitor : public boost::static_visitor<void>
 {
  private:
   //! Number of neighbors to search for.
@@ -55,10 +55,10 @@ class MonoSearchVisitor : public boost::static_visitor<void>
   template<typename RAType>
   void operator()(RAType* ra) const;
 
-  //! Construct the MonoSearchVisitor object with the given parameters.
-  MonoSearchVisitor(const size_t k,
-                    arma::Mat<size_t>& neighbors,
-                    arma::mat& distances) :
+  //! Construct the RAMonoSearchVisitor object with the given parameters.
+  RAMonoSearchVisitor(const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances) :
       k(k),
       neighbors(neighbors),
       distances(distances)
@@ -66,13 +66,13 @@ class MonoSearchVisitor : public boost::static_visitor<void>
 };
 
 /**
- * BiSearchVisitor executes a bichromatic neighbor search on the given RAType.
+ * RABiSearchVisitor executes a bichromatic neighbor search on the given RAType.
  * We use template specialization to differentiate those tree types types that
  * accept leafSize as a parameter. In these cases, before doing neighbor search
  * a query tree with proper leafSize is built from the querySet.
  */
 template<typename SortPolicy>
-class BiSearchVisitor : public boost::static_visitor<void>
+class RABiSearchVisitor : public boost::static_visitor<void>
 {
  private:
   //! The query set for the bichromatic search.
@@ -109,22 +109,22 @@ class BiSearchVisitor : public boost::static_visitor<void>
   //! Bichromatic search on the given RAType specialized for octrees.
   void operator()(RATypeT<tree::Octree>* ra) const;
 
-  //! Construct the BiSearchVisitor.
-  BiSearchVisitor(const arma::mat& querySet,
-                  const size_t k,
-                  arma::Mat<size_t>& neighbors,
-                  arma::mat& distances,
-                  const size_t leafSize);
+  //! Construct the RABiSearchVisitor.
+  RABiSearchVisitor(const arma::mat& querySet,
+                    const size_t k,
+                    arma::Mat<size_t>& neighbors,
+                    arma::mat& distances,
+                    const size_t leafSize);
 };
 
 /**
- * TrainVisitor sets the reference set to a new reference set on the given
+ * RATrainVisitor sets the reference set to a new reference set on the given
  * RAType. We use template specialization to differentiate those trees that 
  * accept leafSize as a parameter. In these cases, a reference tree with proper
  * leafSize is built from the referenceSet.
  */
 template<typename SortPolicy>
-class TrainVisitor : public boost::static_visitor<void>
+class RATrainVisitor : public boost::static_visitor<void>
 {
  private:
   //! The reference set to use for training.
@@ -155,10 +155,10 @@ class TrainVisitor : public boost::static_visitor<void>
   //! Train on the given RAType specialized for Octrees.
   void operator()(RATypeT<tree::Octree>* ra) const;
 
-  //! Construct the TrainVisitor object with the given reference set, leafSize
+  //! Construct the RATrainVisitor object with the given reference set, leafSize
   //! for BinarySpaceTrees.
-  TrainVisitor(arma::mat&& referenceSet,
-               const size_t leafSize);
+  RATrainVisitor(arma::mat&& referenceSet,
+                 const size_t leafSize);
 };
 
 /**
@@ -228,7 +228,7 @@ class SingleModeVisitor : public boost::static_visitor<bool&>
 /**
  * Exposes the referenceSet of the given RAType.
  */
-class ReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
+class RAReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
 {
  public:
   //! Return the reference set.
@@ -237,9 +237,9 @@ class ReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
 };
 
 /**
- * DeleteVisitor deletes the give RAType Instance.
+ * RADeleteVisitor deletes the give RAType Instance.
  */
-class DeleteVisitor : public boost::static_visitor<void>
+class RADeleteVisitor : public boost::static_visitor<void>
 {
  public:
   //! Delete the RAType Object.
diff --git a/src/mlpack/methods/rann/ra_model_impl.hpp b/src/mlpack/methods/rann/ra_model_impl.hpp
index 3b27bfa2d6..e66b3b268a 100644
--- a/src/mlpack/methods/rann/ra_model_impl.hpp
+++ b/src/mlpack/methods/rann/ra_model_impl.hpp
@@ -21,7 +21,7 @@ namespace neighbor {
 
 //! Monochromatic search for the given RAType instance.
 template<typename RAType>
-void MonoSearchVisitor::operator()(RAType* ra) const
+void RAMonoSearchVisitor::operator()(RAType* ra) const
 {
   if (ra)
     return ra->Search(k, neighbors, distances);
@@ -30,11 +30,11 @@ void MonoSearchVisitor::operator()(RAType* ra) const
 
 //! Save the parameters for the rank-approximate search.
 template<typename SortPolicy>
-BiSearchVisitor<SortPolicy>::BiSearchVisitor(const arma::mat& querySet,
-                                 const size_t k,
-                                 arma::Mat<size_t>& neighbors,
-                                 arma::mat& distances,
-                                 const size_t leafSize) :
+RABiSearchVisitor<SortPolicy>::RABiSearchVisitor(const arma::mat& querySet,
+                                                 const size_t k,
+                                                 arma::Mat<size_t>& neighbors,
+                                                 arma::mat& distances,
+                                                 const size_t leafSize) :
     querySet(querySet),
     k(k),
     neighbors(neighbors),
@@ -47,7 +47,7 @@ template<typename SortPolicy>
 template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
+void RABiSearchVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
 {
   if (ra)
     return ra->Search(querySet, k, neighbors, distances);
@@ -56,7 +56,7 @@ void BiSearchVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
 
 //! Bichromatic search on the given RAType specialized for KDTrees.
 template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
+void RABiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
 {
   if (ra)
     return SearchLeaf(ra);
@@ -65,7 +65,7 @@ void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
 
 //! Bichromatic search on the given RAType specialized for Octrees.
 template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
+void RABiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
 {
   if (ra)
     return SearchLeaf(ra);
@@ -75,7 +75,7 @@ void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
 //! Bichromatic search on the given RAType considering the leafSize.
 template<typename SortPolicy>
 template<typename RAType>
-void BiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
+void RABiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
 {
   if (!ra->Naive() && !ra->SingleMode())
   {
@@ -110,8 +110,8 @@ void BiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
 
 //! Save parameters for the Train.
 template<typename SortPolicy>
-TrainVisitor<SortPolicy>::TrainVisitor(arma::mat&& referenceSet,
-                                       const size_t leafSize) :
+RATrainVisitor<SortPolicy>::RATrainVisitor(arma::mat&& referenceSet,
+                                           const size_t leafSize) :
     referenceSet(std::move(referenceSet)),
     leafSize(leafSize)
 {};
@@ -121,7 +121,7 @@ template<typename SortPolicy>
 template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
+void RATrainVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
 {
   if (ra)
     return ra->Train(std::move(referenceSet));
@@ -130,7 +130,7 @@ void TrainVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
 
 //! Train on the given RAType specialized for KDTrees.
 template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
+void RATrainVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
 {
   if (ra)
     return TrainLeaf(ra);
@@ -139,7 +139,7 @@ void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
 
 //! Train on the given RAType specialized for Octrees.
 template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
+void RATrainVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
 {
   if (ra)
     return TrainLeaf(ra);
@@ -149,7 +149,7 @@ void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
 //! Train on the given RAType considering the leafSize.
 template<typename SortPolicy>
 template<typename RAType>
-void TrainVisitor<SortPolicy>::TrainLeaf(RAType* ra) const
+void RATrainVisitor<SortPolicy>::TrainLeaf(RAType* ra) const
 {
   // Build tree, if necessary
   if (ra->Naive())
@@ -226,7 +226,7 @@ bool& SingleModeVisitor::operator()(RAType* ra) const
 
 //! Exposes the referenceSet of the given RAType.
 template<typename RAType>
-const arma::mat& ReferenceSetVisitor::operator()(RAType* ra) const
+const arma::mat& RAReferenceSetVisitor::operator()(RAType* ra) const
 {
   if (ra)
     return ra->ReferenceSet();
@@ -244,7 +244,7 @@ bool& NaiveVisitor::operator()(RAType* ra) const
 
 //! For cleaning memory
 template<typename RSType>
-void DeleteVisitor::operator()(RSType* rs) const
+void RADeleteVisitor::operator()(RSType* rs) const
 {
   if (rs)
     delete rs;
@@ -292,7 +292,7 @@ template<typename SortPolicy>
 RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(const RAModel& other)
 {
   // Clear current model.
-  boost::apply_visitor(DeleteVisitor(), raSearch);
+  boost::apply_visitor(RADeleteVisitor(), raSearch);
 
   treeType = other.treeType;
   leafSize = other.leafSize;
@@ -306,7 +306,7 @@ RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(const RAModel& other)
 template<typename SortPolicy>
 RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(RAModel&& other)
 {
-  boost::apply_visitor(DeleteVisitor(), raSearch);
+  boost::apply_visitor(RADeleteVisitor(), raSearch);
 
   treeType = other.treeType;
   leafSize = other.leafSize;
@@ -327,7 +327,7 @@ RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(RAModel&& other)
 template<typename SortPolicy>
 RAModel<SortPolicy>::~RAModel()
 {
-  boost::apply_visitor(DeleteVisitor(), raSearch);
+  boost::apply_visitor(RADeleteVisitor(), raSearch);
 }
 
 template<typename SortPolicy>
@@ -342,7 +342,7 @@ void RAModel<SortPolicy>::serialize(Archive& ar,
   // This should never happen, but just in case, be clean with memory.
   if (cereal::is_loading<Archive>())
   {
-    boost::apply_visitor(DeleteVisitor(), raSearch);
+    boost::apply_visitor(RADeleteVisitor(), raSearch);
   }
 
   // We only need to serialize one of the kRANN objects.
@@ -352,7 +352,7 @@ void RAModel<SortPolicy>::serialize(Archive& ar,
 template<typename SortPolicy>
 const arma::mat& RAModel<SortPolicy>::Dataset() const
 {
-  return boost::apply_visitor(ReferenceSetVisitor(), raSearch);
+  return boost::apply_visitor(RAReferenceSetVisitor(), raSearch);
 }
 
 template<typename SortPolicy>
@@ -489,7 +489,7 @@ void RAModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
   }
 
   // Clean memory, if necessary.
-  boost::apply_visitor(DeleteVisitor(), raSearch);
+  boost::apply_visitor(RADeleteVisitor(), raSearch);
 
   this->leafSize = leafSize;
 
@@ -538,7 +538,7 @@ void RAModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
       break;
   }
 
-  TrainVisitor<SortPolicy> tn(std::move(referenceSet), leafSize);
+  RATrainVisitor<SortPolicy> tn(std::move(referenceSet), leafSize);
   boost::apply_visitor(tn, raSearch);
 
   if (!naive)
@@ -567,7 +567,7 @@ void RAModel<SortPolicy>::Search(arma::mat&& querySet,
     Log::Info << "brute-force (naive) rank-approximate search...";
   Log::Info << std::endl;
 
-  BiSearchVisitor<SortPolicy> search(querySet, k, neighbors, distances,
+  RABiSearchVisitor<SortPolicy> search(querySet, k, neighbors, distances,
       leafSize);
   boost::apply_visitor(search, raSearch);
 }
@@ -586,7 +586,7 @@ void RAModel<SortPolicy>::Search(const size_t k,
     Log::Info << "brute-force (naive) rank-approximate search...";
   Log::Info << std::endl;
 
-  MonoSearchVisitor search(k, neighbors, distances);
+  RAMonoSearchVisitor search(k, neighbors, distances);
   boost::apply_visitor(search, raSearch);
 }
 
diff --git a/src/mlpack/methods/rann/ra_search.hpp b/src/mlpack/methods/rann/ra_search.hpp
index da3f61c48d..2dd91baf68 100644
--- a/src/mlpack/methods/rann/ra_search.hpp
+++ b/src/mlpack/methods/rann/ra_search.hpp
@@ -395,7 +395,7 @@ class RASearch
 
   //! For access to mappings when building models.
   template<typename SortPol>
-  friend class TrainVisitor;
+  friend class RATrainVisitor;
 }; // class RASearch
 
 } // namespace neighbor

From eb46d8610e3337086bb42016d5df44cd835a6588 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 13 Dec 2020 18:01:06 -0500
Subject: [PATCH 018/253] Hardcode LICENSE file.

---
 src/mlpack/bindings/R/CMakeLists.txt | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index d2c5b46dea..830833b614 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -224,7 +224,7 @@ if (BUILD_R_BINDINGS)
   )
 
   set(LICENSE_SOURCES
-    "${CMAKE_SOURCE_DIR}/LICENSE.txt"
+    "${CMAKE_CURRENT_SOURCE_DIR}/mlpack/LICENSE"
   )
   add_custom_target(r_copy ALL)
 
@@ -276,10 +276,6 @@ if (BUILD_R_BINDINGS)
       COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
           ${LICENSE_SOURCES}
           ${CMAKE_CURRENT_BINARY_DIR}/mlpack)
-  add_custom_command(TARGET r_copy PRE_BUILD
-      COMMAND ${CMAKE_COMMAND} ARGS -E rename
-          "${CMAKE_CURRENT_BINARY_DIR}/mlpack/LICENSE.txt"
-          "${CMAKE_CURRENT_BINARY_DIR}/mlpack/LICENSE")
   # This file will take care of multiple definition of functions in .cpp files.
   add_custom_command(TARGET r_copy PRE_BUILD
       COMMAND ${CMAKE_COMMAND} ARGS -E touch

From 8a38ffd33137056df395159d771cd602c7931e63 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 15 Dec 2020 18:58:27 -0500
Subject: [PATCH 019/253] Add forward declaration.

---
 src/mlpack/methods/rann/ra_search.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/rann/ra_search.hpp b/src/mlpack/methods/rann/ra_search.hpp
index 2dd91baf68..3e7147f54f 100644
--- a/src/mlpack/methods/rann/ra_search.hpp
+++ b/src/mlpack/methods/rann/ra_search.hpp
@@ -40,7 +40,7 @@ namespace neighbor {
 
 // Forward declaration.
 template<typename SortPolicy>
-class TrainVisitor;
+class RATrainVisitor;
 
 /**
  * The RASearch class: This class provides a generic manner to perform

From fa1b299afc1dc74e7c1c47b572b5658ec0449b02 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 15 Dec 2020 22:23:15 -0500
Subject: [PATCH 020/253] Fix incorrect merge.

---
 .../ann/loss_functions/negative_log_likelihood_impl.hpp       | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp b/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
index f4e85dcd2b..1eace1d772 100644
--- a/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
+++ b/src/mlpack/methods/ann/loss_functions/negative_log_likelihood_impl.hpp
@@ -38,7 +38,7 @@ NegativeLogLikelihood<InputDataType, OutputDataType>::Forward(
     Log::Assert(target(i) >= 0 && target(i) < prediction.n_rows,
         "Target class out of range.");
 
-    output -= input(target(i), i);
+    output -= prediction(target(i), i);
   }
 
   return output;
@@ -57,7 +57,7 @@ void NegativeLogLikelihood<InputDataType, OutputDataType>::Backward(
     Log::Assert(target(i) >= 0 && target(i) < prediction.n_rows,
         "Target class out of range.");
 
-    output(target(i), i) = -1;
+    loss(target(i), i) = -1;
   }
 }
 

From 85c3bbc1dd5482a9e2b6f6434eef02dd465c1eb5 Mon Sep 17 00:00:00 2001
From: Anmol2001 <54476451+Anmol2001@users.noreply.github.com>
Date: Wed, 16 Dec 2020 13:37:33 +0530
Subject: [PATCH 021/253] Update pca_impl.hpp

---
 src/mlpack/methods/pca/pca_impl.hpp | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/methods/pca/pca_impl.hpp b/src/mlpack/methods/pca/pca_impl.hpp
index 360586360a..2373128320 100644
--- a/src/mlpack/methods/pca/pca_impl.hpp
+++ b/src/mlpack/methods/pca/pca_impl.hpp
@@ -61,7 +61,8 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
 
 /**
  * Apply Principal Component Analysis to the provided data set.
- *
+ * It creates matrix to store eigenvectors and 
+   that matrix need not to be passed in paramteres
  * @param data - Data matrix
  * @param transformedData - Data with PCA applied
  * @param eigVal - contains eigen values in a column vector
@@ -74,6 +75,20 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
   arma::mat eigvec;
   Apply(data, transformedData, eigVal, eigvec);
 }
+ /*This is another Overload of apply with only 2 parameteres(data & transformed data)
+ and it will create eigval and eigvec and store the corresponding values  in them
+ as the source of information are first 2 parameters only.
+ * @param data - Data matrix
+ * @param transformedData - Data with PCA applied
+ */
+template<typename DecompositionPolicy>
+void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
+                                     arma::mat& transformedData)
+{
+  arma::mat eigvec;
+  arma::vec eigVal;
+  Apply(data, transformedData, eigVal, eigvec);
+}
 
 /**
  * Use PCA for dimensionality reduction on the given dataset.  This will save

From de930500247c682dd9a45d8476f8420e09a1b63b Mon Sep 17 00:00:00 2001
From: Anmol2001 <54476451+Anmol2001@users.noreply.github.com>
Date: Wed, 16 Dec 2020 13:40:14 +0530
Subject: [PATCH 022/253] Update pca.hpp

---
 src/mlpack/methods/pca/pca.hpp | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/mlpack/methods/pca/pca.hpp b/src/mlpack/methods/pca/pca.hpp
index 594cb47344..ae973f27cb 100644
--- a/src/mlpack/methods/pca/pca.hpp
+++ b/src/mlpack/methods/pca/pca.hpp
@@ -68,6 +68,14 @@ class PCA
   void Apply(const arma::mat& data,
              arma::mat& transformedData,
              arma::vec& eigVal);
+/**
+   * Apply Principal Component Analysis to the provided data set. It is safe
+   * to pass the same matrix reference for both data and transformedData.
+   * @param data Data matrix.
+   * @param transformedData Matrix to store results of PCA in.
+   */
+  void Apply(const arma::mat& data,
+             arma::mat& transformedData);
 
   /**
    * Use PCA for dimensionality reduction on the given dataset. This will save

From 42ab241eb9beca2051128e58481b5dbc9291fb94 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Wed, 16 Dec 2020 19:13:20 -0500
Subject: [PATCH 023/253] Make sure all state values are set to zero on reset.

This will avoid unnecessary reallocations with Armadillo 10.
---
 .../methods/ann/layer/fast_lstm_impl.hpp      | 39 ++++++-----------
 src/mlpack/methods/ann/layer/lstm_impl.hpp    | 43 +++++++------------
 2 files changed, 29 insertions(+), 53 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/fast_lstm_impl.hpp b/src/mlpack/methods/ann/layer/fast_lstm_impl.hpp
index 752b132ae4..c72416bdeb 100644
--- a/src/mlpack/methods/ann/layer/fast_lstm_impl.hpp
+++ b/src/mlpack/methods/ann/layer/fast_lstm_impl.hpp
@@ -163,33 +163,20 @@ void FastLSTM<InputDataType, OutputDataType>::ResetCell(const size_t size)
   gradientStep = batchSize * size - 1;
 
   const size_t rhoBatchSize = size * batchSize;
-  if (gate.is_empty() || gate.n_cols != rhoBatchSize)
-  {
-    gate.set_size(4 * outSize, rhoBatchSize);
-    gateActivation.set_size(outSize * 3, rhoBatchSize);
-    stateActivation.set_size(outSize, rhoBatchSize);
-    cellActivation.set_size(outSize, rhoBatchSize);
-    prevError.set_size(4 * outSize, batchSize);
 
-    if (prevOutput.is_empty())
-    {
-      prevOutput = arma::zeros<OutputDataType>(outSize, batchSize);
-      cell = arma::zeros(outSize, size * batchSize);
-      cellActivationError = arma::zeros<OutputDataType>(outSize, batchSize);
-      outParameter = arma::zeros<OutputDataType>(
-          outSize, (size + 1) * batchSize);
-    }
-    else
-    {
-      // To preserve the leading zeros, recreate the object according to given
-      // size specifications, while preserving the elements as well as the
-      // layout of the elements.
-      prevOutput.resize(outSize, batchSize);
-      cell.resize(outSize, size * batchSize);
-      cellActivationError.resize(outSize, batchSize);
-      outParameter.resize(outSize, (size + 1) * batchSize);
-    }
-  }
+  // Make sure all of the matrices we use to store state are at least as large
+  // as we need.
+  gate.set_size(4 * outSize, rhoBatchSize);
+  gateActivation.set_size(outSize * 3, rhoBatchSize);
+  stateActivation.set_size(outSize, rhoBatchSize);
+  cellActivation.set_size(outSize, rhoBatchSize);
+  prevError.set_size(4 * outSize, batchSize);
+
+  // Reset stored state to zeros.
+  prevOutput.zeros(outSize, batchSize);
+  cell.zeros(outSize, size * batchSize);
+  cellActivationError.zeros(outSize, batchSize);
+  outParameter.zeros(outSize, (size + 1) * batchSize);
 }
 
 template<typename InputDataType, typename OutputDataType>
diff --git a/src/mlpack/methods/ann/layer/lstm_impl.hpp b/src/mlpack/methods/ann/layer/lstm_impl.hpp
index b1bd784194..c0aa5797be 100644
--- a/src/mlpack/methods/ann/layer/lstm_impl.hpp
+++ b/src/mlpack/methods/ann/layer/lstm_impl.hpp
@@ -145,36 +145,25 @@ void LSTM<InputDataType, OutputDataType>::ResetCell(const size_t size)
   gradientStep = batchSize * size - 1;
 
   const size_t rhoBatchSize = size * batchSize;
-  if (inputGate.is_empty() || inputGate.n_cols < rhoBatchSize)
-  {
-    inputGate.set_size(outSize, rhoBatchSize);
-    forgetGate.set_size(outSize, rhoBatchSize);
-    hiddenLayer.set_size(outSize, rhoBatchSize);
-    outputGate.set_size(outSize, rhoBatchSize);
 
-    inputGateActivation.set_size(outSize, rhoBatchSize);
-    forgetGateActivation.set_size(outSize, rhoBatchSize);
-    outputGateActivation.set_size(outSize, rhoBatchSize);
-    hiddenLayerActivation.set_size(outSize, rhoBatchSize);
+  // Make sure all of the different matrices we will use to hold parameters are
+  // at least as large as we need.
+  inputGate.set_size(outSize, rhoBatchSize);
+  forgetGate.set_size(outSize, rhoBatchSize);
+  hiddenLayer.set_size(outSize, rhoBatchSize);
+  outputGate.set_size(outSize, rhoBatchSize);
 
-    cellActivation.set_size(outSize, rhoBatchSize);
-    prevError.set_size(4 * outSize, batchSize);
+  inputGateActivation.set_size(outSize, rhoBatchSize);
+  forgetGateActivation.set_size(outSize, rhoBatchSize);
+  outputGateActivation.set_size(outSize, rhoBatchSize);
+  hiddenLayerActivation.set_size(outSize, rhoBatchSize);
 
-    if (cell.is_empty())
-    {
-      cell = arma::zeros(outSize, size * batchSize);
-      outParameter = arma::zeros<OutputDataType>(
-          outSize, (size + 1) * batchSize);
-    }
-    else
-    {
-      // To preserve the leading zeros, recreate the object according to given
-      // size specifications, while preserving the elements as well as the
-      // layout of the elements.
-      cell.resize(outSize, size * batchSize);
-      outParameter.resize(outSize, (size + 1) * batchSize);
-    }
-  }
+  cellActivation.set_size(outSize, rhoBatchSize);
+  prevError.set_size(4 * outSize, batchSize);
+
+  // Now reset recurrent values to 0.
+  cell.zeros(outSize, size * batchSize);
+  outParameter.zeros(outSize, (size + 1) * batchSize);
 }
 
 template<typename InputDataType, typename OutputDataType>

From 3b9c05ed65c79a2f139972943d89360295150740 Mon Sep 17 00:00:00 2001
From: Anmolpreet Singh <54476451+Anmol2001@users.noreply.github.com>
Date: Fri, 18 Dec 2020 23:22:13 +0530
Subject: [PATCH 024/253] Update src/mlpack/methods/pca/pca.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/methods/pca/pca.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/pca/pca.hpp b/src/mlpack/methods/pca/pca.hpp
index ae973f27cb..feae5322a5 100644
--- a/src/mlpack/methods/pca/pca.hpp
+++ b/src/mlpack/methods/pca/pca.hpp
@@ -68,7 +68,7 @@ class PCA
   void Apply(const arma::mat& data,
              arma::mat& transformedData,
              arma::vec& eigVal);
-/**
+  /**
    * Apply Principal Component Analysis to the provided data set. It is safe
    * to pass the same matrix reference for both data and transformedData.
    * @param data Data matrix.

From 8890f43c515f7cf83da80b2e4751e83b335875f2 Mon Sep 17 00:00:00 2001
From: Anmolpreet Singh <54476451+Anmol2001@users.noreply.github.com>
Date: Sun, 20 Dec 2020 13:09:11 +0530
Subject: [PATCH 025/253] Update pca_impl.hpp

made some minor style changes as suggested by @zoq
---
 src/mlpack/methods/pca/pca_impl.hpp | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/methods/pca/pca_impl.hpp b/src/mlpack/methods/pca/pca_impl.hpp
index 2373128320..ce2ecedc66 100644
--- a/src/mlpack/methods/pca/pca_impl.hpp
+++ b/src/mlpack/methods/pca/pca_impl.hpp
@@ -61,8 +61,7 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
 
 /**
  * Apply Principal Component Analysis to the provided data set.
- * It creates matrix to store eigenvectors and 
-   that matrix need not to be passed in paramteres
+ *
  * @param data - Data matrix
  * @param transformedData - Data with PCA applied
  * @param eigVal - contains eigen values in a column vector
@@ -75,9 +74,12 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
   arma::mat eigvec;
   Apply(data, transformedData, eigVal, eigvec);
 }
- /*This is another Overload of apply with only 2 parameteres(data & transformed data)
- and it will create eigval and eigvec and store the corresponding values  in them
- as the source of information are first 2 parameters only.
+    
+/**
+ * This is another Overload of apply with only 2 parameteres(data & transformed data)
+ * and it will create eigval and eigvec and store the corresponding values  in them
+ * as the source of information are first 2 parameters only.
+ *
  * @param data - Data matrix
  * @param transformedData - Data with PCA applied
  */

From e46a7476d0d558128d85b0620e122fbdf4c2aca6 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Thu, 24 Dec 2020 22:54:18 +0530
Subject: [PATCH 026/253] Added Copy and Move constructors to Multiply Layers

---
 .../methods/ann/layer/multiply_constant.hpp   | 12 +++
 .../ann/layer/multiply_constant_impl.hpp      | 40 +++++++++
 .../methods/ann/layer/multiply_merge.hpp      | 12 +++
 .../methods/ann/layer/multiply_merge_impl.hpp | 60 ++++++++++++++
 src/mlpack/methods/ann/rnn_impl.hpp           |  4 +-
 src/mlpack/tests/ann_layer_test.cpp           | 83 +++++++++++++++++++
 6 files changed, 209 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/multiply_constant.hpp b/src/mlpack/methods/ann/layer/multiply_constant.hpp
index 5817d26fbf..a9a32a19ac 100644
--- a/src/mlpack/methods/ann/layer/multiply_constant.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_constant.hpp
@@ -39,6 +39,18 @@ class MultiplyConstant
    */
   MultiplyConstant(const double scalar = 1.0);
 
+  //! Copy Constructor
+  MultiplyConstant(const MultiplyConstant& layer);
+
+  //! Move Constructor
+  MultiplyConstant(MultiplyConstant&& layer);
+
+  //! Copy assignment operator
+  MultiplyConstant& operator=(const MultiplyConstant& layer);
+
+  //! Move assignment operator
+  MultiplyConstant& operator=(MultiplyConstant&& layer);
+
   /**
    * Ordinary feed forward pass of a neural network. Multiply the input with the
    * specified constant scalar value.
diff --git a/src/mlpack/methods/ann/layer/multiply_constant_impl.hpp b/src/mlpack/methods/ann/layer/multiply_constant_impl.hpp
index 7b8cf13e0c..4c02fbd1fa 100644
--- a/src/mlpack/methods/ann/layer/multiply_constant_impl.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_constant_impl.hpp
@@ -26,6 +26,46 @@ MultiplyConstant<InputDataType, OutputDataType>::MultiplyConstant(
   // Nothing to do here.
 }
 
+template<typename InputDataType, typename OutputDataType>
+MultiplyConstant<InputDataType, OutputDataType>::MultiplyConstant(
+    const MultiplyConstant& layer) :
+    scalar(layer.scalar)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+MultiplyConstant<InputDataType, OutputDataType>::MultiplyConstant(
+    MultiplyConstant&& layer) :
+    scalar(std::move(layer.scalar))
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+MultiplyConstant<InputDataType, OutputDataType>&
+MultiplyConstant<InputDataType, OutputDataType>::operator=(
+    const MultiplyConstant& layer)
+{
+  if (this != &layer)
+  {
+    scalar = layer.scalar;
+  }
+  return *this;
+}
+
+template<typename InputDataType, typename OutputDataType>
+MultiplyConstant<InputDataType, OutputDataType>&
+MultiplyConstant<InputDataType, OutputDataType>::operator=(
+    MultiplyConstant&& layer)
+{
+  if (this != &layer)
+  {
+    scalar = std::move(layer.scalar);
+  }
+  return *this;
+}
+
 template<typename InputDataType, typename OutputDataType>
 template<typename InputType, typename OutputType>
 void MultiplyConstant<InputDataType, OutputDataType>::Forward(
diff --git a/src/mlpack/methods/ann/layer/multiply_merge.hpp b/src/mlpack/methods/ann/layer/multiply_merge.hpp
index f459ab2f81..94e4169d52 100644
--- a/src/mlpack/methods/ann/layer/multiply_merge.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_merge.hpp
@@ -50,6 +50,18 @@ class MultiplyMerge
    */
   MultiplyMerge(const bool model = false, const bool run = true);
 
+  //! Copy Constructor
+  MultiplyMerge(const MultiplyMerge& layer);
+
+  //! Move Constructor
+  MultiplyMerge(MultiplyMerge&& layer);
+
+  //! Copy assignment operator
+  MultiplyMerge& operator=(const MultiplyMerge& layer);
+
+  //! Move assignment operator
+  MultiplyMerge& operator=(MultiplyMerge&& layer);
+
   //! Destructor to release allocated memory.
   ~MultiplyMerge();
 
diff --git a/src/mlpack/methods/ann/layer/multiply_merge_impl.hpp b/src/mlpack/methods/ann/layer/multiply_merge_impl.hpp
index ee4c8ed917..29cd111482 100644
--- a/src/mlpack/methods/ann/layer/multiply_merge_impl.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_merge_impl.hpp
@@ -32,6 +32,66 @@ MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::MultiplyMerge(
   // Nothing to do here.
 }
 
+template<typename InputDataType, typename OutputDataType,
+         typename... CustomLayers>
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::MultiplyMerge(
+    const MultiplyMerge& layer) :
+    model(layer.model),
+    run(layer.run),
+    ownsLayer(layer.ownsLayer),
+    network(layer.network),
+    weights(layer.weights)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType,
+         typename... CustomLayers>
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::MultiplyMerge(
+    MultiplyMerge&& layer) :
+    model(std::move(layer.model)),
+    run(std::move(layer.run)),
+    ownsLayer(std::move(layer.ownsLayer)),
+    network(std::move(layer.network)),
+    weights(std::move(layer.weights))
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType,
+         typename... CustomLayers>
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>&
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::operator=(
+    const MultiplyMerge& layer)
+{
+  if (this != &layer)
+  {
+    model = layer.model;
+    run = layer.run;
+    ownsLayer = layer.ownsLayer;
+    network = layer.network;
+    weights = layer.weights;
+  }
+  return *this;
+}
+
+template<typename InputDataType, typename OutputDataType,
+         typename... CustomLayers>
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>&
+MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::operator=(
+    MultiplyMerge&& layer)
+{
+  if (this != &layer)
+  {
+    model = std::move(layer.model);
+    run = std::move(layer.run);
+    ownsLayer = std::move(layer.ownsLayer);
+    network = std::move(layer.network);
+    weights = std::move(layer.weights);
+  }
+  return *this;
+}
+
 template<typename InputDataType, typename OutputDataType,
          typename... CustomLayers>
 MultiplyMerge<InputDataType, OutputDataType, CustomLayers...>::~MultiplyMerge()
diff --git a/src/mlpack/methods/ann/rnn_impl.hpp b/src/mlpack/methods/ann/rnn_impl.hpp
index 75749982f5..d734778bef 100644
--- a/src/mlpack/methods/ann/rnn_impl.hpp
+++ b/src/mlpack/methods/ann/rnn_impl.hpp
@@ -85,10 +85,10 @@ RNN<OutputLayerType, InitializationRuleType, CustomLayers...>::RNN(
     targetSize(std::move(network.targetSize)),
     reset(std::move(network.reset)),
     single(std::move(network.single)),
+    network(std::move(network.network)),
     parameter(std::move(network.parameter)),
     numFunctions(std::move(network.numFunctions)),
-    deterministic(std::move(network.deterministic)),
-    network(std::move(network.network))
+    deterministic(std::move(network.deterministic))
 {
   // Nothing to do here.
 }
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 5471f4be7d..fd718d63ee 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -897,6 +897,39 @@ TEST_CASE("JacobianMultiplyConstantLayerTest", "[ANNLayerTest]")
   }
 }
 
+/**
+ * Check whether copying and moving network with MultiplyConstant is working or
+ * not.
+ */
+TEST_CASE("CheckCopyMoveMultiplyConstantTest", "[ANNLayerTest]")
+{
+  arma::mat input(2, 1000);
+  input.randu();
+
+  arma::mat output1;
+  arma::mat output2;
+  arma::mat output3;
+  arma::mat output4;
+
+  MultiplyConstant<> *module1 = new MultiplyConstant<>(3.0);
+  module1->Forward(input, output1);
+
+  MultiplyConstant<> module2 = *module1;
+  delete module1;
+
+  module2.Forward(input, output2);
+  CheckMatrices(output1, output2);
+
+  MultiplyConstant<> *module3 = new MultiplyConstant<>(3.0);
+  module3->Forward(input, output3);
+
+  MultiplyConstant<> module4(std::move(*module3));
+  delete module3;
+
+  module4.Forward(input, output4);
+  CheckMatrices(output3, output4);
+}
+
 /**
  * Jacobian HardTanH module test.
  */
@@ -2600,6 +2633,56 @@ TEST_CASE("SimpleMultiplyMergeLayerTest", "[ANNLayerTest]")
   }
 }
 
+/**
+ * Check whether copying and moving network with MultiplyMerge is working or
+ * not.
+ */
+TEST_CASE("CheckCopyMoveMultiplyMergeTest", "[ANNLayerTest]")
+{
+  arma::mat input(10, 1);
+  input.randu();
+
+  arma::mat output1;
+  arma::mat output2;
+  arma::mat output3;
+  arma::mat output4;
+
+  const size_t numMergeModules = math::RandInt(2, 10);
+
+  MultiplyMerge<> *module1 = new MultiplyMerge<>(true, false);
+  for (size_t m = 0; m < numMergeModules; ++m)
+  {
+    IdentityLayer<> identityLayer;
+    identityLayer.Forward(input, identityLayer.OutputParameter());
+
+    module1->Add<IdentityLayer<> >(identityLayer);
+  }
+
+  module1->Forward(input, output1);
+
+  MultiplyMerge<> module2 = *module1;
+  delete module1;
+
+  module2.Forward(input, output2);
+  CheckMatrices(output1, output2);
+
+  MultiplyMerge<> *module3 = new MultiplyMerge<>(true, false);
+  for (size_t m = 0; m < numMergeModules; ++m)
+  {
+    IdentityLayer<> identityLayer;
+    identityLayer.Forward(input, identityLayer.OutputParameter());
+
+    module3->Add<IdentityLayer<> >(identityLayer);
+  }
+  module3->Forward(input, output3);
+
+  MultiplyMerge<> module4(std::move(*module3));
+  delete module3;
+
+  module4.Forward(input, output4);
+  CheckMatrices(output3, output4);
+}
+
 /**
  * Simple Atrous Convolution layer test.
  */

From 266ae6e27b0d72fa547d3cde4a67d0937a781fb5 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Mon, 28 Dec 2020 13:50:06 +0530
Subject: [PATCH 027/253] added no_sanity_checks option to python bindings

---
 src/mlpack/bindings/python/mlpack/io.pxd      |  1 +
 src/mlpack/bindings/python/mlpack/io_util.hpp | 10 ++++++++++
 src/mlpack/bindings/python/print_pyx.cpp      | 17 ++++++++++++++++-
 src/mlpack/bindings/python/py_option.hpp      |  4 ++--
 src/mlpack/core/util/mlpack_main.hpp          |  2 ++
 5 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index 91d696d011..4a3a838d4c 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -50,3 +50,4 @@ cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
   void DisableBacktrace() nogil except +
   void ResetTimers() nogil except +
   void EnableTimers() nogil except +
+  void SanityCheck[T](T&) nogil except +
diff --git a/src/mlpack/bindings/python/mlpack/io_util.hpp b/src/mlpack/bindings/python/mlpack/io_util.hpp
index 3a69b06d2d..d2a8bdd4de 100644
--- a/src/mlpack/bindings/python/mlpack/io_util.hpp
+++ b/src/mlpack/bindings/python/mlpack/io_util.hpp
@@ -163,6 +163,16 @@ inline void EnableTimers()
   Timer::EnableTiming();
 }
 
+/**
+ * Sanity Check.
+ */
+template<typename T>
+inline void SanityCheck(T& matrix)
+{
+  if (matrix.has_nan())
+    Log::Fatal << "The input matrix has nan values" << std::endl;
+}
+
 } // namespace util
 } // namespace mlpack
 
diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 87a412346b..4d5bca23e9 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -78,7 +78,7 @@ void PrintPYX(const util::BindingDetails& doc,
   cout << "from io cimport SetParam, SetParamPtr, SetParamWithInfo, "
       << "GetParamPtr" << endl;
   cout << "from io cimport EnableVerbose, DisableVerbose, DisableBacktrace, "
-      << "ResetTimers, EnableTimers" << endl;
+      << "ResetTimers, EnableTimers, SanityCheck" << endl;
   cout << "from matrix_utils import to_matrix, to_matrix_with_info" << endl;
   cout << "from serialization cimport SerializeIn, SerializeOut" << endl;
   cout << endl;
@@ -206,6 +206,17 @@ void PrintPYX(const util::BindingDetails& doc,
       << "\'bool'!\")" << endl;
   cout << endl;
 
+  // Determine whether or not we have to do a sanity check.
+  cout << "  if isinstance(no_sanity_checks, bool):" << endl;
+  cout << "    if no_sanity_checks:" << endl;
+  cout << "      SetParam[cbool](<const string> 'no_sanity_checks', "
+      << "no_sanity_checks)" << endl;
+  cout << "      IO.SetPassed(<const string> 'no_sanity_checks')" << endl;
+  cout << "  else:" << endl;
+  cout << "    raise TypeError(" <<"\"'no_sanity_checks\' must have type "
+      << "\'bool'!\")" << endl;
+  cout << endl;
+
   // Do any input processing.
   for (size_t i = 0; i < inputOptions.size(); ++i)
   {
@@ -224,6 +235,10 @@ void PrintPYX(const util::BindingDetails& doc,
     cout << "  IO.SetPassed(<const string> '" << d.name << "')" << endl;
   }
 
+  // Before calling mlpackMain(), we do a sanity check if needed.
+  cout << "  if not IO.GetParam[cbool](<const string> 'no_sanity_checks'):" << endl;
+  cout << "    SanityCheck[arma.Mat[double]](IO.GetParam[arma.Mat[double]](<const string> 'training'))" << endl;
+
   // Call the method.
   cout << "  # Call the mlpack program." << endl;
   cout << "  mlpackMain()" << endl;
diff --git a/src/mlpack/bindings/python/py_option.hpp b/src/mlpack/bindings/python/py_option.hpp
index 98b9f91844..dfad0926aa 100644
--- a/src/mlpack/bindings/python/py_option.hpp
+++ b/src/mlpack/bindings/python/py_option.hpp
@@ -64,8 +64,8 @@ class PyOption
     data.required = required;
     data.input = input;
     data.loaded = false;
-    // Only "verbose" and "copy_all_inputs" will be persistent.
-    if (identifier == "verbose" || identifier == "copy_all_inputs")
+    // Only "verbose", "copy_all_inputs" and "no_sanity_checks" will be persistent.
+    if (identifier == "verbose" || identifier == "copy_all_inputs" || identifier == "no_sanity_checks")
       data.persistent = true;
     else
       data.persistent = false;
diff --git a/src/mlpack/core/util/mlpack_main.hpp b/src/mlpack/core/util/mlpack_main.hpp
index 06f6f8b060..2e2bf6fed0 100644
--- a/src/mlpack/core/util/mlpack_main.hpp
+++ b/src/mlpack/core/util/mlpack_main.hpp
@@ -230,6 +230,8 @@ PARAM_FLAG("copy_all_inputs", "If specified, all input parameters will be deep"
     " copied before the method is run.  This is useful for debugging problems "
     "where the input parameters are being modified by the algorithm, but can "
     "slow down the code.", "");
+PARAM_FLAG("no_sanity_checks", "If specified, the input matrix is checked for"
+    " nan values.", "");
 
 // Nothing else needs to be defined---the binding will use mlpackMain() as-is.
 

From 41a4cf0caa74862242bd050f79beaae144dcdd98 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 28 Dec 2020 18:22:45 -0500
Subject: [PATCH 028/253] Add missing LICENSE file.

---
 src/mlpack/bindings/R/mlpack/LICENSE | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 src/mlpack/bindings/R/mlpack/LICENSE

diff --git a/src/mlpack/bindings/R/mlpack/LICENSE b/src/mlpack/bindings/R/mlpack/LICENSE
new file mode 100644
index 0000000000..774e59e170
--- /dev/null
+++ b/src/mlpack/bindings/R/mlpack/LICENSE
@@ -0,0 +1,3 @@
+YEAR: 2020
+COPYRIGHT HOLDER: mlpack Team
+ORGANIZATION: mlpack

From f1368e25fb1779b6d865daa2956463bf3629a198 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Tue, 29 Dec 2020 14:11:22 +0530
Subject: [PATCH 029/253] made no_sanity_checks more general

---
 src/mlpack/bindings/python/mlpack/io.pxd      |  2 +-
 src/mlpack/bindings/python/mlpack/io_util.hpp | 26 ++++++++++++++++---
 src/mlpack/bindings/python/print_pyx.cpp      |  4 +--
 3 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index 4a3a838d4c..b7e77dd82d 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -50,4 +50,4 @@ cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
   void DisableBacktrace() nogil except +
   void ResetTimers() nogil except +
   void EnableTimers() nogil except +
-  void SanityCheck[T](T&) nogil except +
+  void SanityChecks() nogil except +
diff --git a/src/mlpack/bindings/python/mlpack/io_util.hpp b/src/mlpack/bindings/python/mlpack/io_util.hpp
index d2a8bdd4de..dd4755cc77 100644
--- a/src/mlpack/bindings/python/mlpack/io_util.hpp
+++ b/src/mlpack/bindings/python/mlpack/io_util.hpp
@@ -166,11 +166,29 @@ inline void EnableTimers()
 /**
  * Sanity Check.
  */
-template<typename T>
-inline void SanityCheck(T& matrix)
+void SanityChecks()
 {
-  if (matrix.has_nan())
-    Log::Fatal << "The input matrix has nan values" << std::endl;
+  std::map<std::string, util::ParamData>::iterator itr;
+  for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
+  {
+    std::string paramName = itr->first;
+    std::string paramType = itr->second.cppType;
+    if (paramType == "arma::mat")
+    {
+      if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
+    else if (paramType == "arma::colvec")
+    {
+      if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
+    else if (paramType == "arma::rowvec")
+    {
+      if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
+  }
 }
 
 } // namespace util
diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 4d5bca23e9..562212ee4e 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -78,7 +78,7 @@ void PrintPYX(const util::BindingDetails& doc,
   cout << "from io cimport SetParam, SetParamPtr, SetParamWithInfo, "
       << "GetParamPtr" << endl;
   cout << "from io cimport EnableVerbose, DisableVerbose, DisableBacktrace, "
-      << "ResetTimers, EnableTimers, SanityCheck" << endl;
+      << "ResetTimers, EnableTimers, SanityChecks" << endl;
   cout << "from matrix_utils import to_matrix, to_matrix_with_info" << endl;
   cout << "from serialization cimport SerializeIn, SerializeOut" << endl;
   cout << endl;
@@ -237,7 +237,7 @@ void PrintPYX(const util::BindingDetails& doc,
 
   // Before calling mlpackMain(), we do a sanity check if needed.
   cout << "  if not IO.GetParam[cbool](<const string> 'no_sanity_checks'):" << endl;
-  cout << "    SanityCheck[arma.Mat[double]](IO.GetParam[arma.Mat[double]](<const string> 'training'))" << endl;
+  cout << "    SanityChecks()" << endl;
 
   // Call the method.
   cout << "  # Call the mlpack program." << endl;

From 6ef1ecac3ac37dc5bafd490a2aea00a39e1c11a5 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Thu, 31 Dec 2020 20:44:56 +0530
Subject: [PATCH 030/253] added arma::Mat<size_t> and categorical data

---
 src/mlpack/bindings/python/mlpack/io.pxd      |  2 +-
 src/mlpack/bindings/python/mlpack/io_util.hpp | 24 +++++++++++++++++--
 src/mlpack/bindings/python/print_pyx.cpp      |  4 ++--
 3 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index b7e77dd82d..b7c2d5937a 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -50,4 +50,4 @@ cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
   void DisableBacktrace() nogil except +
   void ResetTimers() nogil except +
   void EnableTimers() nogil except +
-  void SanityChecks() nogil except +
+  void SanityCheck() nogil except +
diff --git a/src/mlpack/bindings/python/mlpack/io_util.hpp b/src/mlpack/bindings/python/mlpack/io_util.hpp
index dd4755cc77..8722b90833 100644
--- a/src/mlpack/bindings/python/mlpack/io_util.hpp
+++ b/src/mlpack/bindings/python/mlpack/io_util.hpp
@@ -15,7 +15,7 @@
 
 #include <mlpack/core/util/io.hpp>
 #include <mlpack/core/data/dataset_mapper.hpp>
-
+#include <iostream>
 namespace mlpack {
 namespace util {
 
@@ -166,7 +166,7 @@ inline void EnableTimers()
 /**
  * Sanity Check.
  */
-void SanityChecks()
+void SanityCheck()
 {
   std::map<std::string, util::ParamData>::iterator itr;
   for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
@@ -178,16 +178,36 @@ void SanityChecks()
       if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
         Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
     }
+    else if (paramType == "arma::Mat<size_t>")
+    {
+      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
     else if (paramType == "arma::colvec")
     {
       if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
         Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
     }
+    else if (paramType == "arma::Col<size_t>")
+    {
+      if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
     else if (paramType == "arma::rowvec")
     {
       if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
         Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
     }
+    else if (paramType == "arma::Row<size_t>")
+    {
+      if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
+    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
+    {
+      if (std::get<1>(IO::GetParam<std::tuple<data::DatasetInfo, arma::mat>>(paramName)).has_nan())
+        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
+    }
   }
 }
 
diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 562212ee4e..7487f86eda 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -78,7 +78,7 @@ void PrintPYX(const util::BindingDetails& doc,
   cout << "from io cimport SetParam, SetParamPtr, SetParamWithInfo, "
       << "GetParamPtr" << endl;
   cout << "from io cimport EnableVerbose, DisableVerbose, DisableBacktrace, "
-      << "ResetTimers, EnableTimers, SanityChecks" << endl;
+      << "ResetTimers, EnableTimers, SanityCheck" << endl;
   cout << "from matrix_utils import to_matrix, to_matrix_with_info" << endl;
   cout << "from serialization cimport SerializeIn, SerializeOut" << endl;
   cout << endl;
@@ -237,7 +237,7 @@ void PrintPYX(const util::BindingDetails& doc,
 
   // Before calling mlpackMain(), we do a sanity check if needed.
   cout << "  if not IO.GetParam[cbool](<const string> 'no_sanity_checks'):" << endl;
-  cout << "    SanityChecks()" << endl;
+  cout << "    SanityCheck()" << endl;
 
   // Call the method.
   cout << "  # Call the mlpack program." << endl;

From 22f59329614725bf5754d6c7ebd7cf7f50be041e Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Thu, 31 Dec 2020 21:09:57 +0530
Subject: [PATCH 031/253] moved SanityCheck() to IO class and changed
 no_sanity_checks to check_input_matrices

---
 src/mlpack/bindings/python/mlpack/io_util.hpp | 48 -------------------
 src/mlpack/bindings/python/print_pyx.cpp      | 20 ++++----
 src/mlpack/bindings/python/py_option.hpp      |  2 +-
 src/mlpack/core/util/io.cpp                   | 46 ++++++++++++++++++
 src/mlpack/core/util/io.hpp                   |  5 ++
 src/mlpack/core/util/mlpack_main.hpp          |  4 +-
 6 files changed, 64 insertions(+), 61 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io_util.hpp b/src/mlpack/bindings/python/mlpack/io_util.hpp
index 8722b90833..bf2ab0ee05 100644
--- a/src/mlpack/bindings/python/mlpack/io_util.hpp
+++ b/src/mlpack/bindings/python/mlpack/io_util.hpp
@@ -163,54 +163,6 @@ inline void EnableTimers()
   Timer::EnableTiming();
 }
 
-/**
- * Sanity Check.
- */
-void SanityCheck()
-{
-  std::map<std::string, util::ParamData>::iterator itr;
-  for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
-  {
-    std::string paramName = itr->first;
-    std::string paramType = itr->second.cppType;
-    if (paramType == "arma::mat")
-    {
-      if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "arma::Mat<size_t>")
-    {
-      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "arma::colvec")
-    {
-      if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "arma::Col<size_t>")
-    {
-      if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "arma::rowvec")
-    {
-      if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "arma::Row<size_t>")
-    {
-      if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
-    {
-      if (std::get<1>(IO::GetParam<std::tuple<data::DatasetInfo, arma::mat>>(paramName)).has_nan())
-        Log::Fatal << "The input " << paramName << " has nan values." << std::endl;
-    }
-  }
-}
-
 } // namespace util
 } // namespace mlpack
 
diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 7487f86eda..7fa76f6b90 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -78,7 +78,7 @@ void PrintPYX(const util::BindingDetails& doc,
   cout << "from io cimport SetParam, SetParamPtr, SetParamWithInfo, "
       << "GetParamPtr" << endl;
   cout << "from io cimport EnableVerbose, DisableVerbose, DisableBacktrace, "
-      << "ResetTimers, EnableTimers, SanityCheck" << endl;
+      << "ResetTimers, EnableTimers" << endl;
   cout << "from matrix_utils import to_matrix, to_matrix_with_info" << endl;
   cout << "from serialization cimport SerializeIn, SerializeOut" << endl;
   cout << endl;
@@ -206,14 +206,14 @@ void PrintPYX(const util::BindingDetails& doc,
       << "\'bool'!\")" << endl;
   cout << endl;
 
-  // Determine whether or not we have to do a sanity check.
-  cout << "  if isinstance(no_sanity_checks, bool):" << endl;
-  cout << "    if no_sanity_checks:" << endl;
-  cout << "      SetParam[cbool](<const string> 'no_sanity_checks', "
-      << "no_sanity_checks)" << endl;
-  cout << "      IO.SetPassed(<const string> 'no_sanity_checks')" << endl;
+  // Determine whether or not we have to check input matrices for NaN values.
+  cout << "  if isinstance(check_input_matrices, bool):" << endl;
+  cout << "    if check_input_matrices:" << endl;
+  cout << "      SetParam[cbool](<const string> 'check_input_matrices', "
+      << "check_input_matrices)" << endl;
+  cout << "      IO.SetPassed(<const string> 'check_input_matrices')" << endl;
   cout << "  else:" << endl;
-  cout << "    raise TypeError(" <<"\"'no_sanity_checks\' must have type "
+  cout << "    raise TypeError(" <<"\"'check_input_matrices\' must have type "
       << "\'bool'!\")" << endl;
   cout << endl;
 
@@ -236,8 +236,8 @@ void PrintPYX(const util::BindingDetails& doc,
   }
 
   // Before calling mlpackMain(), we do a sanity check if needed.
-  cout << "  if not IO.GetParam[cbool](<const string> 'no_sanity_checks'):" << endl;
-  cout << "    SanityCheck()" << endl;
+  cout << "  if IO.GetParam[cbool](<const string> 'check_input_matrices'):" << endl;
+  cout << "    IO.SanityCheck()" << endl;
 
   // Call the method.
   cout << "  # Call the mlpack program." << endl;
diff --git a/src/mlpack/bindings/python/py_option.hpp b/src/mlpack/bindings/python/py_option.hpp
index dfad0926aa..f6a544e65b 100644
--- a/src/mlpack/bindings/python/py_option.hpp
+++ b/src/mlpack/bindings/python/py_option.hpp
@@ -65,7 +65,7 @@ class PyOption
     data.input = input;
     data.loaded = false;
     // Only "verbose", "copy_all_inputs" and "no_sanity_checks" will be persistent.
-    if (identifier == "verbose" || identifier == "copy_all_inputs" || identifier == "no_sanity_checks")
+    if (identifier == "verbose" || identifier == "copy_all_inputs" || identifier == "check_input_matrices")
       data.persistent = true;
     else
       data.persistent = false;
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 0c8703c406..f4ed2862ca 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -267,3 +267,49 @@ void IO::ClearSettings()
   GetSingleton().aliases = persistentAliases;
   GetSingleton().functionMap = persistentFunctions;
 }
+
+void IO::SanityCheck()
+{
+  std::map<std::string, util::ParamData>::iterator itr;
+  for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
+  {
+    std::string paramName = itr->first;
+    std::string paramType = itr->second.cppType;
+    if (paramType == "arma::mat")
+    {
+      if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "arma::Mat<size_t>")
+    {
+      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "arma::colvec")
+    {
+      if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "arma::Col<size_t>")
+    {
+      if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "arma::rowvec")
+    {
+      if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "arma::Row<size_t>")
+    {
+      if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
+    {
+      if (std::get<1>(IO::GetParam<std::tuple<data::DatasetInfo, arma::mat>>(paramName)).has_nan())
+        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+    }
+  }
+}
+
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index 427142c897..d927c3b917 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -285,6 +285,11 @@ class IO
    */
   static void ClearSettings();
 
+  /**
+   * Checks all input matrices for NaN values, if found throws an exception.
+   */
+  static void SanityCheck();
+
  private:
   //! Convenience map from alias values to names.
   std::map<char, std::string> aliases;
diff --git a/src/mlpack/core/util/mlpack_main.hpp b/src/mlpack/core/util/mlpack_main.hpp
index 2e2bf6fed0..0d65513225 100644
--- a/src/mlpack/core/util/mlpack_main.hpp
+++ b/src/mlpack/core/util/mlpack_main.hpp
@@ -230,8 +230,8 @@ PARAM_FLAG("copy_all_inputs", "If specified, all input parameters will be deep"
     " copied before the method is run.  This is useful for debugging problems "
     "where the input parameters are being modified by the algorithm, but can "
     "slow down the code.", "");
-PARAM_FLAG("no_sanity_checks", "If specified, the input matrix is checked for"
-    " nan values.", "");
+PARAM_FLAG("check_input_matrices", "If specified, the input matrix is checked for"
+    " NaN values; an exception is thrown if any are found.", "");
 
 // Nothing else needs to be defined---the binding will use mlpackMain() as-is.
 

From 124d39d7e894af56b91b6ae8129d3ecdf6f7718b Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Thu, 31 Dec 2020 21:14:52 +0530
Subject: [PATCH 032/253] changed comments

---
 src/mlpack/bindings/python/print_pyx.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 7fa76f6b90..5f22d0759c 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -235,7 +235,7 @@ void PrintPYX(const util::BindingDetails& doc,
     cout << "  IO.SetPassed(<const string> '" << d.name << "')" << endl;
   }
 
-  // Before calling mlpackMain(), we do a sanity check if needed.
+  // Before calling mlpackMain(), we check input matrices for NaN values if needed.
   cout << "  if IO.GetParam[cbool](<const string> 'check_input_matrices'):" << endl;
   cout << "    IO.SanityCheck()" << endl;
 

From e5bfb40c23c4fbada1d1805410087fa94c1123e4 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Thu, 31 Dec 2020 22:31:59 +0530
Subject: [PATCH 033/253] wrapped function with Cython

---
 src/mlpack/bindings/python/mlpack/io.pxd | 4 +++-
 src/mlpack/bindings/python/print_pyx.cpp | 2 +-
 src/mlpack/core/util/io.cpp              | 3 ++-
 src/mlpack/core/util/io.hpp              | 2 +-
 4 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index b7c2d5937a..be260d1913 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -38,6 +38,9 @@ cdef extern from "<mlpack/core/util/io.hpp>" namespace "mlpack" nogil:
     @staticmethod
     void ClearSettings() nogil except +
 
+	@staticmethod
+	void SanityChecks() nogil except +
+
 cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
     namespace "mlpack::util" nogil:
   void SetParam[T](string, T&) nogil except +
@@ -50,4 +53,3 @@ cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
   void DisableBacktrace() nogil except +
   void ResetTimers() nogil except +
   void EnableTimers() nogil except +
-  void SanityCheck() nogil except +
diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 5f22d0759c..b79c9501c5 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -237,7 +237,7 @@ void PrintPYX(const util::BindingDetails& doc,
 
   // Before calling mlpackMain(), we check input matrices for NaN values if needed.
   cout << "  if IO.GetParam[cbool](<const string> 'check_input_matrices'):" << endl;
-  cout << "    IO.SanityCheck()" << endl;
+  cout << "    IO.SanityChecks()" << endl;
 
   // Call the method.
   cout << "  # Call the mlpack program." << endl;
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index f4ed2862ca..24591285dc 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -268,9 +268,10 @@ void IO::ClearSettings()
   GetSingleton().functionMap = persistentFunctions;
 }
 
-void IO::SanityCheck()
+void IO::SanityChecks()
 {
   std::map<std::string, util::ParamData>::iterator itr;
+
   for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
   {
     std::string paramName = itr->first;
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index d927c3b917..3bb9b24f1b 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -288,7 +288,7 @@ class IO
   /**
    * Checks all input matrices for NaN values, if found throws an exception.
    */
-  static void SanityCheck();
+  static void SanityChecks();
 
  private:
   //! Convenience map from alias values to names.

From c3ff8d3e621d3e0535945f979d680a30a2e8413a Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Thu, 31 Dec 2020 23:58:40 +0530
Subject: [PATCH 034/253] indentation removed

---
 src/mlpack/bindings/python/mlpack/io.pxd | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index be260d1913..7517c4e4cc 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -38,8 +38,8 @@ cdef extern from "<mlpack/core/util/io.hpp>" namespace "mlpack" nogil:
     @staticmethod
     void ClearSettings() nogil except +
 
-	@staticmethod
-	void SanityChecks() nogil except +
+    @staticmethod
+    void SanityChecks() nogil except +
 
 cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
     namespace "mlpack::util" nogil:

From ee889c79c29728de27065183bc8d0e9beb83d569 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 12:48:40 +0530
Subject: [PATCH 035/253] removed iostream

---
 src/mlpack/bindings/python/mlpack/io_util.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/bindings/python/mlpack/io_util.hpp b/src/mlpack/bindings/python/mlpack/io_util.hpp
index bf2ab0ee05..3a69b06d2d 100644
--- a/src/mlpack/bindings/python/mlpack/io_util.hpp
+++ b/src/mlpack/bindings/python/mlpack/io_util.hpp
@@ -15,7 +15,7 @@
 
 #include <mlpack/core/util/io.hpp>
 #include <mlpack/core/data/dataset_mapper.hpp>
-#include <iostream>
+
 namespace mlpack {
 namespace util {
 

From 8a8f0eaeca13ef9fcaa2cb29e44964d2369c9402 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 12:51:27 +0530
Subject: [PATCH 036/253] changed name from SanityChecks() to
 CheckInputMatrices()

---
 src/mlpack/bindings/python/print_pyx.cpp | 2 +-
 src/mlpack/core/util/io.cpp              | 2 +-
 src/mlpack/core/util/io.hpp              | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index b79c9501c5..5248b6b0be 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -237,7 +237,7 @@ void PrintPYX(const util::BindingDetails& doc,
 
   // Before calling mlpackMain(), we check input matrices for NaN values if needed.
   cout << "  if IO.GetParam[cbool](<const string> 'check_input_matrices'):" << endl;
-  cout << "    IO.SanityChecks()" << endl;
+  cout << "    IO.CheckInputMatrices()" << endl;
 
   // Call the method.
   cout << "  # Call the mlpack program." << endl;
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 24591285dc..fc2e310e4b 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -268,7 +268,7 @@ void IO::ClearSettings()
   GetSingleton().functionMap = persistentFunctions;
 }
 
-void IO::SanityChecks()
+void IO::CheckInputMatrices()
 {
   std::map<std::string, util::ParamData>::iterator itr;
 
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index 3bb9b24f1b..d4f5cc7a17 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -288,7 +288,7 @@ class IO
   /**
    * Checks all input matrices for NaN values, if found throws an exception.
    */
-  static void SanityChecks();
+  static void CheckInputMatrices();
 
  private:
   //! Convenience map from alias values to names.

From 62c9f50e5c945952606a61cee9a947bbd3d43aa6 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 13:03:57 +0530
Subject: [PATCH 037/253] made single block in print_pyx.cpp

---
 src/mlpack/bindings/python/print_pyx.cpp | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/src/mlpack/bindings/python/print_pyx.cpp b/src/mlpack/bindings/python/print_pyx.cpp
index 5248b6b0be..6853c969da 100644
--- a/src/mlpack/bindings/python/print_pyx.cpp
+++ b/src/mlpack/bindings/python/print_pyx.cpp
@@ -206,17 +206,6 @@ void PrintPYX(const util::BindingDetails& doc,
       << "\'bool'!\")" << endl;
   cout << endl;
 
-  // Determine whether or not we have to check input matrices for NaN values.
-  cout << "  if isinstance(check_input_matrices, bool):" << endl;
-  cout << "    if check_input_matrices:" << endl;
-  cout << "      SetParam[cbool](<const string> 'check_input_matrices', "
-      << "check_input_matrices)" << endl;
-  cout << "      IO.SetPassed(<const string> 'check_input_matrices')" << endl;
-  cout << "  else:" << endl;
-  cout << "    raise TypeError(" <<"\"'check_input_matrices\' must have type "
-      << "\'bool'!\")" << endl;
-  cout << endl;
-
   // Do any input processing.
   for (size_t i = 0; i < inputOptions.size(); ++i)
   {
@@ -235,8 +224,14 @@ void PrintPYX(const util::BindingDetails& doc,
     cout << "  IO.SetPassed(<const string> '" << d.name << "')" << endl;
   }
 
+  // Checking the type of check_input_matrices parameter.
+  cout << "  if not isinstance(check_input_matrices, bool):" << endl;
+  cout << "    raise TypeError(" <<"\"'check_input_matrices\' must have type "
+      << "\'bool'!\")" << endl;
+  cout << endl;
+
   // Before calling mlpackMain(), we check input matrices for NaN values if needed.
-  cout << "  if IO.GetParam[cbool](<const string> 'check_input_matrices'):" << endl;
+  cout << "  if check_input_matrices:" << endl;
   cout << "    IO.CheckInputMatrices()" << endl;
 
   // Call the method.

From be82a0d85ce714d8c865125b8a1d24b080478161 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 13:15:28 +0530
Subject: [PATCH 038/253] reduced num of chars per line in io.cpp

---
 src/mlpack/core/util/io.cpp | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index fc2e310e4b..4e1771e705 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -270,46 +270,48 @@ void IO::ClearSettings()
 
 void IO::CheckInputMatrices()
 {
+  typedef typename std::tuple<data::DatasetInfo, arma::mat> TupleType;
   std::map<std::string, util::ParamData>::iterator itr;
 
   for (itr = IO::Parameters().begin(); itr != IO::Parameters().end(); ++itr)
   {
     std::string paramName = itr->first;
     std::string paramType = itr->second.cppType;
+    std::string errMsg = "The input " + paramName + " has NaN values.";
     if (paramType == "arma::mat")
     {
       if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "arma::Mat<size_t>")
     {
       if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "arma::colvec")
     {
       if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "arma::Col<size_t>")
     {
       if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "arma::rowvec")
     {
       if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "arma::Row<size_t>")
     {
       if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+        Log::Fatal << errMsg << std::endl;
     }
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
     {
-      if (std::get<1>(IO::GetParam<std::tuple<data::DatasetInfo, arma::mat>>(paramName)).has_nan())
-        Log::Fatal << "The input " << paramName << " has NaN values." << std::endl;
+      if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_nan())
+        Log::Fatal << errMsg << std::endl;
     }
   }
 }

From 990ef5347ad1aff53e3587e59efcb1ea272db868 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 13:20:02 +0530
Subject: [PATCH 039/253] reduced num of chars per line in py_option.hpp

---
 src/mlpack/bindings/python/py_option.hpp | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/bindings/python/py_option.hpp b/src/mlpack/bindings/python/py_option.hpp
index f6a544e65b..0a62afc709 100644
--- a/src/mlpack/bindings/python/py_option.hpp
+++ b/src/mlpack/bindings/python/py_option.hpp
@@ -64,8 +64,10 @@ class PyOption
     data.required = required;
     data.input = input;
     data.loaded = false;
-    // Only "verbose", "copy_all_inputs" and "no_sanity_checks" will be persistent.
-    if (identifier == "verbose" || identifier == "copy_all_inputs" || identifier == "check_input_matrices")
+    // Only "verbose", "copy_all_inputs" and "check_input_matrices"
+    //  will be persistent.
+    if (identifier == "verbose" || identifier == "copy_all_inputs" ||
+        identifier == "check_input_matrices")
       data.persistent = true;
     else
       data.persistent = false;

From 7d6a2093dd07108f65ff5f76801b8a6736c9f4ee Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Sat, 2 Jan 2021 15:05:16 +0530
Subject: [PATCH 040/253] changed function name while wrapping

---
 src/mlpack/bindings/python/mlpack/io.pxd | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/bindings/python/mlpack/io.pxd b/src/mlpack/bindings/python/mlpack/io.pxd
index 7517c4e4cc..67961d59c9 100644
--- a/src/mlpack/bindings/python/mlpack/io.pxd
+++ b/src/mlpack/bindings/python/mlpack/io.pxd
@@ -39,7 +39,7 @@ cdef extern from "<mlpack/core/util/io.hpp>" namespace "mlpack" nogil:
     void ClearSettings() nogil except +
 
     @staticmethod
-    void SanityChecks() nogil except +
+    void CheckInputMatrices() nogil except +
 
 cdef extern from "<mlpack/bindings/python/mlpack/io_util.hpp>" \
     namespace "mlpack::util" nogil:

From 49f53e67f8c18e66a1396f02ec15af605a126f05 Mon Sep 17 00:00:00 2001
From: Ayush <ayushsingh11@yahoo.in>
Date: Sat, 2 Jan 2021 20:06:53 +0530
Subject: [PATCH 041/253] WeightSize function for multihead_attention,
 multiply_constant and multiply_merge

---
 .../methods/ann/layer/multihead_attention.hpp    |  3 +++
 .../ann/layer/multihead_attention_impl.hpp       |  2 +-
 .../methods/ann/layer/multiply_constant.hpp      |  3 +++
 src/mlpack/methods/ann/layer/multiply_merge.hpp  |  3 +++
 src/mlpack/tests/ann_visitor_test.cpp            | 16 ++++++++++++++++
 5 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/multihead_attention.hpp b/src/mlpack/methods/ann/layer/multihead_attention.hpp
index ec079d197d..0c2713c0e8 100644
--- a/src/mlpack/methods/ann/layer/multihead_attention.hpp
+++ b/src/mlpack/methods/ann/layer/multihead_attention.hpp
@@ -120,6 +120,9 @@ class MultiheadAttention
                 const arma::Mat<eT>& error,
                 arma::Mat<eT>& gradient);
 
+  //! Get the size of the weights.
+  size_t WeightSize() const { return (4 * (embedDim + 1) * embedDim); }
+
   /**
    * Serialize the layer.
    */
diff --git a/src/mlpack/methods/ann/layer/multihead_attention_impl.hpp b/src/mlpack/methods/ann/layer/multihead_attention_impl.hpp
index d2da8788e9..3d687d93af 100644
--- a/src/mlpack/methods/ann/layer/multihead_attention_impl.hpp
+++ b/src/mlpack/methods/ann/layer/multihead_attention_impl.hpp
@@ -54,7 +54,7 @@ MultiheadAttention(
   }
 
   headDim = embedDim / numHeads;
-  weights.set_size(4 * (embedDim + 1) * embedDim, 1);
+  weights.set_size(WeightSize(), 1);
 }
 
 template <typename InputDataType, typename OutputDataType,
diff --git a/src/mlpack/methods/ann/layer/multiply_constant.hpp b/src/mlpack/methods/ann/layer/multiply_constant.hpp
index 5817d26fbf..7ce5c1248a 100644
--- a/src/mlpack/methods/ann/layer/multiply_constant.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_constant.hpp
@@ -75,6 +75,9 @@ class MultiplyConstant
   //! Modify the scalar multiplier.
   double& Scalar() { return scalar; }
 
+  //! Get the size of the weights.
+  size_t WeightSize() const { return 0; }
+
   /**
    * Serialize the layer.
    */
diff --git a/src/mlpack/methods/ann/layer/multiply_merge.hpp b/src/mlpack/methods/ann/layer/multiply_merge.hpp
index f459ab2f81..d79818653d 100644
--- a/src/mlpack/methods/ann/layer/multiply_merge.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_merge.hpp
@@ -135,6 +135,9 @@ class MultiplyMerge
   //! Modify the parameters.
   OutputDataType& Parameters() { return weights; }
 
+  //! Get the size of the weights.
+  size_t WeightSize() const { return 0; }
+
   /**
    * Serialize the layer.
    */
diff --git a/src/mlpack/tests/ann_visitor_test.cpp b/src/mlpack/tests/ann_visitor_test.cpp
index e5d1310368..2bd9651085 100644
--- a/src/mlpack/tests/ann_visitor_test.cpp
+++ b/src/mlpack/tests/ann_visitor_test.cpp
@@ -205,3 +205,19 @@ TEST_CASE("WeightSizeVisitorTestForNoisyLinearLayer", "[ANNVisitorTest]")
 
   CheckCorrectnessOfWeightSize(noisyLinearLayer);
 }
+
+/**
+ * Test that WeightSizeVisitor works properly for Multihead Attention layer.
+ */
+TEST_CASE("WeightSizeVisitorTestForMultiheadAttentionLayer", "[ANNVisitorTest]")
+{
+  size_t randomtgtSeqLen = arma::randi(arma::distr_param(1, 100));
+  size_t randomsrcSeqLen = arma::randi(arma::distr_param(1, 100));
+  size_t randomembedDim = 768;
+  size_t randomnumHeads = 12;
+
+  LayerTypes<> MultiheadAttentionLayer = new MultiheadAttention<>(randomtgtSeqLen,
+      randomsrcSeqLen, randomembedDim, randomnumHeads);
+
+  CheckCorrectnessOfWeightSize(MultiheadAttentionLayer);
+}

From bc5fc040cbd3daa1f09e2ed11e5eb1834eeb7c52 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 3 Jan 2021 16:50:35 -0500
Subject: [PATCH 042/253] First attempt at a solution.

---
 src/mlpack/bindings/python/CMakeLists.txt      | 10 ++++++++--
 src/mlpack/bindings/python/PythonInstall.cmake |  4 ++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/bindings/python/CMakeLists.txt b/src/mlpack/bindings/python/CMakeLists.txt
index 65490997c3..c36a026590 100644
--- a/src/mlpack/bindings/python/CMakeLists.txt
+++ b/src/mlpack/bindings/python/CMakeLists.txt
@@ -214,14 +214,20 @@ add_custom_command(TARGET python POST_BUILD
 add_dependencies(python python_configured)
 
 # Configure installation script file.
+if (NOT PYTHON_INSTALL_PREFIX)
+  set(PYTHON_INSTALL_PREFIX "${CMAKE_INSTALL_PREFIX}")
+endif ()
+
 execute_process(COMMAND ${PYTHON_EXECUTABLE}
-    "${CMAKE_CURRENT_SOURCE_DIR}/print_python_version.py" "${CMAKE_INSTALL_PREFIX}"
+    "${CMAKE_CURRENT_SOURCE_DIR}/print_python_version.py"
+    "${PYTHON_INSTALL_PREFIX}"
     OUTPUT_VARIABLE CMAKE_PYTHON_PATH)
 string(STRIP "${CMAKE_PYTHON_PATH}" CMAKE_PYTHON_PATH)
 install(CODE "set(ENV{PYTHONPATH} ${CMAKE_PYTHON_PATH})")
 install(CODE "set(PYTHON_EXECUTABLE \"${PYTHON_EXECUTABLE}\")")
 install(CODE "set(CMAKE_BINARY_DIR \"${CMAKE_BINARY_DIR}\")")
-install(CODE "set(CMAKE_INSTALL_PREFIX \"${CMAKE_INSTALL_PREFIX}\")")
+
+install(CODE "set(PYTHON_INSTALL_PREFIX \"${PYTHON_INSTALL_PREFIX}\")")
 install(CODE "execute_process(COMMAND mkdir -p $ENV{DESTDIR}${CMAKE_PYTHON_PATH})")
 install(SCRIPT "${CMAKE_CURRENT_SOURCE_DIR}/PythonInstall.cmake")
 
diff --git a/src/mlpack/bindings/python/PythonInstall.cmake b/src/mlpack/bindings/python/PythonInstall.cmake
index 881b48344a..6e25fb926e 100644
--- a/src/mlpack/bindings/python/PythonInstall.cmake
+++ b/src/mlpack/bindings/python/PythonInstall.cmake
@@ -5,13 +5,13 @@
 if (DEFINED ENV{DESTDIR})
   execute_process(COMMAND ${PYTHON_EXECUTABLE}
       "${CMAKE_BINARY_DIR}/src/mlpack/bindings/python/setup.py" install
-          --prefix=${CMAKE_INSTALL_PREFIX} --root=$ENV{DESTDIR}
+          --prefix=${PYTHON_INSTALL_PREFIX} --root=$ENV{DESTDIR}
       WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/src/mlpack/bindings/python/"
       RESULT_VARIABLE setup_res)
 else ()
   execute_process(COMMAND ${PYTHON_EXECUTABLE}
       "${CMAKE_BINARY_DIR}/src/mlpack/bindings/python/setup.py" install
-          --prefix=${CMAKE_INSTALL_PREFIX}
+          --prefix=${PYTHON_INSTALL_PREFIX}
       WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/src/mlpack/bindings/python/"
       RESULT_VARIABLE setup_res)
 endif ()

From c8c7e6594d9abb3411b45e52d4910250084c2bd8 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 3 Jan 2021 20:38:52 -0500
Subject: [PATCH 043/253] Update documentation for new CMake option.

---
 HISTORY.md          | 3 +++
 README.md           | 1 +
 doc/guide/build.hpp | 1 +
 3 files changed, 5 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index 7529a3ee86..9bb5fc29ff 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -13,6 +13,9 @@
 
   * Add finalizers to Julia binding model types to fix memory handling (#2756).
 
+  * Add `PYTHON_INSTALL_PREFIX` CMake option to specify installation root for
+    Python bindings.
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.
diff --git a/README.md b/README.md
index 610e4f6d33..bb8ba1be6c 100644
--- a/README.md
+++ b/README.md
@@ -203,6 +203,7 @@ Options are specified with the -D flag.  The allowed options include:
     BUILD_CLI_EXECUTABLES=(ON/OFF): whether or not to build command-line programs
     BUILD_PYTHON_BINDINGS=(ON/OFF): whether or not to build Python bindings
     PYTHON_EXECUTABLE=(/path/to/python_version): Path to specific Python executable
+    PYTHON_INSTALL_PREFIX=(/path/to/python/): Path to root of Python installation
     BUILD_JULIA_BINDINGS=(ON/OFF): whether or not to build Julia bindings
     JULIA_EXECUTABLE=(/path/to/julia): Path to specific Julia executable
     BUILD_GO_BINDINGS=(ON/OFF): whether or not to build Go bindings
diff --git a/doc/guide/build.hpp b/doc/guide/build.hpp
index a7b5d149ad..d889652e81 100644
--- a/doc/guide/build.hpp
+++ b/doc/guide/build.hpp
@@ -190,6 +190,7 @@ The full list of options mlpack allows:
  - BUILD_WITH_COVERAGE=(ON/OFF): Build with support for code coverage tools
       (gcc only) (default OFF)
  - PYTHON_EXECUTABLE=(/path/to/python_version): Path to specific Python executable
+ - PYTHON_INSTALL_PREFIX=(/path/to/python/): Path to root of Python installation
  - JULIA_EXECUTABLE=(/path/to/julia): Path to specific Julia executable
  - BUILD_MARKDOWN_BINDINGS=(ON/OFF): Build Markdown bindings for website
        documentation (default OFF)

From c3307b2ad91f354e727145d9479563834671ca48 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 5 Jan 2021 13:01:08 -0500
Subject: [PATCH 044/253] Remove use of boost::visitor in NSModel.

---
 .../methods/neighbor_search/kfn_main.cpp      |   4 +-
 .../methods/neighbor_search/knn_main.cpp      |   3 +-
 .../neighbor_search/neighbor_search.hpp       |  13 +-
 .../methods/neighbor_search/ns_model.hpp      | 517 ++++++++------
 .../methods/neighbor_search/ns_model_impl.hpp | 651 ++++++++++--------
 src/mlpack/tests/aknn_test.cpp                |  16 +-
 src/mlpack/tests/knn_test.cpp                 |  44 +-
 7 files changed, 687 insertions(+), 561 deletions(-)

diff --git a/src/mlpack/methods/neighbor_search/kfn_main.cpp b/src/mlpack/methods/neighbor_search/kfn_main.cpp
index 73b9dbd64f..65f3083d56 100644
--- a/src/mlpack/methods/neighbor_search/kfn_main.cpp
+++ b/src/mlpack/methods/neighbor_search/kfn_main.cpp
@@ -237,14 +237,14 @@ static void mlpackMain()
 
     kfn->TreeType() = tree;
     kfn->RandomBasis() = randomBasis;
+    kfn->LeafSize() = size_t(lsInt);
 
     Log::Info << "Using reference data from "
         << IO::GetPrintableParam<arma::mat>("reference") << "." << endl;
 
     arma::mat referenceSet = std::move(IO::GetParam<arma::mat>("reference"));
 
-    kfn->BuildModel(std::move(referenceSet), size_t(lsInt), searchMode,
-        epsilon);
+    kfn->BuildModel(std::move(referenceSet), searchMode, epsilon);
   }
   else
   {
diff --git a/src/mlpack/methods/neighbor_search/knn_main.cpp b/src/mlpack/methods/neighbor_search/knn_main.cpp
index 9f643ecd61..87ca2203b0 100644
--- a/src/mlpack/methods/neighbor_search/knn_main.cpp
+++ b/src/mlpack/methods/neighbor_search/knn_main.cpp
@@ -261,8 +261,7 @@ static void mlpackMain()
 
     arma::mat referenceSet = std::move(IO::GetParam<arma::mat>("reference"));
 
-    knn->BuildModel(std::move(referenceSet), size_t(lsInt), searchMode,
-        epsilon);
+    knn->BuildModel(std::move(referenceSet), searchMode, epsilon);
   }
   else
   {
diff --git a/src/mlpack/methods/neighbor_search/neighbor_search.hpp b/src/mlpack/methods/neighbor_search/neighbor_search.hpp
index 1475970af6..2476e0484a 100644
--- a/src/mlpack/methods/neighbor_search/neighbor_search.hpp
+++ b/src/mlpack/methods/neighbor_search/neighbor_search.hpp
@@ -31,8 +31,13 @@ namespace mlpack {
 namespace neighbor  {
 
 // Forward declaration.
-template<typename SortPolicy>
-class TrainVisitor;
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+class LeafSizeNSWrapper;
 
 //! NeighborSearchMode represents the different neighbor search modes available.
 enum NeighborSearchMode
@@ -359,8 +364,8 @@ class NeighborSearch
   bool treeNeedsReset;
 
   //! The NSModel class should have access to internal members.
-  template<typename SortPol>
-  friend class TrainVisitor;
+  friend class LeafSizeNSWrapper<SortPolicy, TreeType, DualTreeTraversalType,
+      SingleTreeTraversalType>;
 }; // class NeighborSearch
 
 } // namespace neighbor
diff --git a/src/mlpack/methods/neighbor_search/ns_model.hpp b/src/mlpack/methods/neighbor_search/ns_model.hpp
index 981d0f9be9..c88b6226cd 100644
--- a/src/mlpack/methods/neighbor_search/ns_model.hpp
+++ b/src/mlpack/methods/neighbor_search/ns_model.hpp
@@ -4,8 +4,9 @@
  *
  * This is a model for nearest or furthest neighbor search.  It is useful in
  * that it provides an easy way to serialize a model, abstracts away the
- * different types of trees, and also reflects the NeighborSearch API and
- * automatically directs to the right tree type.
+ * different types of trees, and also (roughly) reflects the NeighborSearch API and
+ * automatically directs to the right tree type.  It is meant to be used by the
+ * knn and kfn bindings.
  *
  * mlpack is free software; you may redistribute it and/or modify it under the
  * terms of the 3-clause BSD license.  You should have received a copy of the
@@ -20,218 +21,302 @@
 #include <mlpack/core/tree/rectangle_tree.hpp>
 #include <mlpack/core/tree/spill_tree.hpp>
 #include <mlpack/core/tree/octree.hpp>
-#include <boost/variant.hpp>
 #include "neighbor_search.hpp"
 
 namespace mlpack {
 namespace neighbor {
 
 /**
- * Alias template for euclidean neighbor search.
+ * NSWrapperBase is a base wrapper class for holding all NeighborSearch types
+ * supported by NSModel.  All NeighborSearch type wrappers inherit from this
+ * class, allowing a simple interface via inheritance for all the different
+ * types we want to support.
+ */
+class NSWrapperBase
+{
+ public:
+  //! Create the NSWrapperBase object.  The base class does not hold anything,
+  //! so this constructor does not do anything.
+  NSWrapperBase() { }
+
+  //! Create a new NSWrapperBase that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual NSWrapperBase* Clone() const = 0;
+
+  //! Destruct the NSWrapperBase (nothing to do).
+  virtual ~NSWrapperBase() { };
+
+  //! Return a reference to the dataset.
+  virtual const arma::mat& Dataset() const = 0;
+
+  //! Get the search mode.
+  virtual NeighborSearchMode SearchMode() const = 0;
+  //! Modify the search modem
+  virtual NeighborSearchMode& SearchMode() = 0;
+
+  //! Get the approximation parameter epsilon.
+  virtual double Epsilon() const = 0;
+  //! Modify the approximation parameter epsilon.
+  virtual double& Epsilon() = 0;
+
+  //! Train the NeighborSearch model with the given parameters.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize,
+                     const double tau,
+                     const double rho) = 0;
+
+  //! Perform bichromatic neighbor search (i.e. search with a separate query
+  //! set).
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize,
+                      const double rho) = 0;
+
+  //! Perform monochromatic neighbor search (i.e. use the reference set as the
+  //! query set).
+  virtual void Search(const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances) = 0;
+};
+
+/**
+ * NSWrapper is a wrapper class for most NeighborSearch types.
  */
 template<typename SortPolicy,
          template<typename TreeMetricType,
                   typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-using NSType = NeighborSearch<SortPolicy,
-                              metric::EuclideanDistance,
-                              arma::mat,
-                              TreeType,
-                              TreeType<metric::EuclideanDistance,
-                                  NeighborSearchStat<SortPolicy>,
-                                  arma::mat>::template DualTreeTraverser>;
-
-/**
- * MonoSearchVisitor executes a monochromatic neighbor search on the given
- * NSType. We don't make any difference for different instantiations of NSType.
- */
-class MonoSearchVisitor : public boost::static_visitor<void>
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType =
+             TreeType<metric::EuclideanDistance,
+                      NeighborSearchStat<SortPolicy>,
+                      arma::mat>::template DualTreeTraverser,
+         template<typename RuleType> class SingleTreeTraversalType =
+             TreeType<metric::EuclideanDistance,
+                      NeighborSearchStat<SortPolicy>,
+                      arma::mat>::template SingleTreeTraverser>
+class NSWrapper : public NSWrapperBase
 {
- private:
-  //! Number of neighbors to search for.
-  const size_t k;
-  //! Result matrix for neighbors.
-  arma::Mat<size_t>& neighbors;
-  //! Result matrix for distances.
-  arma::mat& distances;
-
  public:
-  //! Perform monochromatic nearest neighbor search.
-  template<typename NSType>
-  void operator()(NSType* ns) const;
+  //! Construct the NSWrapper object, initializing the internally-held
+  //! NeighborSearch object.
+  NSWrapper(const NeighborSearchMode searchMode,
+            const double epsilon) :
+      ns(searchMode, epsilon)
+  {
+    // Nothing else to do.
+  }
 
-  //! Construct the MonoSearchVisitor object with the given parameters.
-  MonoSearchVisitor(const size_t k,
-                    arma::Mat<size_t>& neighbors,
-                    arma::mat& distances) :
-      k(k),
-      neighbors(neighbors),
-      distances(distances)
-  {};
+  //! Delete the NSWrapper object.
+  virtual ~NSWrapper() { }
+
+  //! Create a copy of this NSWrapper object.  This correctly handles
+  //! polymorphism.
+  virtual NSWrapper* Clone() const { return new NSWrapper(*this); }
+
+  //! Get a reference to the reference set.
+  const arma::mat& Dataset() const { return ns.ReferenceSet(); }
+
+  //! Get the search mode.
+  NeighborSearchMode SearchMode() const { return ns.SearchMode(); }
+  //! Modify the search mode.
+  NeighborSearchMode& SearchMode() { return ns.SearchMode(); }
+
+  //! Get epsilon, the approximation parameter.
+  double Epsilon() const { return ns.Epsilon(); }
+  //! Modify epsilon, the approximation parameter.
+  double& Epsilon() { return ns.Epsilon(); }
+
+  //! Train the model with the given options.  For NSWrapper, we ignore the
+  //! extra parameters.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t /* leafSize */,
+                     const double /* tau */,
+                     const double /* rho */);
+
+  //! Perform bichromatic neighbor search (i.e. search with a separate query
+  //! set).  For NSWrapper, we ignore the extra parameters.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t /* leafSize */,
+                      const double /* rho */);
+
+  //! Perform monochromatic neighbor search (i.e. use the reference set as the
+  //! query set).
+  virtual void Search(const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances);
+
+  //! Serialize the NeighborSearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(ns));
+  }
+
+ protected:
+  // Convenience typedef for the neighbor search type held by this class.
+  typedef NeighborSearch<SortPolicy,
+                         metric::EuclideanDistance,
+                         arma::mat,
+                         TreeType,
+                         DualTreeTraversalType,
+                         SingleTreeTraversalType> NSType;
+
+  //! The instantiated NeighborSearch object that we are wrapping.
+  NSType ns;
 };
 
 /**
- * BiSearchVisitor executes a bichromatic neighbor search on the given NSType.
- * We use template specialization to differentiate those tree types that
- * accept leafSize as a parameter. In these cases, before doing neighbor search,
- * a query tree with proper leafSize is built from the querySet.
+ * LeafSizeNSWrapper wraps any NeighborSearch types that take a leaf size for
+ * tree construction.  The implementations of Train() and Search() take the leaf
+ * size into account.
+ */
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType =
+             TreeType<metric::EuclideanDistance,
+                      NeighborSearchStat<SortPolicy>,
+                      arma::mat>::template DualTreeTraverser,
+         template<typename RuleType> class SingleTreeTraversalType =
+             TreeType<metric::EuclideanDistance,
+                      NeighborSearchStat<SortPolicy>,
+                      arma::mat>::template SingleTreeTraverser>
+class LeafSizeNSWrapper :
+    public NSWrapper<SortPolicy,
+                     TreeType,
+                     DualTreeTraversalType,
+                     SingleTreeTraversalType>
+{
+ public:
+  //! Construct the LeafSizeNSWrapper by delegating to the NSWrapper
+  //! constructor.
+  LeafSizeNSWrapper(const NeighborSearchMode searchMode,
+                    const double epsilon) :
+      NSWrapper<SortPolicy,
+                TreeType,
+                DualTreeTraversalType,
+                SingleTreeTraversalType>(searchMode, epsilon)
+  {
+    // Nothing to do.
+  }
+
+  //! Delete the LeafSizeNSWrapper.
+  virtual ~LeafSizeNSWrapper() { }
+
+  //! Return a copy of the LeafSizeNSWrapper.
+  virtual LeafSizeNSWrapper* Clone() const
+  {
+    return new LeafSizeNSWrapper(*this);
+  }
+
+  //! Train a model with the given parameters.  This overload uses leafSize but
+  //! ignores the other parameters.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize,
+                     const double /* tau */,
+                     const double /* rho */);
+
+  //! Perform bichromatic search (e.g. search with a separate query set).  This
+  //! overload uses the leaf size, but ignores the other parameters.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize,
+                      const double /* rho */);
+
+  //! Serialize the NeighborSearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(ns));
+  }
+
+ protected:
+  using NSWrapper<SortPolicy,
+                  TreeType,
+                  DualTreeTraversalType,
+                  SingleTreeTraversalType>::ns;
+};
+
+/**
+ * The SpillNSWrapper class wraps the NeighborSearch class when the spill tree
+ * is used.
  */
 template<typename SortPolicy>
-class BiSearchVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The query set for the bichromatic search.
-  const arma::mat& querySet;
-  //! The number of neighbors to search for.
-  const size_t k;
-  //! The result matrix for neighbors.
-  arma::Mat<size_t>& neighbors;
-  //! The result matrix for distances.
-  arma::mat& distances;
-  //! The number of points in a leaf (for BinarySpaceTrees).
-  const size_t leafSize;
-  //! Overlapping size (for spill trees).
-  const double tau;
-  //! Balance threshold (for spill trees).
-  const double rho;
-
-  //! Bichromatic neighbor search on the given NSType considering the leafSize.
-  template<typename NSType>
-  void SearchLeaf(NSType* ns) const;
-
- public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using NSTypeT = NSType<SortPolicy, TreeType>;
-
-  //! Default Bichromatic neighbor search on the given NSType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(NSTypeT<TreeType>* ns) const;
-
-  //! Bichromatic neighbor search on the given NSType specialized for KDTrees.
-  void operator()(NSTypeT<tree::KDTree>* ns) const;
-
-  //! Bichromatic neighbor search on the given NSType specialized for BallTrees.
-  void operator()(NSTypeT<tree::BallTree>* ns) const;
-
-  //! Bichromatic neighbor search specialized for SPTrees.
-  void operator()(SpillKNN* ns) const;
-
-  //! Bichromatic neighbor search specialized for octrees.
-  void operator()(NSTypeT<tree::Octree>* ns) const;
-
-  //! Construct the BiSearchVisitor.
-  BiSearchVisitor(const arma::mat& querySet,
-                  const size_t k,
-                  arma::Mat<size_t>& neighbors,
-                  arma::mat& distances,
-                  const size_t leafSize,
-                  const double tau,
-                  const double rho);
-};
-
-/**
- * TrainVisitor sets the reference set to a new reference set on the given
- * NSType. We use template specialization to differentiate those tree types that
- * accept leafSize as a parameter. In these cases, a reference tree with proper
- * leafSize is built from the referenceSet.
- */
-template<typename SortPolicy>
-class TrainVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The reference set to use for training.
-  arma::mat&& referenceSet;
-  //! The leaf size, used only by BinarySpaceTree.
-  size_t leafSize;
-  //! Overlapping size (for spill trees).
-  const double tau;
-  //! Balance threshold (for spill trees).
-  const double rho;
-
-  //! Train on the given NSType considering the leafSize.
-  template<typename NSType>
-  void TrainLeaf(NSType* ns) const;
-
- public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using NSTypeT = NSType<SortPolicy, TreeType>;
-
-  //! Default Train on the given NSType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(NSTypeT<TreeType>* ns) const;
-
-  //! Train on the given NSType specialized for KDTrees.
-  void operator()(NSTypeT<tree::KDTree>* ns) const;
-
-  //! Train on the given NSType specialized for BallTrees.
-  void operator()(NSTypeT<tree::BallTree>* ns) const;
-
-  //! Train specialized for SPTrees.
-  void operator()(SpillKNN* ns) const;
-
-  //! Train specialized for octrees.
-  void operator()(NSTypeT<tree::Octree>* ns) const;
-
-  //! Construct the TrainVisitor object with the given reference set, leafSize
-  //! for BinarySpaceTrees, and tau and rho for spill trees.
-  TrainVisitor(arma::mat&& referenceSet,
-               const size_t leafSize,
-               const double tau,
-               const double rho);
-};
-
-/**
- * SearchModeVisitor exposes the SearchMode() method of the given NSType.
- */
-class SearchModeVisitor : public boost::static_visitor<NeighborSearchMode&>
+class SpillNSWrapper :
+    public NSWrapper<
+        SortPolicy,
+        tree::SPTree,
+        tree::SPTree<metric::EuclideanDistance,
+                     NeighborSearchStat<SortPolicy>,
+                     arma::mat>::template DefeatistDualTreeTraverser,
+        tree::SPTree<metric::EuclideanDistance,
+                     NeighborSearchStat<SortPolicy>,
+                     arma::mat>::template DefeatistSingleTreeTraverser>
 {
  public:
-  //! Return the search mode.
-  template<typename NSType>
-  NeighborSearchMode& operator()(NSType* ns) const;
-};
+  //! Construct the SpillNSWrapper.
+  SpillNSWrapper(const NeighborSearchMode searchMode,
+                 const double epsilon) :
+      NSWrapper<
+          SortPolicy,
+          tree::SPTree,
+          tree::SPTree<metric::EuclideanDistance,
+                       NeighborSearchStat<SortPolicy>,
+                       arma::mat>::template DefeatistDualTreeTraverser,
+          tree::SPTree<metric::EuclideanDistance,
+                       NeighborSearchStat<SortPolicy>,
+                       arma::mat>::template DefeatistSingleTreeTraverser>(
+          searchMode, epsilon)
+  {
+    // Nothing to do.
+  }
 
-/**
- * EpsilonVisitor exposes the Epsilon method of the given NSType.
- */
-class EpsilonVisitor : public boost::static_visitor<double&>
-{
- public:
-  //! Return epsilon, the approximation parameter.
-  template<typename NSType>
-  double& operator()(NSType *ns) const;
-};
+  //! Destruct the SpillNSWrapper.
+  virtual ~SpillNSWrapper() { }
 
-/**
- * ReferenceSetVisitor exposes the referenceSet of the given NSType.
- */
-class ReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
-{
- public:
-  //! Return the reference set.
-  template<typename NSType>
-  const arma::mat& operator()(NSType *ns) const;
-};
+  //! Return a copy of the SpillNSWrapper.
+  virtual SpillNSWrapper* Clone() const { return new SpillNSWrapper(*this); }
 
-/**
- * DeleteVisitor deletes the given NSType instance.
- */
-class DeleteVisitor : public boost::static_visitor<void>
-{
- public:
-  //! Delete the NSType object.
-  template<typename NSType>
-  void operator()(NSType *ns) const;
+  //! Train the model using the given parameters.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize,
+                     const double tau,
+                     const double rho);
+
+  //! Perform bichromatic search (i.e. search with a different query set) using
+  //! the given parameters.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize,
+                      const double rho);
+
+  //! Serialize the NeighborSearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(ns));
+  }
+
+ protected:
+  using NSWrapper<
+      SortPolicy,
+      tree::SPTree,
+      tree::SPTree<metric::EuclideanDistance,
+                   NeighborSearchStat<SortPolicy>,
+                   arma::mat>::template DefeatistDualTreeTraverser,
+      tree::SPTree<metric::EuclideanDistance,
+                   NeighborSearchStat<SortPolicy>,
+                   arma::mat>::template DefeatistSingleTreeTraverser>::ns;
 };
 
 /**
@@ -272,39 +357,20 @@ class NSModel
   //! Tree type considered for neighbor search.
   TreeTypes treeType;
 
-  //! For tree types that accept the maxLeafSize parameter.
-  size_t leafSize;
-
-  //! Overlapping size (for spill trees).
-  double tau;
-  //! Balance threshold (for spill trees).
-  double rho;
-
   //! If true, random projections are used.
   bool randomBasis;
   //! This is the random projection matrix; only used if randomBasis is true.
   arma::mat q;
 
+  size_t leafSize;
+  double tau;
+  double rho;
+
   /**
-   * nSearch holds an instance of the NeigborSearch class for the current
+   * nSearch holds an instance of the NeighborSearch class for the current
    * treeType. It is initialized every time BuildModel is executed.
-   * We access to the contained value through the visitor classes defined above.
    */
-  boost::variant<NSType<SortPolicy, tree::KDTree>*,
-                 NSType<SortPolicy, tree::StandardCoverTree>*,
-                 NSType<SortPolicy, tree::RTree>*,
-                 NSType<SortPolicy, tree::RStarTree>*,
-                 NSType<SortPolicy, tree::BallTree>*,
-                 NSType<SortPolicy, tree::XTree>*,
-                 NSType<SortPolicy, tree::HilbertRTree>*,
-                 NSType<SortPolicy, tree::RPlusTree>*,
-                 NSType<SortPolicy, tree::RPlusPlusTree>*,
-                 NSType<SortPolicy, tree::VPTree>*,
-                 NSType<SortPolicy, tree::RPTree>*,
-                 NSType<SortPolicy, tree::MaxRPTree>*,
-                 SpillKNN*,
-                 NSType<SortPolicy, tree::UBTree>*,
-                 NSType<SortPolicy, tree::Octree>*> nSearch;
+  NSWrapperBase* nSearch;
 
  public:
   /**
@@ -359,22 +425,22 @@ class NSModel
   NeighborSearchMode SearchMode() const;
   NeighborSearchMode& SearchMode();
 
-  //! Expose Epsilon.
-  double Epsilon() const;
-  double& Epsilon();
-
-  //! Expose leafSize.
+  //! Expose LeafSize.
   size_t LeafSize() const { return leafSize; }
   size_t& LeafSize() { return leafSize; }
 
-  //! Expose tau.
+  //! Expose Tau.
   double Tau() const { return tau; }
   double& Tau() { return tau; }
 
-  //! Expose rho.
+  //! Expose Rho.
   double Rho() const { return rho; }
   double& Rho() { return rho; }
 
+  //! Expose Epsilon.
+  double Epsilon() const;
+  double& Epsilon();
+
   //! Expose treeType.
   TreeTypes TreeType() const { return treeType; }
   TreeTypes& TreeType() { return treeType; }
@@ -383,9 +449,12 @@ class NSModel
   bool RandomBasis() const { return randomBasis; }
   bool& RandomBasis() { return randomBasis; }
 
+  //! Initialize the model type.  (This does not perform any training.)
+  void InitializeModel(const NeighborSearchMode searchMode,
+                       const double epsilon);
+
   //! Build the reference tree.
   void BuildModel(arma::mat&& referenceSet,
-                  const size_t leafSize,
                   const NeighborSearchMode searchMode,
                   const double epsilon = 0);
 
diff --git a/src/mlpack/methods/neighbor_search/ns_model_impl.hpp b/src/mlpack/methods/neighbor_search/ns_model_impl.hpp
index 8c90aa9ec8..319fb652af 100644
--- a/src/mlpack/methods/neighbor_search/ns_model_impl.hpp
+++ b/src/mlpack/methods/neighbor_search/ns_model_impl.hpp
@@ -21,107 +21,121 @@
 namespace mlpack {
 namespace neighbor {
 
-//! Monochromatic neighbor search on the given NSType instance.
-template<typename NSType>
-void MonoSearchVisitor::operator()(NSType *ns) const
-{
-  if (ns)
-    return ns->Search(k, neighbors, distances);
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Save parameters for bichromatic neighbor search.
-template<typename SortPolicy>
-BiSearchVisitor<SortPolicy>::BiSearchVisitor(const arma::mat& querySet,
-                                             const size_t k,
-                                             arma::Mat<size_t>& neighbors,
-                                             arma::mat& distances,
-                                             const size_t leafSize,
-                                             const double tau,
-                                             const double rho) :
-    querySet(querySet),
-    k(k),
-    neighbors(neighbors),
-    distances(distances),
-    leafSize(leafSize),
-    tau(tau),
-    rho(rho)
-{}
-
-//! Default Bichromatic neighbor search on the given NSType instance.
-template<typename SortPolicy>
-template<template<typename TreeMetricType,
+//! Train the model with the given options.  For NSWrapper, we ignore the
+//! extra parameters.
+template<typename SortPolicy,
+         template<typename TreeMetricType,
                   typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void BiSearchVisitor<SortPolicy>::operator()(NSTypeT<TreeType>* ns) const
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+void NSWrapper<
+    SortPolicy, TreeType, DualTreeTraversalType, SingleTreeTraversalType
+>::Train(arma::mat&& referenceSet,
+         const size_t /* leafSize */,
+         const double /* tau */,
+         const double /* rho */)
 {
-  if (ns)
-    return ns->Search(querySet, k, neighbors, distances);
-  throw std::runtime_error("no neighbor search model initialized");
+  ns.Train(std::move(referenceSet));
 }
 
-//! Bichromatic neighbor search on the given NSType specialized for KDTrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(NSTypeT<tree::KDTree>* ns) const
+//! Perform bichromatic neighbor search (i.e. search with a separate query
+//! set).  For NSWrapper, we ignore the extra parameters.
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+void NSWrapper<
+    SortPolicy, TreeType, DualTreeTraversalType, SingleTreeTraversalType
+>::Search(arma::mat&& querySet,
+          const size_t k,
+          arma::Mat<size_t>& neighbors,
+          arma::mat& distances,
+          const size_t /* leafSize */,
+          const double /* rho */)
 {
-  if (ns)
-    return SearchLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
+  ns.Search(std::move(querySet), k, neighbors, distances);
 }
 
-//! Bichromatic neighbor search on the given NSType specialized for BallTrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(NSTypeT<tree::BallTree>* ns) const
+//! Perform monochromatic neighbor search (i.e. use the reference set as the
+//! query set).
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+void NSWrapper<
+    SortPolicy, TreeType, DualTreeTraversalType, SingleTreeTraversalType
+>::Search(const size_t k,
+          arma::Mat<size_t>& neighbors,
+          arma::mat& distances)
 {
-  if (ns)
-    return SearchLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
+  ns.Search(k, neighbors, distances);
 }
 
-//! Bichromatic neighbor search specialized for SPTrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(SpillKNN* ns) const
+//! Train a model with the given parameters.  This overload uses leafSize but
+//! ignores the other parameters.
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+void LeafSizeNSWrapper<
+    SortPolicy, TreeType, DualTreeTraversalType, SingleTreeTraversalType
+>::Train(arma::mat&& referenceSet,
+         const size_t leafSize,
+         const double /* tau */,
+         const double /* rho */)
 {
-  if (ns)
+  if (ns.SearchMode() == NAIVE_MODE)
   {
-    if (ns->SearchMode() == DUAL_TREE_MODE)
-    {
-      // For Dual Tree Search on SpillTrees, the queryTree must be built with
-      // non overlapping (tau = 0).
-      typename SpillKNN::Tree queryTree(std::move(querySet), 0 /* tau*/,
-          leafSize, rho);
-      ns->Search(queryTree, k, neighbors, distances);
-    }
-    else
-      ns->Search(querySet, k, neighbors, distances);
+    ns.Train(std::move(referenceSet));
   }
   else
-    throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Bichromatic neighbor search specialized for octrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(NSTypeT<tree::Octree>* ns) const
-{
-  if (ns)
-    return SearchLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Bichromatic neighbor search on the given NSType considering the leafSize.
-template<typename SortPolicy>
-template<typename NSType>
-void BiSearchVisitor<SortPolicy>::SearchLeaf(NSType* ns) const
-{
-  if (ns->SearchMode() == DUAL_TREE_MODE)
   {
+    // Build the tree with the specified leaf size.
+    std::vector<size_t> oldFromNewReferences;
+    typename decltype(ns)::Tree referenceTree(std::move(referenceSet),
+        oldFromNewReferences, leafSize);
+    ns.Train(std::move(referenceTree));
+    ns.oldFromNewReferences = std::move(oldFromNewReferences);
+  }
+}
+
+//! Perform bichromatic search (e.g. search with a separate query set).  This
+//! overload uses the leaf size, but ignores the other parameters.
+template<typename SortPolicy,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename RuleType> class DualTreeTraversalType,
+         template<typename RuleType> class SingleTreeTraversalType>
+void LeafSizeNSWrapper<
+    SortPolicy, TreeType, DualTreeTraversalType, SingleTreeTraversalType
+>::Search(arma::mat&& querySet,
+          const size_t k,
+          arma::Mat<size_t>& neighbors,
+          arma::mat& distances,
+          const size_t leafSize,
+          const double /* rho */)
+{
+  if (ns.SearchMode() == DUAL_TREE_MODE)
+  {
+    // We actually have to do the mapping of query points ourselves, since the
+    // NeighborSearch class does not provide a way for us to specify the leaf
+    // size when building the query tree.  (Therefore we must also build the
+    // query tree manually.)
     std::vector<size_t> oldFromNewQueries;
-    typename NSType::Tree queryTree(std::move(querySet), oldFromNewQueries,
-        leafSize);
+    typename decltype(ns)::Tree queryTree(std::move(querySet),
+        oldFromNewQueries, leafSize);
 
     arma::Mat<size_t> neighborsOut;
     arma::mat distancesOut;
-    ns->Search(queryTree, k, neighborsOut, distancesOut);
+    ns.Search(queryTree, k, neighborsOut, distancesOut);
 
     // Unmap the query points.
     distances.set_size(distancesOut.n_rows, distancesOut.n_cols);
@@ -133,131 +147,47 @@ void BiSearchVisitor<SortPolicy>::SearchLeaf(NSType* ns) const
     }
   }
   else
-    ns->Search(querySet, k, neighbors, distances);
+  {
+    ns.Search(querySet, k, neighbors, distances);
+  }
 }
 
-//! Save parameters for Train.
+//! Train the model using the given parameters.
 template<typename SortPolicy>
-TrainVisitor<SortPolicy>::TrainVisitor(arma::mat&& referenceSet,
+void SpillNSWrapper<SortPolicy>::Train(arma::mat&& referenceSet,
                                        const size_t leafSize,
                                        const double tau,
-                                       const double rho) :
-    referenceSet(std::move(referenceSet)),
-    leafSize(leafSize),
-    tau(tau),
-    rho(rho)
-{}
-
-//! Default Train on the given NSType instance.
-template<typename SortPolicy>
-template<template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void TrainVisitor<SortPolicy>::operator()(NSTypeT<TreeType>* ns) const
+                                       const double rho)
 {
-  if (ns)
-    return ns->Train(std::move(referenceSet));
-  throw std::runtime_error("no neighbor search model initialized");
+  typename decltype(ns)::Tree tree(std::move(referenceSet), tau, leafSize,
+      rho);
+  ns.Train(std::move(tree));
 }
 
-//! Train on the given NSType specialized for KDTrees.
+//! Perform bichromatic search (i.e. search with a different query set) using
+//! the given parameters.
 template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(NSTypeT<tree::KDTree>* ns) const
+void SpillNSWrapper<SortPolicy>::Search(arma::mat&& querySet,
+                                        const size_t k,
+                                        arma::Mat<size_t>& neighbors,
+                                        arma::mat& distances,
+                                        const size_t leafSize,
+                                        const double rho)
 {
-  if (ns)
-    return TrainLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Train on the given NSType specialized for BallTrees.
-template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(NSTypeT<tree::BallTree>* ns) const
-{
-  if (ns)
-    return TrainLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Train specialized for SPTrees.
-template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(SpillKNN* ns) const
-{
-  if (ns)
+  if (ns.SearchMode() == DUAL_TREE_MODE)
   {
-    if (ns->SearchMode() == NAIVE_MODE)
-      ns->Train(std::move(referenceSet));
-    else
-    {
-      typename SpillKNN::Tree tree(std::move(referenceSet), tau, leafSize, rho);
-      ns->Train(std::move(tree));
-    }
+    // For Dual Tree Search on SpillTrees, the queryTree must be built with
+    // non overlapping (tau = 0).
+    typename decltype(ns)::Tree queryTree(std::move(querySet), 0 /* tau */,
+        leafSize, rho);
+    ns.Search(queryTree, k, neighbors, distances);
   }
-  else
-    throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Train specialized for Octrees.
-template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(NSTypeT<tree::Octree>* ns) const
-{
-  if (ns)
-    return TrainLeaf(ns);
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Train on the given NSType considering the leafSize.
-template<typename SortPolicy>
-template<typename NSType>
-void TrainVisitor<SortPolicy>::TrainLeaf(NSType* ns) const
-{
-  if (ns->SearchMode() == NAIVE_MODE)
-    ns->Train(std::move(referenceSet));
   else
   {
-    std::vector<size_t> oldFromNewReferences;
-    typename NSType::Tree referenceTree(std::move(referenceSet),
-        oldFromNewReferences, leafSize);
-    ns->Train(std::move(referenceTree));
-    // Set the mappings.
-    ns->oldFromNewReferences = std::move(oldFromNewReferences);
+    ns.Search(querySet, k, neighbors, distances);
   }
 }
 
-//! Return the search mode.
-template<typename NSType>
-NeighborSearchMode& SearchModeVisitor::operator()(NSType* ns) const
-{
-  if (ns)
-    return ns->SearchMode();
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Expose the Epsilon method of the given NSType.
-template<typename NSType>
-double& EpsilonVisitor::operator()(NSType* ns) const
-{
-  if (ns)
-    return ns->Epsilon();
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Expose the referenceSet of the given NSType.
-template<typename NSType>
-const arma::mat& ReferenceSetVisitor::operator()(NSType* ns) const
-{
-  if (ns)
-    return ns->ReferenceSet();
-  throw std::runtime_error("no neighbor search model initialized");
-}
-
-//! Clean memory, if necessary.
-template<typename NSType>
-void DeleteVisitor::operator()(NSType* ns) const
-{
-  if (ns)
-    delete ns;
-}
-
 /**
  * Initialize the NSModel with the given type and whether or not a random
  * basis should be used.
@@ -265,10 +195,11 @@ void DeleteVisitor::operator()(NSType* ns) const
 template<typename SortPolicy>
 NSModel<SortPolicy>::NSModel(TreeTypes treeType, bool randomBasis) :
     treeType(treeType),
+    randomBasis(randomBasis),
     leafSize(20),
-    tau(0),
+    tau(0.0),
     rho(0.7),
-    randomBasis(randomBasis)
+    nSearch(NULL)
 {
   // Nothing to do.
 }
@@ -276,12 +207,12 @@ NSModel<SortPolicy>::NSModel(TreeTypes treeType, bool randomBasis) :
 template<typename SortPolicy>
 NSModel<SortPolicy>::NSModel(const NSModel& other) :
     treeType(other.treeType),
+    randomBasis(other.randomBasis),
+    q(other.q),
     leafSize(other.leafSize),
     tau(other.tau),
     rho(other.rho),
-    randomBasis(other.randomBasis),
-    q(other.q),
-    nSearch(other.nSearch)
+    nSearch(other.nSearch->Clone())
 {
   // Nothing to do.
 }
@@ -289,34 +220,37 @@ NSModel<SortPolicy>::NSModel(const NSModel& other) :
 template<typename SortPolicy>
 NSModel<SortPolicy>::NSModel(NSModel&& other) :
     treeType(other.treeType),
+    randomBasis(other.randomBasis),
+    q(std::move(other.q)),
     leafSize(other.leafSize),
     tau(other.tau),
     rho(other.rho),
-    randomBasis(other.randomBasis),
-    q(std::move(other.q)),
     nSearch(other.nSearch)
 {
   // Reset parameters of the other model.
   other.treeType = TreeTypes::KD_TREE;
-  other.leafSize = 20;
-  other.tau = 0;
-  other.rho = 0.7;
   other.randomBasis = false;
-  other.nSearch = decltype(other.nSearch)();
+  other.leafSize = 20;
+  other.tau = 0.0;
+  other.rho = 0.7;
+  other.nSearch = NULL;
 }
 
 template<typename SortPolicy>
 NSModel<SortPolicy>& NSModel<SortPolicy>::operator=(const NSModel& other)
 {
-  boost::apply_visitor(DeleteVisitor(), nSearch);
+  if (this != &other)
+  {
+    delete nSearch;
 
-  treeType = other.treeType;
-  leafSize = other.leafSize;
-  tau = other.tau;
-  rho = other.rho;
-  randomBasis = other.randomBasis;
-  q = other.q;
-  nSearch = other.nSearch;
+    treeType = other.treeType;
+    randomBasis = other.randomBasis;
+    q = other.q;
+    leafSize = other.leafSize;
+    tau = other.tau;
+    rho = other.rho;
+    nSearch = other.nSearch->Clone();
+  }
 
   return *this;
 }
@@ -324,24 +258,26 @@ NSModel<SortPolicy>& NSModel<SortPolicy>::operator=(const NSModel& other)
 template<typename SortPolicy>
 NSModel<SortPolicy>& NSModel<SortPolicy>::operator=(NSModel&& other)
 {
-  boost::apply_visitor(DeleteVisitor(), nSearch);
+  if (this != &other)
+  {
+    delete nSearch;
 
-  treeType = other.treeType;
-  leafSize = other.leafSize;
-  tau = other.tau;
-  rho = other.rho;
-  randomBasis = other.randomBasis;
-  q = std::move(other.q);
-  // Copy the pointer and type.
-  nSearch = other.nSearch;
+    treeType = other.treeType;
+    randomBasis = other.randomBasis;
+    q = std::move(other.q);
+    leafSize = other.leafSize;
+    tau = other.tau;
+    rho = other.rho;
+    nSearch = other.nSearch;
 
-  // Reset parameters of the other model.
-  other.treeType = TreeTypes::KD_TREE;
-  other.leafSize = 20;
-  other.tau = 0;
-  other.rho = 0.7;
-  other.randomBasis = false;
-  other.nSearch = decltype(other.nSearch)();
+    // Reset parameters of the other model.
+    other.treeType = TreeTypes::KD_TREE;
+    other.randomBasis = false;
+    other.leafSize = 20;
+    other.tau = 0.0;
+    other.rho = 0.7;
+    other.nSearch = NULL;
+  }
 
   return *this;
 }
@@ -350,7 +286,7 @@ NSModel<SortPolicy>& NSModel<SortPolicy>::operator=(NSModel&& other)
 template<typename SortPolicy>
 NSModel<SortPolicy>::~NSModel()
 {
-  boost::apply_visitor(DeleteVisitor(), nSearch);
+  delete nSearch;
 }
 
 //! Serialize the kNN model.
@@ -359,60 +295,236 @@ template<typename Archive>
 void NSModel<SortPolicy>::serialize(Archive& ar, const uint32_t /* version */)
 {
   ar(CEREAL_NVP(treeType));
+  ar(CEREAL_NVP(randomBasis));
+  ar(CEREAL_NVP(q));
   ar(CEREAL_NVP(leafSize));
   ar(CEREAL_NVP(tau));
   ar(CEREAL_NVP(rho));
-  ar(CEREAL_NVP(randomBasis));
-  ar(CEREAL_NVP(q));
 
   // This should never happen, but just in case, be clean with memory.
   if (cereal::is_loading<Archive>())
-    boost::apply_visitor(DeleteVisitor(), nSearch);
+    InitializeModel(DUAL_TREE_MODE, 0.0); // Values will be overwritten.
 
-  ar(CEREAL_VARIANT_POINTER(nSearch));
+  // Avoid polymorphic serialization by explicitly serializing the correct type.
+  switch (treeType)
+  {
+    case KD_TREE:
+      {
+        LeafSizeNSWrapper<SortPolicy, tree::KDTree>& typedSearch =
+            dynamic_cast<LeafSizeNSWrapper<SortPolicy,
+                         tree::KDTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case COVER_TREE:
+      {
+        NSWrapper<SortPolicy, tree::StandardCoverTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy,
+                                   tree::StandardCoverTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case R_TREE:
+      {
+        NSWrapper<SortPolicy, tree::RTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::RTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case R_STAR_TREE:
+      {
+        NSWrapper<SortPolicy, tree::RStarTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::RStarTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case BALL_TREE:
+      {
+        LeafSizeNSWrapper<SortPolicy, tree::BallTree>& typedSearch =
+            dynamic_cast<LeafSizeNSWrapper<SortPolicy,
+                                           tree::BallTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case X_TREE:
+      {
+        NSWrapper<SortPolicy, tree::XTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::XTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case HILBERT_R_TREE:
+      {
+        NSWrapper<SortPolicy, tree::HilbertRTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::HilbertRTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case R_PLUS_TREE:
+      {
+        NSWrapper<SortPolicy, tree::RPlusTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::RPlusTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case R_PLUS_PLUS_TREE:
+      {
+        NSWrapper<SortPolicy, tree::RPlusPlusTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::RPlusPlusTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case SPILL_TREE:
+      {
+        SpillNSWrapper<SortPolicy>& typedSearch =
+            dynamic_cast<SpillNSWrapper<SortPolicy>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case VP_TREE:
+      {
+        NSWrapper<SortPolicy, tree::VPTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::VPTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case RP_TREE:
+      {
+        NSWrapper<SortPolicy, tree::RPTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::RPTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case MAX_RP_TREE:
+      {
+        NSWrapper<SortPolicy, tree::MaxRPTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::MaxRPTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case UB_TREE:
+      {
+        NSWrapper<SortPolicy, tree::UBTree>& typedSearch =
+            dynamic_cast<NSWrapper<SortPolicy, tree::UBTree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case OCTREE:
+      {
+        LeafSizeNSWrapper<SortPolicy, tree::Octree>& typedSearch =
+            dynamic_cast<LeafSizeNSWrapper<SortPolicy,
+                                           tree::Octree>&>(*nSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+  }
 }
 
 //! Expose the dataset.
 template<typename SortPolicy>
 const arma::mat& NSModel<SortPolicy>::Dataset() const
 {
-  return boost::apply_visitor(ReferenceSetVisitor(), nSearch);
+  return nSearch->Dataset();
 }
 
 //! Access the search mode.
 template<typename SortPolicy>
 NeighborSearchMode NSModel<SortPolicy>::SearchMode() const
 {
-  return boost::apply_visitor(SearchModeVisitor(), nSearch);
+  return nSearch->SearchMode();
 }
 
 //! Modify the search mode.
 template<typename SortPolicy>
 NeighborSearchMode& NSModel<SortPolicy>::SearchMode()
 {
-  return boost::apply_visitor(SearchModeVisitor(), nSearch);
+  return nSearch->SearchMode();
 }
 
 template<typename SortPolicy>
 double NSModel<SortPolicy>::Epsilon() const
 {
-  return boost::apply_visitor(EpsilonVisitor(), nSearch);
+  return nSearch->Epsilon();
 }
 
 template<typename SortPolicy>
 double& NSModel<SortPolicy>::Epsilon()
 {
-  return boost::apply_visitor(EpsilonVisitor(), nSearch);
+  return nSearch->Epsilon();
+}
+
+//! Initialize a model given the tree type.  (No training happens here.)
+template<typename SortPolicy>
+void NSModel<SortPolicy>::InitializeModel(const NeighborSearchMode searchMode,
+                                          const double epsilon)
+{
+  // Clear existing memory.
+  if (nSearch)
+    delete nSearch;
+
+  switch (treeType)
+  {
+    case KD_TREE:
+      nSearch = new LeafSizeNSWrapper<SortPolicy, tree::KDTree>(searchMode,
+          epsilon);
+      break;
+    case COVER_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::StandardCoverTree>(searchMode,
+          epsilon);
+      break;
+    case R_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::RTree>(searchMode, epsilon);
+      break;
+    case R_STAR_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::RStarTree>(searchMode, epsilon);
+      break;
+    case BALL_TREE:
+      nSearch = new LeafSizeNSWrapper<SortPolicy, tree::BallTree>(searchMode,
+          epsilon);
+      break;
+    case X_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::XTree>(searchMode, epsilon);
+      break;
+    case HILBERT_R_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::HilbertRTree>(searchMode,
+          epsilon);
+      break;
+    case R_PLUS_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::RPlusTree>(searchMode, epsilon);
+      break;
+    case R_PLUS_PLUS_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::RPlusPlusTree>(searchMode,
+          epsilon);
+      break;
+    case VP_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::VPTree>(searchMode, epsilon);
+      break;
+    case RP_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::RPTree>(searchMode, epsilon);
+      break;
+    case MAX_RP_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::MaxRPTree>(searchMode, epsilon);
+      break;
+    case SPILL_TREE:
+      nSearch = new SpillNSWrapper<SortPolicy>(searchMode, epsilon);
+      break;
+    case UB_TREE:
+      nSearch = new NSWrapper<SortPolicy, tree::UBTree>(searchMode, epsilon);
+      break;
+    case OCTREE:
+      nSearch = new LeafSizeNSWrapper<SortPolicy, tree::Octree>(searchMode,
+          epsilon);
+      break;
+  }
+
 }
 
 //! Build the reference tree.
 template<typename SortPolicy>
 void NSModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
-                                     const size_t leafSize,
                                      const NeighborSearchMode searchMode,
                                      const double epsilon)
 {
-  this->leafSize = leafSize;
   // Initialize random basis if necessary.
   if (randomBasis)
   {
@@ -445,9 +557,6 @@ void NSModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
     }
   }
 
-  // Clean memory, if necessary.
-  boost::apply_visitor(DeleteVisitor(), nSearch);
-
   // Do we need to modify the reference set?
   if (randomBasis)
     referenceSet = q * referenceSet;
@@ -458,59 +567,8 @@ void NSModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
     Log::Info << "Building reference tree..." << std::endl;
   }
 
-  switch (treeType)
-  {
-    case KD_TREE:
-      nSearch = new NSType<SortPolicy, tree::KDTree>(searchMode, epsilon);
-      break;
-    case COVER_TREE:
-      nSearch = new NSType<SortPolicy, tree::StandardCoverTree>(searchMode,
-          epsilon);
-      break;
-    case R_TREE:
-      nSearch = new NSType<SortPolicy, tree::RTree>(searchMode, epsilon);
-      break;
-    case R_STAR_TREE:
-      nSearch = new NSType<SortPolicy, tree::RStarTree>(searchMode, epsilon);
-      break;
-    case BALL_TREE:
-      nSearch = new NSType<SortPolicy, tree::BallTree>(searchMode, epsilon);
-      break;
-    case X_TREE:
-      nSearch = new NSType<SortPolicy, tree::XTree>(searchMode, epsilon);
-      break;
-    case HILBERT_R_TREE:
-      nSearch = new NSType<SortPolicy, tree::HilbertRTree>(searchMode, epsilon);
-      break;
-    case R_PLUS_TREE:
-      nSearch = new NSType<SortPolicy, tree::RPlusTree>(searchMode, epsilon);
-      break;
-    case R_PLUS_PLUS_TREE:
-      nSearch = new NSType<SortPolicy, tree::RPlusPlusTree>(searchMode,
-          epsilon);
-      break;
-    case VP_TREE:
-      nSearch = new NSType<SortPolicy, tree::VPTree>(searchMode, epsilon);
-      break;
-    case RP_TREE:
-      nSearch = new NSType<SortPolicy, tree::RPTree>(searchMode, epsilon);
-      break;
-    case MAX_RP_TREE:
-      nSearch = new NSType<SortPolicy, tree::MaxRPTree>(searchMode, epsilon);
-      break;
-    case SPILL_TREE:
-      nSearch = new SpillKNN(searchMode, epsilon);
-      break;
-    case UB_TREE:
-      nSearch = new NSType<SortPolicy, tree::UBTree>(searchMode, epsilon);
-      break;
-    case OCTREE:
-      nSearch = new NSType<SortPolicy, tree::Octree>(searchMode, epsilon);
-      break;
-  }
-
-  TrainVisitor<SortPolicy> tn(std::move(referenceSet), leafSize, tau, rho);
-  boost::apply_visitor(tn, nSearch);
+  InitializeModel(searchMode, epsilon);
+  nSearch->Train(std::move(referenceSet), leafSize, tau, rho);
 
   if (searchMode != NAIVE_MODE)
   {
@@ -549,9 +607,7 @@ void NSModel<SortPolicy>::Search(arma::mat&& querySet,
       break;
   }
 
-  BiSearchVisitor<SortPolicy> search(querySet, k, neighbors, distances,
-      leafSize, tau, rho);
-  boost::apply_visitor(search, nSearch);
+  nSearch->Search(std::move(querySet), k, neighbors, distances, leafSize, rho);
 }
 
 //! Perform neighbor search.
@@ -583,8 +639,7 @@ void NSModel<SortPolicy>::Search(const size_t k,
     Log::Info << "Maximum of " << Epsilon() * 100 << "% relative error."
         << std::endl;
 
-  MonoSearchVisitor search(k, neighbors, distances);
-  boost::apply_visitor(search, nSearch);
+  nSearch->Search(k, neighbors, distances);
 }
 
 //! Get the name of the tree type.
diff --git a/src/mlpack/tests/aknn_test.cpp b/src/mlpack/tests/aknn_test.cpp
index 37b5e820da..9358b57de7 100644
--- a/src/mlpack/tests/aknn_test.cpp
+++ b/src/mlpack/tests/aknn_test.cpp
@@ -370,14 +370,13 @@ TEST_CASE("AKNNModelTest", "[AKNNTest]")
       // We only have std::move() constructors so make a copy of our data.
       arma::mat referenceCopy(referenceData);
       arma::mat queryCopy(queryData);
+      models[i].LeafSize() = 20;
       if (j == 0)
-        models[i].BuildModel(std::move(referenceCopy), 20, DUAL_TREE_MODE,
-            0.05);
+        models[i].BuildModel(std::move(referenceCopy), DUAL_TREE_MODE, 0.05);
       if (j == 1)
-        models[i].BuildModel(std::move(referenceCopy), 20,
-            SINGLE_TREE_MODE, 0.05);
+        models[i].BuildModel(std::move(referenceCopy), SINGLE_TREE_MODE, 0.05);
       if (j == 2)
-        models[i].BuildModel(std::move(referenceCopy), 20, NAIVE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), NAIVE_MODE);
 
       arma::Mat<size_t> neighborsApprox;
       arma::mat distancesApprox;
@@ -448,12 +447,11 @@ TEST_CASE("AKNNModelMonochromaticTest", "[AKNNTest]")
     {
       // We only have a std::move() constructor... so copy the data.
       arma::mat referenceCopy(referenceData);
+      models[i].LeafSize() = 20;
       if (j == 0)
-        models[i].BuildModel(std::move(referenceCopy), 20, DUAL_TREE_MODE,
-            0.05);
+        models[i].BuildModel(std::move(referenceCopy), DUAL_TREE_MODE, 0.05);
       if (j == 1)
-        models[i].BuildModel(std::move(referenceCopy), 20,
-            SINGLE_TREE_MODE, 0.05);
+        models[i].BuildModel(std::move(referenceCopy), SINGLE_TREE_MODE, 0.05);
 
       arma::Mat<size_t> neighborsApprox;
       arma::mat distancesApprox;
diff --git a/src/mlpack/tests/knn_test.cpp b/src/mlpack/tests/knn_test.cpp
index 7e84700843..31f1daf056 100644
--- a/src/mlpack/tests/knn_test.cpp
+++ b/src/mlpack/tests/knn_test.cpp
@@ -1112,28 +1112,28 @@ TEST_CASE("KNNModelTest", "[KNNTest]")
       // We only have std::move() constructors so make a copy of our data.
       arma::mat referenceCopy(referenceData);
       arma::mat queryCopy(queryData);
+      models[i].LeafSize() = 20;
       if (j == 0)
-        models[i].BuildModel(std::move(referenceCopy), 20, DUAL_TREE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), DUAL_TREE_MODE);
       if (j == 1)
-        models[i].BuildModel(std::move(referenceCopy), 20,
-            SINGLE_TREE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), SINGLE_TREE_MODE);
       if (j == 2)
-        models[i].BuildModel(std::move(referenceCopy), 20, NAIVE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), NAIVE_MODE);
 
       arma::Mat<size_t> neighbors;
       arma::mat distances;
 
       models[i].Search(std::move(queryCopy), 3, neighbors, distances);
 
-      REQUIRE(neighbors.n_rows ==baselineNeighbors.n_rows);
-      REQUIRE(neighbors.n_cols ==baselineNeighbors.n_cols);
-      REQUIRE(neighbors.n_elem ==baselineNeighbors.n_elem);
-      REQUIRE(distances.n_rows ==baselineDistances.n_rows);
-      REQUIRE(distances.n_cols ==baselineDistances.n_cols);
-      REQUIRE(distances.n_elem ==baselineDistances.n_elem);
+      REQUIRE(neighbors.n_rows == baselineNeighbors.n_rows);
+      REQUIRE(neighbors.n_cols == baselineNeighbors.n_cols);
+      REQUIRE(neighbors.n_elem == baselineNeighbors.n_elem);
+      REQUIRE(distances.n_rows == baselineDistances.n_rows);
+      REQUIRE(distances.n_cols == baselineDistances.n_cols);
+      REQUIRE(distances.n_elem == baselineDistances.n_elem);
       for (size_t k = 0; k < distances.n_elem; ++k)
       {
-        REQUIRE(neighbors[k] ==baselineNeighbors[k]);
+        REQUIRE(neighbors[k] == baselineNeighbors[k]);
         if (std::abs(baselineDistances[k]) < 1e-5)
           REQUIRE(distances[k] == Approx(0.0).margin(1e-7));
         else
@@ -1194,28 +1194,28 @@ TEST_CASE("KNNModelMonochromaticTest", "[KNNTest]")
     {
       // We only have a std::move() constructor... so copy the data.
       arma::mat referenceCopy(referenceData);
+      models[i].LeafSize() = 20;
       if (j == 0)
-        models[i].BuildModel(std::move(referenceCopy), 20, DUAL_TREE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), DUAL_TREE_MODE);
       if (j == 1)
-        models[i].BuildModel(std::move(referenceCopy), 20,
-            SINGLE_TREE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), SINGLE_TREE_MODE);
       if (j == 2)
-        models[i].BuildModel(std::move(referenceCopy), 20, NAIVE_MODE);
+        models[i].BuildModel(std::move(referenceCopy), NAIVE_MODE);
 
       arma::Mat<size_t> neighbors;
       arma::mat distances;
 
       models[i].Search(3, neighbors, distances);
 
-      REQUIRE(neighbors.n_rows ==baselineNeighbors.n_rows);
-      REQUIRE(neighbors.n_cols ==baselineNeighbors.n_cols);
-      REQUIRE(neighbors.n_elem ==baselineNeighbors.n_elem);
-      REQUIRE(distances.n_rows ==baselineDistances.n_rows);
-      REQUIRE(distances.n_cols ==baselineDistances.n_cols);
-      REQUIRE(distances.n_elem ==baselineDistances.n_elem);
+      REQUIRE(neighbors.n_rows == baselineNeighbors.n_rows);
+      REQUIRE(neighbors.n_cols == baselineNeighbors.n_cols);
+      REQUIRE(neighbors.n_elem == baselineNeighbors.n_elem);
+      REQUIRE(distances.n_rows == baselineDistances.n_rows);
+      REQUIRE(distances.n_cols == baselineDistances.n_cols);
+      REQUIRE(distances.n_elem == baselineDistances.n_elem);
       for (size_t k = 0; k < distances.n_elem; ++k)
       {
-        REQUIRE(neighbors[k] ==baselineNeighbors[k]);
+        REQUIRE(neighbors[k] == baselineNeighbors[k]);
         if (std::abs(baselineDistances[k]) < 1e-5)
           REQUIRE(distances[k] == Approx(0.0).margin(1e-7));
         else

From 8462fc20bde74dba00c2c7145a26875e141ca2cb Mon Sep 17 00:00:00 2001
From: Anmolpreet Singh <54476451+Anmol2001@users.noreply.github.com>
Date: Wed, 6 Jan 2021 00:29:22 +0530
Subject: [PATCH 045/253] updated method description

---
 src/mlpack/methods/pca/pca_impl.hpp | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/mlpack/methods/pca/pca_impl.hpp b/src/mlpack/methods/pca/pca_impl.hpp
index ce2ecedc66..a122cd7159 100644
--- a/src/mlpack/methods/pca/pca_impl.hpp
+++ b/src/mlpack/methods/pca/pca_impl.hpp
@@ -76,9 +76,7 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
 }
     
 /**
- * This is another Overload of apply with only 2 parameteres(data & transformed data)
- * and it will create eigval and eigvec and store the corresponding values  in them
- * as the source of information are first 2 parameters only.
+ * Apply Principal Component Analysis to the provided data set.
  *
  * @param data - Data matrix
  * @param transformedData - Data with PCA applied

From 116c534a2b57a778a02b07bb7736206f2ba14858 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 5 Jan 2021 14:45:06 -0500
Subject: [PATCH 046/253] Fix missing parenthesis.

---
 src/mlpack/bindings/R/CMakeLists.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index a6e8ee16e1..13f171140d 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -230,7 +230,7 @@ if (BUILD_R_BINDINGS)
   install(CODE
       "execute_process(
          COMMAND R CMD INSTALL mlpack_${PACKAGE_VERSION}.tar.gz
-         WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}"
+         WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})"
   )
 
   add_dependencies(R r_build)

From 43c62e830a60361e3ff41fb233aa2fe2c539a664 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 5 Jan 2021 14:45:28 -0500
Subject: [PATCH 047/253] Update issue number.

---
 HISTORY.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HISTORY.md b/HISTORY.md
index 9bb5fc29ff..918c95a59f 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -14,7 +14,7 @@
   * Add finalizers to Julia binding model types to fix memory handling (#2756).
 
   * Add `PYTHON_INSTALL_PREFIX` CMake option to specify installation root for
-    Python bindings.
+    Python bindings (#2797).
 
 ### mlpack 3.4.2
 ###### 2020-10-26

From b89af6ef324403b1c7c36abe13e6f721922061af Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Wed, 6 Jan 2021 10:25:39 +0530
Subject: [PATCH 048/253] Update src/mlpack/tests/test_catch_tools.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/tests/test_catch_tools.hpp | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/mlpack/tests/test_catch_tools.hpp b/src/mlpack/tests/test_catch_tools.hpp
index 7b34cfc150..dfd0577b19 100644
--- a/src/mlpack/tests/test_catch_tools.hpp
+++ b/src/mlpack/tests/test_catch_tools.hpp
@@ -64,7 +64,6 @@ inline void CheckFields(const FieldType& a,
     CheckMatrices(a(i), b(i));
 }
 
-
 // Check the values of two cubes.
 inline void CheckMatrices(const arma::cube& a,
                           const arma::cube& b,

From d50af3ee7bb2529638c6b22cee5bc6e4bdb3123f Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Wed, 6 Jan 2021 12:47:22 +0530
Subject: [PATCH 049/253] Added documentation for template parameter

---
 src/mlpack/core/data/split_data.hpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 02395ad432..8a50ceeaf3 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -169,6 +169,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  *                testData, trainLabel, testLabel, 0.3);
  * @endcode
  *
+ * @tparam T Type of the elements of the input matrix.
  * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
@@ -298,6 +299,7 @@ void Split(const arma::Mat<T>& input,
  * auto splitResult = Split(input, label, 0.2);
  * @endcode
  *
+ * @tparam T Type of the elements of the input matrix.
  * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.

From fe6facd9b47c3b7c06f5d7b010208c3ad7174ea1 Mon Sep 17 00:00:00 2001
From: ayushsingh11 <30299945+ayushsingh11@users.noreply.github.com>
Date: Sat, 9 Jan 2021 11:44:55 +0530
Subject: [PATCH 050/253] Minor Fix - Removed redundant ()

---
 src/mlpack/methods/ann/layer/multihead_attention.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/multihead_attention.hpp b/src/mlpack/methods/ann/layer/multihead_attention.hpp
index 0c2713c0e8..0d7506ea51 100644
--- a/src/mlpack/methods/ann/layer/multihead_attention.hpp
+++ b/src/mlpack/methods/ann/layer/multihead_attention.hpp
@@ -121,7 +121,7 @@ class MultiheadAttention
                 arma::Mat<eT>& gradient);
 
   //! Get the size of the weights.
-  size_t WeightSize() const { return (4 * (embedDim + 1) * embedDim); }
+  size_t WeightSize() const { return 4 * (embedDim + 1) * embedDim; }
 
   /**
    * Serialize the layer.

From 2b1778ab7aa5221a976d81dce6b8ca3a524459e3 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 9 Jan 2021 21:48:21 -0500
Subject: [PATCH 051/253] Clarify comments.

---
 src/mlpack/methods/neighbor_search/ns_model.hpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/neighbor_search/ns_model.hpp b/src/mlpack/methods/neighbor_search/ns_model.hpp
index c88b6226cd..b13918fa7d 100644
--- a/src/mlpack/methods/neighbor_search/ns_model.hpp
+++ b/src/mlpack/methods/neighbor_search/ns_model.hpp
@@ -4,9 +4,9 @@
  *
  * This is a model for nearest or furthest neighbor search.  It is useful in
  * that it provides an easy way to serialize a model, abstracts away the
- * different types of trees, and also (roughly) reflects the NeighborSearch API and
- * automatically directs to the right tree type.  It is meant to be used by the
- * knn and kfn bindings.
+ * different types of trees, and also (roughly) reflects the NeighborSearch API
+ * and automatically directs to the right tree type.  It is meant to be used by
+ * the knn and kfn bindings.
  *
  * mlpack is free software; you may redistribute it and/or modify it under the
  * terms of the 3-clause BSD license.  You should have received a copy of the

From f0e570f5b4901dc0584f570f3170b7c19692e77b Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 9 Jan 2021 21:48:46 -0500
Subject: [PATCH 052/253] Refactor RAModel to not use boost::visitor.

---
 src/mlpack/methods/rann/CMakeLists.txt     |   1 +
 src/mlpack/methods/rann/krann_main.cpp     |  39 +-
 src/mlpack/methods/rann/ra_model.cpp       | 234 ++++++++
 src/mlpack/methods/rann/ra_model.hpp       | 474 +++++++--------
 src/mlpack/methods/rann/ra_model_impl.hpp  | 662 ++++-----------------
 src/mlpack/methods/rann/ra_search.hpp      |   9 +-
 src/mlpack/tests/krann_search_test.cpp     |  44 +-
 src/mlpack/tests/main_tests/krann_test.cpp |  42 +-
 8 files changed, 650 insertions(+), 855 deletions(-)
 create mode 100644 src/mlpack/methods/rann/ra_model.cpp

diff --git a/src/mlpack/methods/rann/CMakeLists.txt b/src/mlpack/methods/rann/CMakeLists.txt
index 99e838b459..42a70dbc26 100644
--- a/src/mlpack/methods/rann/CMakeLists.txt
+++ b/src/mlpack/methods/rann/CMakeLists.txt
@@ -23,6 +23,7 @@ set(SOURCES
   # model
   ra_model.hpp
   ra_model_impl.hpp
+  ra_model.cpp
 )
 
 # add directory name to sources
diff --git a/src/mlpack/methods/rann/krann_main.cpp b/src/mlpack/methods/rann/krann_main.cpp
index 9d830f5fff..0ed34fd0f2 100644
--- a/src/mlpack/methods/rann/krann_main.cpp
+++ b/src/mlpack/methods/rann/krann_main.cpp
@@ -25,9 +25,6 @@ using namespace mlpack::tree;
 using namespace mlpack::metric;
 using namespace mlpack::util;
 
-// Convenience typedef.
-typedef RAModel<NearestNeighborSort> RANNModel;
-
 // Program Name.
 BINDING_NAME("K-Rank-Approximate-Nearest-Neighbors (kRANN)");
 
@@ -86,8 +83,8 @@ PARAM_MATRIX_OUT("distances", "Matrix to output distances into.", "d");
 PARAM_UMATRIX_OUT("neighbors", "Matrix to output neighbors into.", "n");
 
 // The option exists to load or save models.
-PARAM_MODEL_IN(RANNModel, "input_model", "Pre-trained kNN model.", "m");
-PARAM_MODEL_OUT(RANNModel, "output_model", "If specified, the kNN model will be"
+PARAM_MODEL_IN(RAModel, "input_model", "Pre-trained kNN model.", "m");
+PARAM_MODEL_OUT(RAModel, "output_model", "If specified, the kNN model will be"
     " output here.", "M");
 
 // The user may specify a query file of query points and a number of nearest
@@ -170,12 +167,12 @@ static void mlpackMain()
       "alpha must be in range [0.0, 1.0]");
 
   // We either have to load the reference data, or we have to load the model.
-  RANNModel* rann;
+  RAModel* rann;
   const bool naive = IO::HasParam("naive");
   const bool singleMode = IO::HasParam("single_mode");
   if (IO::HasParam("reference"))
   {
-    rann = new RANNModel();
+    rann = new RAModel();
 
     // Get all the parameters.
     const string treeType = IO::GetParam<string>("tree_type");
@@ -184,27 +181,27 @@ static void mlpackMain()
         "unknown tree type");
     const bool randomBasis = IO::HasParam("random_basis");
 
-    RANNModel::TreeTypes tree = RANNModel::KD_TREE;
+    RAModel::TreeTypes tree = RAModel::KD_TREE;
     if (treeType == "kd")
-      tree = RANNModel::KD_TREE;
+      tree = RAModel::KD_TREE;
     else if (treeType == "cover")
-      tree = RANNModel::COVER_TREE;
+      tree = RAModel::COVER_TREE;
     else if (treeType == "r")
-      tree = RANNModel::R_TREE;
+      tree = RAModel::R_TREE;
     else if (treeType == "r-star")
-      tree = RANNModel::R_STAR_TREE;
+      tree = RAModel::R_STAR_TREE;
     else if (treeType == "x")
-      tree = RANNModel::X_TREE;
+      tree = RAModel::X_TREE;
     else if (treeType == "hilbert-r")
-      tree = RANNModel::HILBERT_R_TREE;
+      tree = RAModel::HILBERT_R_TREE;
     else if (treeType == "r-plus")
-      tree = RANNModel::R_PLUS_TREE;
+      tree = RAModel::R_PLUS_TREE;
     else if (treeType == "r-plus-plus")
-      tree = RANNModel::R_PLUS_PLUS_TREE;
+      tree = RAModel::R_PLUS_PLUS_TREE;
     else if (treeType == "ub")
-      tree = RANNModel::UB_TREE;
+      tree = RAModel::UB_TREE;
     else if (treeType == "oct")
-      tree = RANNModel::OCTREE;
+      tree = RAModel::OCTREE;
 
     rann->TreeType() = tree;
     rann->RandomBasis() = randomBasis;
@@ -218,10 +215,10 @@ static void mlpackMain()
   else
   {
     // Load the model from file.
-    rann = IO::GetParam<RANNModel*>("input_model");
+    rann = IO::GetParam<RAModel*>("input_model");
 
     Log::Info << "Using rank-approximate kNN model from '"
-        << IO::GetPrintableParam<RANNModel*>("input_model") << "' (trained on "
+        << IO::GetPrintableParam<RAModel*>("input_model") << "' (trained on "
         << rann->Dataset().n_rows << "x" << rann->Dataset().n_cols
         << " dataset)." << endl;
 
@@ -285,5 +282,5 @@ static void mlpackMain()
   }
 
   // Save the output model.
-  IO::GetParam<RANNModel*>("output_model") = rann;
+  IO::GetParam<RAModel*>("output_model") = rann;
 }
diff --git a/src/mlpack/methods/rann/ra_model.cpp b/src/mlpack/methods/rann/ra_model.cpp
new file mode 100644
index 0000000000..a6a997a22c
--- /dev/null
+++ b/src/mlpack/methods/rann/ra_model.cpp
@@ -0,0 +1,234 @@
+/**
+ * @file methods/rann/ra_model.cpp
+ * @author Ryan Curtin
+ *
+ * Implementation of the RAModel class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include "ra_model.hpp"
+#include <mlpack/core/math/random_basis.hpp>
+
+namespace mlpack {
+namespace neighbor {
+
+RAModel::RAModel(const TreeTypes treeType, const bool randomBasis) :
+    treeType(treeType),
+    leafSize(20),
+    randomBasis(randomBasis),
+    raSearch(NULL)
+{
+  // Nothing to do.
+}
+
+// Copy constructor.
+RAModel::RAModel(const RAModel& other) :
+    treeType(other.treeType),
+    leafSize(other.leafSize),
+    randomBasis(other.randomBasis),
+    q(other.q),
+    raSearch(other.raSearch->Clone())
+{
+  // Nothing to do.
+}
+
+// Move constructor.
+RAModel::RAModel(RAModel&& other) :
+    treeType(other.treeType),
+    leafSize(other.leafSize),
+    randomBasis(other.randomBasis),
+    q(std::move(other.q)),
+    raSearch(std::move(other.raSearch))
+{
+  // Clear other model.
+  other.treeType = TreeTypes::KD_TREE;
+  other.leafSize = 20;
+  other.randomBasis = false;
+}
+
+// Copy operator.
+RAModel& RAModel::operator=(const RAModel& other)
+{
+  if (this != &other)
+  {
+    // Clear current model.
+    delete raSearch;
+
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = other.q;
+    raSearch = other.raSearch->Clone();
+  }
+
+  return *this;
+}
+
+RAModel& RAModel::operator=(RAModel&& other)
+{
+  if (this != &other)
+  {
+    // Clear current model.
+    delete raSearch;
+
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = std::move(other.q);
+    raSearch = std::move(other.raSearch);
+
+    // Reset other model.
+    other.treeType = TreeTypes::KD_TREE;
+    other.leafSize = 20;
+    other.randomBasis = false;
+  }
+
+  return *this;
+}
+
+// Clean memory, if necessary
+RAModel::~RAModel()
+{
+  delete raSearch;
+}
+
+void RAModel::BuildModel(arma::mat&& referenceSet,
+                                     const size_t leafSize,
+                                     const bool naive,
+                                     const bool singleMode)
+{
+  // Initialize random basis, if necessary.
+  if (randomBasis)
+  {
+    Log::Info << "Creating random basis..." << std::endl;
+    math::RandomBasis(q, referenceSet.n_rows);
+  }
+
+  // Clean memory, if necessary.
+  delete raSearch;
+
+  this->leafSize = leafSize;
+
+  if (randomBasis)
+    referenceSet = q * referenceSet;
+
+  if (!naive)
+  {
+    Timer::Start("tree_building");
+    Log::Info << "Building reference tree..." << std::endl;
+  }
+
+  switch (treeType)
+  {
+    case KD_TREE:
+      raSearch = new LeafSizeRAWrapper<tree::KDTree>(naive, singleMode);
+      break;
+    case COVER_TREE:
+      raSearch = new RAWrapper<tree::StandardCoverTree>(naive, singleMode);
+      break;
+    case R_TREE:
+      raSearch = new RAWrapper<tree::RTree>(naive, singleMode);
+      break;
+    case R_STAR_TREE:
+      raSearch = new RAWrapper<tree::RStarTree>(naive, singleMode);
+      break;
+    case X_TREE:
+      raSearch = new RAWrapper<tree::XTree>(naive, singleMode);
+      break;
+    case HILBERT_R_TREE:
+      raSearch = new RAWrapper<tree::HilbertRTree>(naive, singleMode);
+      break;
+    case R_PLUS_TREE:
+      raSearch = new RAWrapper<tree::RPlusTree>(naive, singleMode);
+      break;
+    case R_PLUS_PLUS_TREE:
+      raSearch = new RAWrapper<tree::RPlusPlusTree>(naive, singleMode);
+      break;
+    case UB_TREE:
+      raSearch = new RAWrapper<tree::UBTree>(naive, singleMode);
+      break;
+    case OCTREE:
+      raSearch = new LeafSizeRAWrapper<tree::Octree>(naive, singleMode);
+      break;
+  }
+
+  raSearch->Train(std::move(referenceSet), leafSize);
+
+  if (!naive)
+  {
+    Timer::Stop("tree_building");
+    Log::Info << "Tree built." << std::endl;
+  }
+}
+
+void RAModel::Search(arma::mat&& querySet,
+                     const size_t k,
+                     arma::Mat<size_t>& neighbors,
+                     arma::mat& distances)
+{
+  // Apply the random basis if necessary.
+  if (randomBasis)
+    querySet = q * querySet;
+
+  Log::Info << "Searching for " << k << " approximate nearest neighbors with ";
+  if (!Naive() && !SingleMode())
+    Log::Info << "dual-tree rank-approximate " << TreeName() << " search...";
+  else if (!Naive())
+    Log::Info << "single-tree rank-approximate " << TreeName() << " search...";
+  else
+    Log::Info << "brute-force (naive) rank-approximate search...";
+  Log::Info << std::endl;
+
+  raSearch->Search(std::move(querySet), k, neighbors, distances, leafSize);
+}
+
+void RAModel::Search(const size_t k,
+                     arma::Mat<size_t>& neighbors,
+                     arma::mat& distances)
+{
+  Log::Info << "Searching for " << k << " approximate nearest neighbors with ";
+  if (!Naive() && !SingleMode())
+    Log::Info << "dual-tree rank-approximate " << TreeName() << " search...";
+  else if (!Naive())
+    Log::Info << "single-tree rank-approximate " << TreeName() << " search...";
+  else
+    Log::Info << "brute-force (naive) rank-approximate search...";
+  Log::Info << std::endl;
+
+  raSearch->Search(k, neighbors, distances);
+}
+
+std::string RAModel::TreeName() const
+{
+  switch (treeType)
+  {
+    case KD_TREE:
+      return "kd-tree";
+    case COVER_TREE:
+      return "cover tree";
+    case R_TREE:
+      return "R tree";
+    case R_STAR_TREE:
+      return "R* tree";
+    case X_TREE:
+      return "X tree";
+    case HILBERT_R_TREE:
+      return "Hilbert R tree";
+    case R_PLUS_TREE:
+      return "R+ tree";
+    case R_PLUS_PLUS_TREE:
+      return "R++ tree";
+    case UB_TREE:
+      return "UB tree";
+    case OCTREE:
+      return "octree";
+    default:
+      return "unknown tree";
+  }
+}
+
+} // namespace neighbor
+} // namespace mlpack
diff --git a/src/mlpack/methods/rann/ra_model.hpp b/src/mlpack/methods/rann/ra_model.hpp
index ed32d4a352..afe42bf3da 100644
--- a/src/mlpack/methods/rann/ra_model.hpp
+++ b/src/mlpack/methods/rann/ra_model.hpp
@@ -25,238 +25,228 @@ namespace mlpack {
 namespace neighbor {
 
 /**
- * Alias template for RASearch
+ * RAWrapperBase is a base wrapper class for holding all RASearch types
+ * supported by RAModel.  All RASearch type wrappers inherit from this class,
+ * allowing a simple interface via inheritance for all the different types we
+ * want to support.
  */
-template<typename SortPolicy,
-         template<typename TreeMetricType,
+class RAWrapperBase
+{
+ public:
+  //! Create the RAWrapperBase object.  The base class does not hold anything,
+  //! so this constructor does nothing.
+  RAWrapperBase() { }
+
+  //! Create a new RAWrapperBase that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual RAWrapperBase* Clone() const = 0;
+
+  //! Destruct the RAWrapperBase (nothing to do).
+  virtual ~RAWrapperBase() { };
+
+  //! Return a reference to the dataset.
+  virtual const arma::mat& Dataset() const = 0;
+
+  //! Get the single sample limit.
+  virtual size_t SingleSampleLimit() const = 0;
+  //! Modify the single sample limit.
+  virtual size_t& SingleSampleLimit() = 0;
+
+  //! Get whether to do exact search at the first leaf.
+  virtual bool FirstLeafExact() const = 0;
+  //! Modify whether to do exact search at the first leaf.
+  virtual bool& FirstLeafExact() = 0;
+
+  //! Get whether to do sampling at leaves.
+  virtual bool SampleAtLeaves() const = 0;
+  //! Modify whether to do sampling at leaves.
+  virtual bool& SampleAtLeaves() = 0;
+
+  //! Get the value of alpha.
+  virtual double Alpha() const = 0;
+  //! Modify the value of alpha.
+  virtual double& Alpha() = 0;
+
+  //! Get the value of tau.
+  virtual double Tau() const = 0;
+  //! Modify the value of tau.
+  virtual double& Tau() = 0;
+
+  //! Get whether single-tree search is being used.
+  virtual bool SingleMode() const = 0;
+  //! Modify whether single-tree search is being used.
+  virtual bool& SingleMode() = 0;
+
+  //! Get whether naive search is being used.
+  virtual bool Naive() const = 0;
+  //! Modify whether naive search is being used.
+  virtual bool& Naive() = 0;
+
+  //! Train the RASearch model with the given parameters.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize) = 0;
+
+  //! Perform bichromatic rank-approximate nearest neighbor search (i.e. search
+  //! with a separate query set).
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize) = 0;
+
+  //! Perform monochromatic rank-approximate nearest neighbor search (i.e. a
+  //! search with the reference set as the query set).
+  virtual void Search(const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances) = 0;
+};
+
+/**
+ * RAWrapper is a wrapper class for most RASearch types.
+ */
+template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-using RAType = RASearch<SortPolicy,
-                        metric::EuclideanDistance,
-                        arma::mat,
-                        TreeType>;
-
-/**
- * MonoSearchVisitor executes a monochromatic neighbor search on the given
- * RAType. We don't make any difference for different instantiation of RAType.
- */
-class MonoSearchVisitor : public boost::static_visitor<void>
+class RAWrapper : public RAWrapperBase
 {
- private:
-  //! Number of neighbors to search for.
-  const size_t k;
-  //! Result matrix for neighbors.
-  arma::Mat<size_t>& neighbors;
-  //! Result matrix for distances.
-  arma::mat& distances;
-
  public:
-  //! Perform monochromatic nearest neighbor search.
-  template<typename RAType>
-  void operator()(RAType* ra) const;
+  //! Construct the RAWrapper object, initializing the internally-held RASearch
+  //! object.
+  RAWrapper(const bool singleMode, const bool naive) :
+      ra(singleMode, naive)
+  {
+    // Nothing else to do.
+  }
 
-  //! Construct the MonoSearchVisitor object with the given parameters.
-  MonoSearchVisitor(const size_t k,
-                    arma::Mat<size_t>& neighbors,
-                    arma::mat& distances) :
-      k(k),
-      neighbors(neighbors),
-      distances(distances)
-  {};
+  //! Delete the RAWrapper object.
+  virtual ~RAWrapper() { }
+
+  //! Create a copy of this RAWrapper object.  This correctly handles
+  //! polymorphism.
+  virtual RAWrapper* Clone() const { return new RAWrapper(*this); }
+
+  //! Get a reference to the reference set.
+  const arma::mat& Dataset() const { return ra.ReferenceSet(); }
+
+  //! Get the single sample limit.
+  size_t SingleSampleLimit() const { return ra.SingleSampleLimit(); }
+  //! Modify the single sample limit.
+  size_t& SingleSampleLimit() { return ra.SingleSampleLimit(); }
+
+  //! Get whether to do exact search at the first leaf.
+  bool FirstLeafExact() const { return ra.FirstLeafExact(); }
+  //! Modify whether to do exact search at the first leaf.
+  bool& FirstLeafExact() { return ra.FirstLeafExact(); }
+
+  //! Get whether to do sampling at leaves.
+  bool SampleAtLeaves() const { return ra.SampleAtLeaves(); }
+  //! Modify whether to do sampling at leaves.
+  bool& SampleAtLeaves() { return ra.SampleAtLeaves(); }
+
+  //! Get the value of alpha.
+  double Alpha() const { return ra.Alpha(); }
+  //! Modify the value of alpha.
+  double& Alpha() { return ra.Alpha(); }
+
+  //! Get the value of tau.
+  double Tau() const { return ra.Tau(); }
+  //! Modify the value of tau.
+  double& Tau() { return ra.Tau(); }
+
+  //! Get whether single-tree search is being used.
+  bool SingleMode() const { return ra.SingleMode(); }
+  //! Modify whether single-tree search is being used.
+  bool& SingleMode() { return ra.SingleMode(); }
+
+  //! Get whether naive search is being used.
+  bool Naive() const { return ra.Naive(); }
+  //! Modify whether naive search is being used.
+  bool& Naive() { return ra.Naive(); }
+
+  //! Train the model.  For RAWrapper, we ignore the leaf size.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t /* leafSize */);
+
+  //! Perform bichromatic neighbor search (i.e. search with a separate query
+  //! set).  For RAWrapper, we ignore the leaf size.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t /* leafSize */);
+
+  //! Perform monochromatic neighbor search (i.e. search where the reference set
+  //! is used as the query set).
+  virtual void Search(const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances);
+
+  //! Serialize the RASearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(ra));
+  }
+
+ protected:
+  typedef RASearch<NearestNeighborSort,
+                   metric::EuclideanDistance,
+                   arma::mat,
+                   TreeType> RAType;
+
+  //! The instantiated RASearch object that we are wrapping.
+  RAType ra;
 };
 
 /**
- * BiSearchVisitor executes a bichromatic neighbor search on the given RAType.
- * We use template specialization to differentiate those tree types types that
- * accept leafSize as a parameter. In these cases, before doing neighbor search
- * a query tree with proper leafSize is built from the querySet.
+ * LeafSizeRAWrapper wraps any RASearch type that needs to be able to take the
+ * leaf size into account when building trees.  The implementations of Train()
+ * and bichromatic Search() take this leaf size into account.
  */
-template<typename SortPolicy>
-class BiSearchVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The query set for the bichromatic search.
-  const arma::mat& querySet;
-  //! The number of neighbors to search for.
-  const size_t k;
-  //! The results matrix for neighbors.
-  arma::Mat<size_t>& neighbors;
-  //! The result matrix for distances.
-  arma::mat& distances;
-  //! The number of points in a leaf (for BinarySpaceTrees).
-  const size_t leafSize;
-
-  //! Bichromatic neighbor search on the given RAType considering leafSize.
-  template<typename RAType>
-  void SearchLeaf(RAType* ra) const;
-
- public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using RATypeT = RAType<SortPolicy, TreeType>;
-
-  //! Default Bichromatic neighbor search on the given RAType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(RATypeT<TreeType>* ra) const;
-
-  //! Bichromatic search on the given RAType specialized for KDTrees.
-  void operator()(RATypeT<tree::KDTree>* ra) const;
-
-  //! Bichromatic search on the given RAType specialized for octrees.
-  void operator()(RATypeT<tree::Octree>* ra) const;
-
-  //! Construct the BiSearchVisitor.
-  BiSearchVisitor(const arma::mat& querySet,
-                  const size_t k,
-                  arma::Mat<size_t>& neighbors,
-                  arma::mat& distances,
-                  const size_t leafSize);
-};
-
-/**
- * TrainVisitor sets the reference set to a new reference set on the given
- * RAType. We use template specialization to differentiate those trees that 
- * accept leafSize as a parameter. In these cases, a reference tree with proper
- * leafSize is built from the referenceSet.
- */
-template<typename SortPolicy>
-class TrainVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The reference set to use for training.
-  arma::mat&& referenceSet;
-  //! The leaf size, used only by BinarySpaceTree.
-  size_t leafSize;
-
-  //! Train on the given RAType considering the leafSize.
-  template<typename RAType>
-  void TrainLeaf(RAType* ra) const;
-
- public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using RATypeT = RAType<SortPolicy, TreeType>;
-
-  //! Default Train on the given RAType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(RATypeT<TreeType>* ra) const;
-
-  //! Train on the given RAType specialized for KDTrees.
-  void operator()(RATypeT<tree::KDTree>* ra) const;
-
-  //! Train on the given RAType specialized for Octrees.
-  void operator()(RATypeT<tree::Octree>* ra) const;
-
-  //! Construct the TrainVisitor object with the given reference set, leafSize
-  //! for BinarySpaceTrees.
-  TrainVisitor(arma::mat&& referenceSet,
-               const size_t leafSize);
-};
-
-/**
- * Exposes the SingleSampleLimit() method of the given RAType.
- */
-class SingleSampleLimitVisitor : public boost::static_visitor<size_t&>
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+class LeafSizeRAWrapper : public RAWrapper<TreeType>
 {
  public:
-  template<typename RAType>
-  size_t& operator()(RAType* ra) const;
-};
+  //! Construct the LeafSizeRAWrapper by delegating to the RAWrapper
+  //! constructor.
+  LeafSizeRAWrapper(const bool singleMode, const bool naive) :
+      RAWrapper<TreeType>(singleMode, naive)
+  {
+    // Nothing else to do.
+  }
 
-/**
- * Exposes the FirstLeafExact() method of the given RAType.
- */
-class FirstLeafExactVisitor : public boost::static_visitor<bool&>
-{
- public:
-  template<typename RAType>
-  bool& operator()(RAType* ra) const;
-};
+  //! Delete the LeafSizeRAWrapper.
+  virtual ~LeafSizeRAWrapper() { }
 
-/**
- * Exposes the SampleAtLeaves() method of the given RAType.
- */
-class SampleAtLeavesVisitor : public boost::static_visitor<bool&>
-{
- public:
-  //! Return SampleAtLeaves (whether or not sampling is done at leaves).
-  template<typename RAType>
-  bool& operator()(RAType *) const;
-};
+  //! Return a copy of the LeafSizeRAWrapper.
+  virtual LeafSizeRAWrapper* Clone() const
+  {
+    return new LeafSizeRAWrapper(*this);
+  }
 
-/**
- * Exposes the Alpha() method of the given RAType.
- */
-class AlphaVisitor : public boost::static_visitor<double&>
-{
- public:
-  //! Return Alpha parameter.
-  template<typename RAType>
-  double& operator()(RAType* ra) const;
-};
+  //! Train a model with the given parameters.  This overload uses leafSize.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize);
 
-/**
- * Exposes the Tau() method of the given RAType.
- */
-class TauVisitor : public boost::static_visitor<double&>
-{
- public:
-  //! Get a reference to the Tau parameter.
-  template<typename RAType>
-  double& operator()(RAType* ra) const;
-};
+  //! Perform bichromatic search (e.g. search with a separate query set).  This
+  //! overload takes the leaf size into account to build the query tree.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize);
 
-/**
- * Exposes the SingleMode() method of the given RAType.
- */
-class SingleModeVisitor : public boost::static_visitor<bool&>
-{
- public:
-  //! Get a reference to the SingleMode parameter of the given RASearch object.
-  template<typename RAType>
-  bool& operator()(RAType* ra) const;
-};
+  //! Serialize the RASearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(ra));
+  }
 
-/**
- * Exposes the referenceSet of the given RAType.
- */
-class ReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
-{
- public:
-  //! Return the reference set.
-  template<typename RAType>
-  const arma::mat& operator()(RAType* ra) const;
-};
-
-/**
- * DeleteVisitor deletes the give RAType Instance.
- */
-class DeleteVisitor : public boost::static_visitor<void>
-{
- public:
-  //! Delete the RAType Object.
-  template<typename RAType> void operator()(RAType* ra) const;
-};
-
-/**
- * NaiveVisitor exposes the Naive() method of the given RAType.
- */
-class NaiveVisitor : public boost::static_visitor<bool&>
-{
- public:
-  /**
-   * Get a reference to the naive parameter of the given RASearch object.
-   */
-  template<typename RAType>
-  bool& operator()(RAType* ra) const;
+ protected:
+  using RAWrapper<TreeType>::ra;
 };
 
 /**
@@ -264,10 +254,7 @@ class NaiveVisitor : public boost::static_visitor<bool&>
  * away the TreeType parameter and allowing it to be specified at runtime in
  * this class.  This class is written for the sake of the 'allkrann' program,
  * but is not necessarily restricted to that use.
- *
- * @param SortPolicy Sorting policy for neighbor searching (see RASearch).
  */
-template<typename SortPolicy>
 class RAModel
 {
  public:
@@ -301,16 +288,7 @@ class RAModel
   arma::mat q;
 
   //! The rank-approximate model.
-  boost::variant<RAType<SortPolicy, tree::KDTree>*,
-                 RAType<SortPolicy, tree::StandardCoverTree>*,
-                 RAType<SortPolicy, tree::RTree>*,
-                 RAType<SortPolicy, tree::RStarTree>*,
-                 RAType<SortPolicy, tree::XTree>*,
-                 RAType<SortPolicy, tree::HilbertRTree>*,
-                 RAType<SortPolicy, tree::RPlusTree>*,
-                 RAType<SortPolicy, tree::RPlusPlusTree>*,
-                 RAType<SortPolicy, tree::UBTree>*,
-                 RAType<SortPolicy, tree::Octree>*> raSearch;
+  RAWrapperBase* raSearch;
 
  public:
   /**
@@ -355,58 +333,58 @@ class RAModel
   void serialize(Archive& ar, const uint32_t /* version */);
 
   //! Expose the dataset.
-  const arma::mat& Dataset() const;
+  const arma::mat& Dataset() const { return raSearch->Dataset(); }
 
   //! Get whether or not single-tree search is being used.
-  bool SingleMode() const;
+  bool SingleMode() const { return raSearch->SingleMode(); }
   //! Modify whether or not single-tree search is being used.
-  bool& SingleMode();
+  bool& SingleMode() { return raSearch->SingleMode(); }
 
   //! Get whether or not naive search is being used.
-  bool Naive() const;
+  bool Naive() const { return raSearch->Naive(); }
   //! Modify whether or not naive search is being used.
-  bool& Naive();
+  bool& Naive() { return raSearch->Naive(); }
 
   //! Get the rank-approximation in percentile of the data.
-  double Tau() const;
+  double Tau() const { return raSearch->Tau(); }
   //! Modify the rank-approximation in percentile of the data.
-  double& Tau();
+  double& Tau() { return raSearch->Tau(); }
 
   //! Get the desired success probability.
-  double Alpha() const;
+  double Alpha() const { return raSearch->Alpha(); }
   //! Modify the desired success probability.
-  double& Alpha();
+  double& Alpha() { return raSearch->Alpha(); }
 
   //! Get whether or not sampling is done at the leaves.
-  bool SampleAtLeaves() const;
+  bool SampleAtLeaves() const { return raSearch->SampleAtLeaves(); }
   //! Modify whether or not sampling is done at the leaves.
-  bool& SampleAtLeaves();
+  bool& SampleAtLeaves() { return raSearch->SampleAtLeaves(); }
 
   //! Get whether or not we traverse to the first leaf without approximation.
-  bool FirstLeafExact() const;
+  bool FirstLeafExact() const { return raSearch->FirstLeafExact(); }
   //! Modify whether or not we traverse to the first leaf without approximation.
-  bool& FirstLeafExact();
+  bool& FirstLeafExact() { return raSearch->FirstLeafExact(); }
 
   //! Get the limit on the size of a node that can be approximated.
-  size_t SingleSampleLimit() const;
+  size_t SingleSampleLimit() const { return raSearch->SingleSampleLimit(); }
   //! Modify the limit on the size of a node that can be approximation.
-  size_t& SingleSampleLimit();
+  size_t& SingleSampleLimit() { return raSearch->SingleSampleLimit(); }
 
   //! Get the leaf size (only relevant when the kd-tree is used).
-  size_t LeafSize() const;
+  size_t LeafSize() const { return leafSize; }
   //! Modify the leaf size (only relevant when the kd-tree is used).
-  size_t& LeafSize();
+  size_t& LeafSize() { return leafSize; }
 
   //! Get the type of tree being used.
-  TreeTypes TreeType() const;
+  TreeTypes TreeType() const { return treeType; }
   //! Modify the type of tree being used.
-  TreeTypes& TreeType();
+  TreeTypes& TreeType() { return treeType; }
 
   //! Get whether or not a random basis is being used.
-  bool RandomBasis() const;
+  bool RandomBasis() const { return randomBasis; }
   //! Modify whether or not a random basis is being used.  Be sure to rebuild
   //! the model using BuildModel().
-  bool& RandomBasis();
+  bool& RandomBasis() { return randomBasis; }
 
   //! Build the reference tree.
   void BuildModel(arma::mat&& referenceSet,
diff --git a/src/mlpack/methods/rann/ra_model_impl.hpp b/src/mlpack/methods/rann/ra_model_impl.hpp
index 3b27bfa2d6..6955bd9f46 100644
--- a/src/mlpack/methods/rann/ra_model_impl.hpp
+++ b/src/mlpack/methods/rann/ra_model_impl.hpp
@@ -19,78 +19,87 @@
 namespace mlpack {
 namespace neighbor {
 
-//! Monochromatic search for the given RAType instance.
-template<typename RAType>
-void MonoSearchVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->Search(k, neighbors, distances);
-  throw std::runtime_error("no rank-approximate model initialized");
-}
-
-//! Save the parameters for the rank-approximate search.
-template<typename SortPolicy>
-BiSearchVisitor<SortPolicy>::BiSearchVisitor(const arma::mat& querySet,
-                                 const size_t k,
-                                 arma::Mat<size_t>& neighbors,
-                                 arma::mat& distances,
-                                 const size_t leafSize) :
-    querySet(querySet),
-    k(k),
-    neighbors(neighbors),
-    distances(distances),
-    leafSize(leafSize)
-{};
-
-//! Default Bichromatic search on the given RAType instance.
-template<typename SortPolicy>
 template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
+void RAWrapper<TreeType>::Train(arma::mat&& referenceSet,
+                                const size_t /* leafSize */)
 {
-  if (ra)
-    return ra->Search(querySet, k, neighbors, distances);
-  throw std::runtime_error("no rank-approximate model initialized");
+  ra.Train(std::move(referenceSet));
 }
 
-//! Bichromatic search on the given RAType specialized for KDTrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void RAWrapper<TreeType>::Search(arma::mat&& querySet,
+                                 const size_t k,
+                                 arma::Mat<size_t>& neighbors,
+                                 arma::mat& distances,
+                                 const size_t /* leafSize */)
 {
-  if (ra)
-    return SearchLeaf(ra);
-  throw std::runtime_error("no rank-approximate search model initialized");
+  ra.Search(querySet, k, neighbors, distances);
 }
 
-//! Bichromatic search on the given RAType specialized for Octrees.
-template<typename SortPolicy>
-void BiSearchVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void RAWrapper<TreeType>::Search(const size_t k,
+                                 arma::Mat<size_t>& neighbors,
+                                 arma::mat& distances)
 {
-  if (ra)
-    return SearchLeaf(ra);
-  throw std::runtime_error("no rank-approximate search model initialized");
+  ra.Search(k, neighbors, distances);
 }
 
-//! Bichromatic search on the given RAType considering the leafSize.
-template<typename SortPolicy>
-template<typename RAType>
-void BiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void LeafSizeRAWrapper<TreeType>::Train(arma::mat&& referenceSet,
+                                        const size_t leafSize)
 {
-  if (!ra->Naive() && !ra->SingleMode())
+  // Build tree, if necessary.
+  if (ra.Naive())
   {
-    // Build a second tree and search
+    ra.Train(std::move(referenceSet));
+  }
+  else
+  {
+    std::vector<size_t> oldFromNewReferences;
+    typename decltype(ra)::Tree* tree =
+        new typename decltype(ra)::Tree(std::move(referenceSet),
+                                        oldFromNewReferences,
+                                        leafSize);
+    ra.Train(tree);
+
+    // Give the model ownership of the tree and the mappings.
+    ra.treeOwner = true;
+    ra.oldFromNewReferences = std::move(oldFromNewReferences);
+  }
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void LeafSizeRAWrapper<TreeType>::Search(arma::mat&& querySet,
+                                         const size_t k,
+                                         arma::Mat<size_t>& neighbors,
+                                         arma::mat& distances,
+                                         const size_t leafSize)
+{
+  if (!ra.Naive() && !ra.SingleMode())
+  {
+    // Build a second tree and search, taking the leaf size into account.
     Timer::Start("tree_building");
     Log::Info << "Building query tree...."<< std::endl;
     std::vector<size_t> oldFromNewQueries;
-    typename RAType::Tree queryTree(std::move(querySet), oldFromNewQueries,
-        leafSize);
-    Log::Info << "Tree Built." << std::endl;
+    typename decltype(ra)::Tree queryTree(std::move(querySet),
+                                          oldFromNewQueries,
+                                          leafSize);
+    Log::Info << "Tree built." << std::endl;
     Timer::Stop("tree_building");
 
     arma::Mat<size_t> neighborsOut;
     arma::mat distancesOut;
-    ra->Search(&queryTree, k, neighborsOut, distancesOut);
+    ra.Search(&queryTree, k, neighborsOut, distancesOut);
 
     // Unmap the query points.
     distances.set_size(distancesOut.n_rows, distancesOut.n_cols);
@@ -104,236 +113,12 @@ void BiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
   else
   {
     // Search without building a second tree.
-    ra->Search(querySet, k, neighbors, distances);
+    ra.Search(querySet, k, neighbors, distances);
   }
 }
 
-//! Save parameters for the Train.
-template<typename SortPolicy>
-TrainVisitor<SortPolicy>::TrainVisitor(arma::mat&& referenceSet,
-                                       const size_t leafSize) :
-    referenceSet(std::move(referenceSet)),
-    leafSize(leafSize)
-{};
-
-//! Default Train on the given RAType instance.
-template<typename SortPolicy>
-template<template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<TreeType>* ra) const
-{
-  if (ra)
-    return ra->Train(std::move(referenceSet));
-  throw std::runtime_error("no rank-approximate search model initialized");
-}
-
-//! Train on the given RAType specialized for KDTrees.
-template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::KDTree>* ra) const
-{
-  if (ra)
-    return TrainLeaf(ra);
-  throw std::runtime_error("no rank-approximate search model initialized");
-}
-
-//! Train on the given RAType specialized for Octrees.
-template<typename SortPolicy>
-void TrainVisitor<SortPolicy>::operator()(RATypeT<tree::Octree>* ra) const
-{
-  if (ra)
-    return TrainLeaf(ra);
-  throw std::runtime_error("no rank-approximate search model is initialized");
-}
-
-//! Train on the given RAType considering the leafSize.
-template<typename SortPolicy>
-template<typename RAType>
-void TrainVisitor<SortPolicy>::TrainLeaf(RAType* ra) const
-{
-  // Build tree, if necessary
-  if (ra->Naive())
-  {
-    ra->Train(std::move(referenceSet));
-  }
-  else
-  {
-    std::vector<size_t> oldFromNewReferences;
-    typename RAType::Tree* tree =
-        new typename RAType::Tree(std::move(referenceSet), oldFromNewReferences,
-        leafSize);
-    ra->Train(tree);
-
-    // Give the model ownership of the tree and the mappings.
-    ra->treeOwner = true;
-    ra->oldFromNewReferences = std::move(oldFromNewReferences);
-  }
-}
-
-//! Exposes the SingleSampleLimit() method of the given RAType.
-template<typename RAType>
-size_t& SingleSampleLimitVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->SingleSampleLimit();
-  throw std::runtime_error("no rank-approximate search model is initialized");
-}
-
-//! Exposes the FirstLeafExact() method of the given RAType.
-template<typename RAType>
-bool& FirstLeafExactVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->FirstLeafExact();
-  throw std::runtime_error("no rank-approximate search model is initialized");
-}
-
-//! Exposes the SampleAtLeaves() method of the given RAType.
-template<typename RAType>
-bool& SampleAtLeavesVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->SampleAtLeaves();
-  throw std::runtime_error("no rank-approximate search model is initialized");
-}
-
-//! Exposes the Alpha() method of the given RAType instance.
-template<typename RAType>
-double& AlphaVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->Alpha();
-  throw std::runtime_error("no rank-approximate model is initialized");
-}
-
-//! Exposes the Tau() method of the given RAType instance.
-template<typename RAType>
-double& TauVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->Tau();
-  throw std::runtime_error("no rank-approximate model is initialized");
-}
-
-//! Exposes the SingleMode() method of the given RAType.
-template<typename RAType>
-bool& SingleModeVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->SingleMode();
-  throw std::runtime_error("no rank-approximate model is initialized");
-}
-
-//! Exposes the referenceSet of the given RAType.
-template<typename RAType>
-const arma::mat& ReferenceSetVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->ReferenceSet();
-  throw std::runtime_error("no rank-approximate model is initialized");
-}
-
-//! Exposes the Naive() method of the given RAType instance.
-template<typename RAType>
-bool& NaiveVisitor::operator()(RAType* ra) const
-{
-  if (ra)
-    return ra->Naive();
-  throw std::runtime_error("no rank-approximate search model is initialized");
-}
-
-//! For cleaning memory
-template<typename RSType>
-void DeleteVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    delete rs;
-}
-
-template<typename SortPolicy>
-RAModel<SortPolicy>::RAModel(const TreeTypes treeType, const bool randomBasis) :
-    treeType(treeType),
-    leafSize(20),
-    randomBasis(randomBasis)
-{
-  // Nothing to do.
-}
-
-// Copy constructor.
-template<typename SortPolicy>
-RAModel<SortPolicy>::RAModel(const RAModel& other) :
-    treeType(other.treeType),
-    leafSize(other.leafSize),
-    randomBasis(other.randomBasis),
-    q(other.q),
-    raSearch(other.raSearch)
-{
-  // Nothing to do.
-}
-
-// Move constructor.
-template<typename SortPolicy>
-RAModel<SortPolicy>::RAModel(RAModel&& other) :
-    treeType(other.treeType),
-    leafSize(other.leafSize),
-    randomBasis(other.randomBasis),
-    q(std::move(other.q)),
-    raSearch(std::move(other.raSearch))
-{
-  // Clear other model.
-  other.treeType = TreeTypes::KD_TREE;
-  other.leafSize = 20;
-  other.randomBasis = false;
-  other.raSearch = decltype(other.raSearch)();
-}
-
-// Copy operator.
-template<typename SortPolicy>
-RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(const RAModel& other)
-{
-  // Clear current model.
-  boost::apply_visitor(DeleteVisitor(), raSearch);
-
-  treeType = other.treeType;
-  leafSize = other.leafSize;
-  randomBasis = other.randomBasis;
-  q = other.q;
-  raSearch = other.raSearch;
-
-  return *this;
-}
-
-template<typename SortPolicy>
-RAModel<SortPolicy>& RAModel<SortPolicy>::operator=(RAModel&& other)
-{
-  boost::apply_visitor(DeleteVisitor(), raSearch);
-
-  treeType = other.treeType;
-  leafSize = other.leafSize;
-  randomBasis = other.randomBasis;
-  q = std::move(other.q);
-  raSearch = std::move(other.raSearch);
-
-  // Reset other model.
-  other.treeType = TreeTypes::KD_TREE;
-  other.leafSize = 20;
-  other.randomBasis = false;
-  other.raSearch = decltype(other.raSearch)();
-
-  return *this;
-}
-
-// Clean memory, if necessary
-template<typename SortPolicy>
-RAModel<SortPolicy>::~RAModel()
-{
-  boost::apply_visitor(DeleteVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
 template<typename Archive>
-void RAModel<SortPolicy>::serialize(Archive& ar,
-    const uint32_t /* version */)
+void RAModel::serialize(Archive& ar, const uint32_t /* version */)
 {
   ar(CEREAL_NVP(treeType));
   ar(CEREAL_NVP(randomBasis));
@@ -342,281 +127,82 @@ void RAModel<SortPolicy>::serialize(Archive& ar,
   // This should never happen, but just in case, be clean with memory.
   if (cereal::is_loading<Archive>())
   {
-    boost::apply_visitor(DeleteVisitor(), raSearch);
-  }
-
-  // We only need to serialize one of the kRANN objects.
-  ar(CEREAL_VARIANT_POINTER(raSearch));
-}
-
-template<typename SortPolicy>
-const arma::mat& RAModel<SortPolicy>::Dataset() const
-{
-  return boost::apply_visitor(ReferenceSetVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool RAModel<SortPolicy>::Naive() const
-{
-  return boost::apply_visitor(NaiveVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool& RAModel<SortPolicy>::Naive()
-{
-  return boost::apply_visitor(NaiveVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool RAModel<SortPolicy>::SingleMode() const
-{
-  return boost::apply_visitor(SingleModeVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool& RAModel<SortPolicy>::SingleMode()
-{
-  return boost::apply_visitor(SingleModeVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-double RAModel<SortPolicy>::Tau() const
-{
-  return boost::apply_visitor(TauVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-double& RAModel<SortPolicy>::Tau()
-{
-  return boost::apply_visitor(TauVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-double RAModel<SortPolicy>::Alpha() const
-{
-  return boost::apply_visitor(AlphaVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-double& RAModel<SortPolicy>::Alpha()
-{
-  return boost::apply_visitor(AlphaVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool RAModel<SortPolicy>::SampleAtLeaves() const
-{
-  return boost::apply_visitor(SampleAtLeavesVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool& RAModel<SortPolicy>::SampleAtLeaves()
-{
-  return boost::apply_visitor(SampleAtLeavesVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool RAModel<SortPolicy>::FirstLeafExact() const
-{
-  return boost::apply_visitor(FirstLeafExactVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-bool& RAModel<SortPolicy>::FirstLeafExact()
-{
-  return boost::apply_visitor(FirstLeafExactVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-size_t RAModel<SortPolicy>::SingleSampleLimit() const
-{
-  return boost::apply_visitor(SingleSampleLimitVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-size_t& RAModel<SortPolicy>::SingleSampleLimit()
-{
-  return boost::apply_visitor(SingleSampleLimitVisitor(), raSearch);
-}
-
-template<typename SortPolicy>
-size_t RAModel<SortPolicy>::LeafSize() const
-{
-  return leafSize;
-}
-
-template<typename SortPolicy>
-size_t& RAModel<SortPolicy>::LeafSize()
-{
-  return leafSize;
-}
-
-template<typename SortPolicy>
-typename RAModel<SortPolicy>::TreeTypes RAModel<SortPolicy>::TreeType() const
-{
-  return treeType;
-}
-
-template<typename SortPolicy>
-typename RAModel<SortPolicy>::TreeTypes& RAModel<SortPolicy>::TreeType()
-{
-  return treeType;
-}
-
-template<typename SortPolicy>
-bool RAModel<SortPolicy>::RandomBasis() const
-{
-  return randomBasis;
-}
-
-template<typename SortPolicy>
-bool& RAModel<SortPolicy>::RandomBasis()
-{
-  return randomBasis;
-}
-
-template<typename SortPolicy>
-void RAModel<SortPolicy>::BuildModel(arma::mat&& referenceSet,
-                                     const size_t leafSize,
-                                     const bool naive,
-                                     const bool singleMode)
-{
-  // Initialize random basis, if necessary.
-  if (randomBasis)
-  {
-    Log::Info << "Creating random basis..." << std::endl;
-    math::RandomBasis(q, referenceSet.n_rows);
-  }
-
-  // Clean memory, if necessary.
-  boost::apply_visitor(DeleteVisitor(), raSearch);
-
-  this->leafSize = leafSize;
-
-  if (randomBasis)
-    referenceSet = q * referenceSet;
-
-  if (!naive)
-  {
-    Timer::Start("tree_building");
-    Log::Info << "Building reference tree..." << std::endl;
+    delete raSearch;
   }
 
+  // Avoid polymorphic serialization by explicitly serializing the correct type.
   switch (treeType)
   {
     case KD_TREE:
-      raSearch = new RAType<SortPolicy, tree::KDTree>(naive, singleMode);
-      break;
+      {
+        LeafSizeRAWrapper<tree::KDTree>& typedSearch =
+            dynamic_cast<LeafSizeRAWrapper<tree::KDTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case COVER_TREE:
-      raSearch = new RAType<SortPolicy, tree::StandardCoverTree>(naive,
-          singleMode);
-      break;
+      {
+        RAWrapper<tree::StandardCoverTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::StandardCoverTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case R_TREE:
-      raSearch = new RAType<SortPolicy, tree::RTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::RTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::RTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case R_STAR_TREE:
-      raSearch = new RAType<SortPolicy, tree::RStarTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::RStarTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::RStarTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case X_TREE:
-      raSearch = new RAType<SortPolicy, tree::XTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::XTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::XTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case HILBERT_R_TREE:
-      raSearch = new RAType<SortPolicy, tree::HilbertRTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::HilbertRTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::HilbertRTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case R_PLUS_TREE:
-      raSearch = new RAType<SortPolicy, tree::RPlusTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::RPlusTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::RPlusTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case R_PLUS_PLUS_TREE:
-      raSearch = new RAType<SortPolicy, tree::RPlusPlusTree>(naive,
-          singleMode);
-      break;
+      {
+        RAWrapper<tree::RPlusPlusTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::RPlusPlusTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case UB_TREE:
-      raSearch = new RAType<SortPolicy, tree::UBTree>(naive, singleMode);
-      break;
+      {
+        RAWrapper<tree::UBTree>& typedSearch =
+            dynamic_cast<RAWrapper<tree::UBTree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
     case OCTREE:
-      raSearch = new RAType<SortPolicy, tree::Octree>(naive, singleMode);
-      break;
-  }
-
-  TrainVisitor<SortPolicy> tn(std::move(referenceSet), leafSize);
-  boost::apply_visitor(tn, raSearch);
-
-  if (!naive)
-  {
-    Timer::Stop("tree_building");
-    Log::Info << "Tree built." << std::endl;
-  }
-}
-
-template<typename SortPolicy>
-void RAModel<SortPolicy>::Search(arma::mat&& querySet,
-                                 const size_t k,
-                                 arma::Mat<size_t>& neighbors,
-                                 arma::mat& distances)
-{
-  // Apply the random basis if necessary.
-  if (randomBasis)
-    querySet = q * querySet;
-
-  Log::Info << "Searching for " << k << " approximate nearest neighbors with ";
-  if (!Naive() && !SingleMode())
-    Log::Info << "dual-tree rank-approximate " << TreeName() << " search...";
-  else if (!Naive())
-    Log::Info << "single-tree rank-approximate " << TreeName() << " search...";
-  else
-    Log::Info << "brute-force (naive) rank-approximate search...";
-  Log::Info << std::endl;
-
-  BiSearchVisitor<SortPolicy> search(querySet, k, neighbors, distances,
-      leafSize);
-  boost::apply_visitor(search, raSearch);
-}
-
-template<typename SortPolicy>
-void RAModel<SortPolicy>::Search(const size_t k,
-                                 arma::Mat<size_t>& neighbors,
-                                 arma::mat& distances)
-{
-  Log::Info << "Searching for " << k << " approximate nearest neighbors with ";
-  if (!Naive() && !SingleMode())
-    Log::Info << "dual-tree rank-approximate " << TreeName() << " search...";
-  else if (!Naive())
-    Log::Info << "single-tree rank-approximate " << TreeName() << " search...";
-  else
-    Log::Info << "brute-force (naive) rank-approximate search...";
-  Log::Info << std::endl;
-
-  MonoSearchVisitor search(k, neighbors, distances);
-  boost::apply_visitor(search, raSearch);
-}
-
-template<typename SortPolicy>
-std::string RAModel<SortPolicy>::TreeName() const
-{
-  switch (treeType)
-  {
-    case KD_TREE:
-      return "kd-tree";
-    case COVER_TREE:
-      return "cover tree";
-    case R_TREE:
-      return "R tree";
-    case R_STAR_TREE:
-      return "R* tree";
-    case X_TREE:
-      return "X tree";
-    case HILBERT_R_TREE:
-      return "Hilbert R tree";
-    case R_PLUS_TREE:
-      return "R+ tree";
-    case R_PLUS_PLUS_TREE:
-      return "R++ tree";
-    case UB_TREE:
-      return "UB tree";
-    case OCTREE:
-      return "octree";
-    default:
-      return "unknown tree";
+      {
+        LeafSizeRAWrapper<tree::Octree>& typedSearch =
+            dynamic_cast<LeafSizeRAWrapper<tree::Octree>&>(*raSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
   }
 }
 
diff --git a/src/mlpack/methods/rann/ra_search.hpp b/src/mlpack/methods/rann/ra_search.hpp
index da3f61c48d..634260c213 100644
--- a/src/mlpack/methods/rann/ra_search.hpp
+++ b/src/mlpack/methods/rann/ra_search.hpp
@@ -39,8 +39,10 @@ namespace mlpack {
 namespace neighbor {
 
 // Forward declaration.
-template<typename SortPolicy>
-class TrainVisitor;
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+class LeafSizeRAWrapper;
 
 /**
  * The RASearch class: This class provides a generic manner to perform
@@ -394,8 +396,7 @@ class RASearch
   MetricType metric;
 
   //! For access to mappings when building models.
-  template<typename SortPol>
-  friend class TrainVisitor;
+  friend class LeafSizeRAWrapper<TreeType>;
 }; // class RASearch
 
 } // namespace neighbor
diff --git a/src/mlpack/tests/krann_search_test.cpp b/src/mlpack/tests/krann_search_test.cpp
index 4efa022776..411e08a025 100644
--- a/src/mlpack/tests/krann_search_test.cpp
+++ b/src/mlpack/tests/krann_search_test.cpp
@@ -620,34 +620,32 @@ TEST_CASE("RAModelTest", "[KRANNTest]")
 {
   // Ensure that we can build an RAModel<NearestNeighborSearch> and get correct
   // results.
-  typedef RAModel<NearestNeighborSort> KNNModel;
-
   arma::mat queryData, referenceData;
   data::Load("rann_test_r_3_900.csv", referenceData, true);
   data::Load("rann_test_q_3_100.csv", queryData, true);
 
   // Build all the possible models.
-  KNNModel models[20];
-  models[0] = KNNModel(KNNModel::TreeTypes::KD_TREE, false);
-  models[1] = KNNModel(KNNModel::TreeTypes::KD_TREE, true);
-  models[2] = KNNModel(KNNModel::TreeTypes::COVER_TREE, false);
-  models[3] = KNNModel(KNNModel::TreeTypes::COVER_TREE, true);
-  models[4] = KNNModel(KNNModel::TreeTypes::R_TREE, false);
-  models[5] = KNNModel(KNNModel::TreeTypes::R_TREE, true);
-  models[6] = KNNModel(KNNModel::TreeTypes::R_STAR_TREE, false);
-  models[7] = KNNModel(KNNModel::TreeTypes::R_STAR_TREE, true);
-  models[8] = KNNModel(KNNModel::TreeTypes::X_TREE, false);
-  models[9] = KNNModel(KNNModel::TreeTypes::X_TREE, true);
-  models[10] = KNNModel(KNNModel::TreeTypes::HILBERT_R_TREE, false);
-  models[11] = KNNModel(KNNModel::TreeTypes::HILBERT_R_TREE, true);
-  models[12] = KNNModel(KNNModel::TreeTypes::R_PLUS_TREE, false);
-  models[13] = KNNModel(KNNModel::TreeTypes::R_PLUS_TREE, true);
-  models[14] = KNNModel(KNNModel::TreeTypes::R_PLUS_PLUS_TREE, false);
-  models[15] = KNNModel(KNNModel::TreeTypes::R_PLUS_PLUS_TREE, true);
-  models[16] = KNNModel(KNNModel::TreeTypes::UB_TREE, false);
-  models[17] = KNNModel(KNNModel::TreeTypes::UB_TREE, true);
-  models[18] = KNNModel(KNNModel::TreeTypes::OCTREE, false);
-  models[19] = KNNModel(KNNModel::TreeTypes::OCTREE, true);
+  RAModel models[20];
+  models[0] = RAModel(RAModel::TreeTypes::KD_TREE, false);
+  models[1] = RAModel(RAModel::TreeTypes::KD_TREE, true);
+  models[2] = RAModel(RAModel::TreeTypes::COVER_TREE, false);
+  models[3] = RAModel(RAModel::TreeTypes::COVER_TREE, true);
+  models[4] = RAModel(RAModel::TreeTypes::R_TREE, false);
+  models[5] = RAModel(RAModel::TreeTypes::R_TREE, true);
+  models[6] = RAModel(RAModel::TreeTypes::R_STAR_TREE, false);
+  models[7] = RAModel(RAModel::TreeTypes::R_STAR_TREE, true);
+  models[8] = RAModel(RAModel::TreeTypes::X_TREE, false);
+  models[9] = RAModel(RAModel::TreeTypes::X_TREE, true);
+  models[10] = RAModel(RAModel::TreeTypes::HILBERT_R_TREE, false);
+  models[11] = RAModel(RAModel::TreeTypes::HILBERT_R_TREE, true);
+  models[12] = RAModel(RAModel::TreeTypes::R_PLUS_TREE, false);
+  models[13] = RAModel(RAModel::TreeTypes::R_PLUS_TREE, true);
+  models[14] = RAModel(RAModel::TreeTypes::R_PLUS_PLUS_TREE, false);
+  models[15] = RAModel(RAModel::TreeTypes::R_PLUS_PLUS_TREE, true);
+  models[16] = RAModel(RAModel::TreeTypes::UB_TREE, false);
+  models[17] = RAModel(RAModel::TreeTypes::UB_TREE, true);
+  models[18] = RAModel(RAModel::TreeTypes::OCTREE, false);
+  models[19] = RAModel(RAModel::TreeTypes::OCTREE, true);
 
   arma::Mat<size_t> qrRanks;
   data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
diff --git a/src/mlpack/tests/main_tests/krann_test.cpp b/src/mlpack/tests/main_tests/krann_test.cpp
index b61044f104..57cb0905d6 100644
--- a/src/mlpack/tests/main_tests/krann_test.cpp
+++ b/src/mlpack/tests/main_tests/krann_test.cpp
@@ -192,7 +192,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNRefModelTest",
 
   // Input pre-trained model.
   SetInputParam("input_model",
-      std::move(IO::GetParam<RANNModel*>("output_model")));
+      std::move(IO::GetParam<RAModel*>("output_model")));
 
   Log::Fatal.ignoreInput = true;
   REQUIRE_THROWS_AS(mlpackMain(), std::runtime_error);
@@ -285,10 +285,10 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNModelReuseTest",
 
   arma::Mat<size_t> neighbors;
   arma::mat distances;
-  RANNModel* output_model;
+  RAModel* output_model;
   neighbors = std::move(IO::GetParam<arma::Mat<size_t>>("neighbors"));
   distances = std::move(IO::GetParam<arma::mat>("distances"));
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -324,8 +324,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentLeafSizes",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -341,7 +341,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentLeafSizes",
   // Check that initial output matrices and the output matrices using
   // saved model are equal.
   CHECK(output_model->LeafSize() == (int) 1);
-  CHECK(IO::GetParam<RANNModel*>("output_model")->LeafSize() == (int) 10);
+  CHECK(IO::GetParam<RAModel*>("output_model")->LeafSize() == (int) 10);
   delete output_model;
 }
 
@@ -361,8 +361,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentTau",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset the passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -378,7 +378,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentTau",
   // Check that initial output matrices and the output matrices using
   // saved model are equal
   CHECK(output_model->Tau() == (double) 5);
-  CHECK(IO::GetParam<RANNModel*>("output_model")->Tau() ==
+  CHECK(IO::GetParam<RAModel*>("output_model")->Tau() ==
       (double) 10);
   delete output_model;
 }
@@ -399,8 +399,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentAlpha",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset the passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -416,7 +416,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentAlpha",
   // Check that initial output matrices and the output matrices using
   // saved model are equal
   CHECK(output_model->Alpha() == (double) 0.95);
-  CHECK(IO::GetParam<RANNModel*>("output_model")->Alpha() ==
+  CHECK(IO::GetParam<RAModel*>("output_model")->Alpha() ==
       (double) 0.80);
   delete output_model;
 }
@@ -437,8 +437,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentTreeType",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset the passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -455,7 +455,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentTreeType",
   // saved model are equal
   const bool check = output_model->TreeType() == 0;
   CHECK(check == true);
-  CHECK(IO::GetParam<RANNModel*>("output_model")->TreeType() ==
+  CHECK(IO::GetParam<RAModel*>("output_model")->TreeType() ==
       8);
   delete output_model;
 }
@@ -476,8 +476,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentSingleSampleLimit",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -492,7 +492,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentSingleSampleLimit",
 
   // Check that initial output matrices and the output matrices using
   // saved model are equal.
-  CHECK(IO::GetParam<RANNModel*>("output_model")->SingleSampleLimit() ==
+  CHECK(IO::GetParam<RAModel*>("output_model")->SingleSampleLimit() ==
       (int) 15);
   CHECK(output_model->SingleSampleLimit() == (int) 20);
   delete output_model;
@@ -514,8 +514,8 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentSampleAtLeaves",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  RANNModel* output_model;
-  output_model = std::move(IO::GetParam<RANNModel*>("output_model"));
+  RAModel* output_model;
+  output_model = std::move(IO::GetParam<RAModel*>("output_model"));
 
   // Reset passed parameters.
   IO::GetSingleton().Parameters()["reference"].wasPassed = false;
@@ -530,7 +530,7 @@ TEST_CASE_METHOD(KRANNTestFixture, "KRANNDifferentSampleAtLeaves",
 
   // Check that initial output matrices and the output matrices using
   // saved model are equal.
-  CHECK(IO::GetParam<RANNModel*>("output_model")->SampleAtLeaves() ==
+  CHECK(IO::GetParam<RAModel*>("output_model")->SampleAtLeaves() ==
       (bool) true);
   CHECK(output_model->SampleAtLeaves() == (bool) false);
   delete output_model;

From aeaf7528bead4d352c0bb9ca5aa9f99b845ffcbd Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 9 Jan 2021 21:49:02 -0500
Subject: [PATCH 053/253] Remove boost::visitor header.

---
 src/mlpack/methods/rann/ra_model.hpp | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/mlpack/methods/rann/ra_model.hpp b/src/mlpack/methods/rann/ra_model.hpp
index afe42bf3da..8ed91a9c9b 100644
--- a/src/mlpack/methods/rann/ra_model.hpp
+++ b/src/mlpack/methods/rann/ra_model.hpp
@@ -18,7 +18,6 @@
 #include <mlpack/core/tree/cover_tree.hpp>
 #include <mlpack/core/tree/rectangle_tree.hpp>
 #include <mlpack/core/tree/octree.hpp>
-#include <boost/variant.hpp>
 #include "ra_search.hpp"
 
 namespace mlpack {

From dcac51194eae04b31ce5c6b7b5adc3204ee40933 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 9 Jan 2021 22:10:04 -0500
Subject: [PATCH 054/253] Partial work on RSModel.

---
 src/mlpack/methods/range_search/rs_model.hpp  | 347 +++++++++---------
 .../methods/range_search/rs_model_impl.hpp    | 257 ++++---------
 2 files changed, 238 insertions(+), 366 deletions(-)

diff --git a/src/mlpack/methods/range_search/rs_model.hpp b/src/mlpack/methods/range_search/rs_model.hpp
index ab71f20a21..bf1f6b98f4 100644
--- a/src/mlpack/methods/range_search/rs_model.hpp
+++ b/src/mlpack/methods/range_search/rs_model.hpp
@@ -27,189 +27,183 @@ namespace mlpack {
 namespace range {
 
 /**
- * Alias template for Range Search.
+ * RSWrapperBase is a base wrapper class for holding all RangeSearch types
+ * supported by RSModel.  All RangeSearch type wrappers inherit from this class,
+ * allowing a simple interface via inheritance for all the different types we
+ * want to support.
+ */
+class RSWrapperBase
+{
+ public:
+  //! Create the RSWrapperBase object.  The base class does not hold anything,
+  //! so this constructor does nothing.
+  RSWrapperBase() { }
+
+  //! Create a new RSWrapperBase that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual RSWrapperBase* Clone() const = 0;
+
+  //! Destruct the RSWrapperBase (nothing to do).
+  virtual ~RSWrapperBase() { }
+
+  //! Get the dataset.
+  const arma::mat& Dataset() const = 0;
+
+  //! Get whether single-tree search is being used.
+  bool SingleMode() const = 0;
+  //! Modify whether single-tree search is being used.
+  bool& SingleMode() = 0;
+
+  //! Get whether naive search is being used.
+  bool Naive() const = 0;
+  //! Modify whether naive search is being used.
+  bool& Naive() = 0;
+
+  //! Train the model (build the reference tree if needed).
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize) = 0;
+
+  //! Perform bichromatic range search (i.e. a search with a separate query
+  //! set).
+  virtual void Search(arma::mat&& querySet,
+                      const math::Range& range,
+                      std::vector<std::vector<size_t>>& neighbors,
+                      std::vector<std::vector<double>>& distances,
+                      const size_t leafSize) = 0;
+
+  //! Perform monochromatic range search (i.e. a search with the reference set
+  //! as the query set).
+  virtual void Search(const math::Range& range,
+                      std::vector<std::vector<size_t>>& neighbors,
+                      std::vector<std::vector<double>>& distances) = 0;
+};
+
+/**
+ * RSWrapper is a wrapper class for most RangeSearch types.
  */
 template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-using RSType = RangeSearch<metric::EuclideanDistance, arma::mat, TreeType>;
-
-/**
- * MonoSearchVisitor executes a monochromatic range search on the given
- * RSType. Range Search is performed on the reference set itself, no querySet.
- */
-class MonoSearchVisitor : public  boost::static_visitor<void>
+class RSWrapper : public RSWrapperBase
 {
- private:
-  //! The range to search for.
-  const math::Range& range;
-  //! Output neighbors.
-  std::vector<std::vector<size_t>>& neighbors;
-  //! Output distances.
-  std::vector<std::vector<double>>& distances;
-
  public:
-  //! Perform monochromatic search with the given RangeSearch object.
-  template<typename RSType>
-  void operator()(RSType* rs) const;
+  //! Create the RSWrapper object.
+  RSWrapper(const bool singleMode, const bool naive) :
+      ra(singleMode, naive)
+  {
+    // Nothing else to do.
+  }
 
-  //! Construct the MonoSearchVisitor with the given parameters.
-  MonoSearchVisitor(const math::Range& range,
-                    std::vector<std::vector<size_t>>& neighbors,
-                    std::vector<std::vector<double>>& distances):
-      range(range),
-      neighbors(neighbors),
-      distances(distances)
-  {};
+  //! Create a new RSWrapper that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual RSWrapper* Clone() const { return new RSWrapper(*this); }
+
+  //! Destruct the RSWrapper (nothing to do).
+  virtual ~RSWrapper() { }
+
+  //! Get the dataset.
+  const arma::mat& Dataset() const { return rs.ReferenceSet(); }
+
+  //! Get whether single-tree search is being used.
+  bool SingleMode() const { return rs.SingleMode(); }
+  //! Modify whether single-tree search is being used.
+  bool& SingleMode() { return rs.SingleMode(); }
+
+  //! Get whether naive search is being used.
+  bool Naive() const { return rs.Naive(); }
+  //! Modify whether naive search is being used.
+  bool& Naive() { return rs.Naive(); }
+
+  //! Train the model (build the reference tree if needed).  This ignores the
+  //! leaf size.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t /* leafSize */);
+
+  //! Perform bichromatic range search (i.e. a search with a separate query
+  //! set).  This ignores the leaf size.
+  virtual void Search(arma::mat&& querySet,
+                      const math::Range& range,
+                      std::vector<std::vector<size_t>>& neighbors,
+                      std::vector<std::vector<double>>& distances,
+                      const size_t /* leafSize */);
+
+  //! Perform monochromatic range search (i.e. a search with the reference set
+  //! as the query set).
+  virtual void Search(const math::Range& range,
+                      std::vector<std::vector<size_t>>& neighbors,
+                      std::vector<std::vector<double>>& distances);
+
+  //! Serialize the RangeSearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(rs));
+  }
+
+ protected:
+  typedef RangeSearch<metric::EuclideanDistance, arma::mat, TreeType> RSType;
+
+  //! The instantiated RangeSearch object that we are wrapping.
+  RSType rs;
 };
 
 /**
- * BiSearchVisitor executes a bichromatic range search on the given RSType.
- * We use template specialization to differentiate those tree types that
- * accept leafSize as a parameter. In these cases, before doing range search,
- * a query tree with proper leafSize is built from the querySet.
+ * LeafSizeRSWrapper wraps any RangeSearch type that needs to be able to take
+ * the leaf size into account when building trees.  The implementations of
+ * Train() and bichromatic Search() take this leaf size into account.
  */
-class BiSearchVisitor : public boost::static_visitor<void>
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+class LeafSizeRSWrapper : public RSWrapper<TreeType>
 {
- private:
-  //! The query set for the bichromatic search.
-  const arma::mat& querySet;
-  //! Range to search neighbours for.
-  const math::Range& range;
-  //! The result vector for neighbors.
-  std::vector<std::vector<size_t>>& neighbors;
-  //! The result vector for distances.
-  std::vector<std::vector<double>>& distances;
-  //! The number of points in a leaf (for BinarySpaceTrees).
-  const size_t leafSize;
-
-  //! Bichromatic range search on the given RSType considering the leafSize.
-  template<typename RSType>
-  void SearchLeaf(RSType* rs) const;
-
  public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using RSTypeT = RSType<TreeType>;
+  //! Construct the LeafSizeRSWrapper by delegating to the RSWrapper
+  //! constructor.
+  LeafSizeRSWrapper(const bool singleMode, const bool naive) :
+      RSWrapper<TreeType>(singleMode, naive)
+  {
+    // Nothing else to do.
+  }
 
-  //! Default Bichromatic range search on the given RSType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(RSTypeT<TreeType>* rs) const;
+  //! Delete the LeafSizeRSWrapper.
+  virtual ~LeafSizeRSWrapper() { }
 
-  //! Bichromatic range search on the given RSType specialized for KDTrees.
-  void operator()(RSTypeT<tree::KDTree>* rs) const;
+  //! Return a copy of the LeafSizeRSWrapper.
+  virtual LeafSizeRSWrapper* Clone() const
+  {
+    return new LeafSizeRSWrapper(*this);
+  }
 
-  //! Bichromatic range search on the given RSType specialized for BallTrees.
-  void operator()(RSTypeT<tree::BallTree>* rs) const;
+  //! Train a model with the given parameters.  This overload uses leafSize.
+  virtual void Train(arma::mat&& referenceSet,
+                     const size_t leafSize);
 
-  //! Bichromatic range search specialized for octrees.
-  void operator()(RSTypeT<tree::Octree>* rs) const;
+  //! Perform bichromatic search (e.g. search with a separate query set).  This
+  //! overload takes the leaf size into account when building the query tree.
+  virtual void Search(arma::mat&& querySet,
+                      const size_t k,
+                      arma::Mat<size_t>& neighbors,
+                      arma::mat& distances,
+                      const size_t leafSize);
 
-  //! Construct the BiSearchVisitor.
-  BiSearchVisitor(const arma::mat& querySet,
-                  const math::Range& range,
-                  std::vector<std::vector<size_t>>& neighbors,
-                  std::vector<std::vector<double>>& distances,
-                  const size_t leafSize);
+  //! Serialize the RangeSearch model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(rs));
+  }
+
+ protected:
+  using RSWrapper<TreeType>::rs;
 };
 
 /**
- * TrainVisitor sets the reference set to a new reference set on the given
- * RSType. We use template specialization to differentiate those tree types that
- * accept leafSize as a parameter. In these cases, a reference tree with proper
- * leafSize is built from the referenceSet.
+ * The RSModel class provides an abstraction for the RangeSearch class,
+ * abstracting away the TreeType parameter and allowing it to be specified at
+ * runtime.  This class is written for the sake of the `range_search` binding,
+ * but is not necessarily restricted to that usage.
  */
-class TrainVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The reference set to use for training.
-  arma::mat&& referenceSet;
-  //! The leaf size, used only by BinarySpaceTree.
-  size_t leafSize;
-  //! Train on the given RsType considering the leafSize.
-  template<typename RSType>
-  void TrainLeaf(RSType* rs) const;
-
- public:
-  //! Alias template necessary for visual c++ compiler.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using RSTypeT = RSType<TreeType>;
-
-  //! Default Train on the given RSType instance.
-  template<template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(RSTypeT<TreeType>* rs) const;
-
-  //! Train on the given RSType specialized for KDTrees.
-  void operator()(RSTypeT<tree::KDTree>* rs) const;
-
-  //! Train on the given RSType specialized for BallTrees.
-  void operator()(RSTypeT<tree::BallTree>* rs) const;
-
-  //! Train specialized for octrees.
-  void operator()(RSTypeT<tree::Octree>* rs) const;
-
-  //! Construct the TrainVisitor object with the given reference set, leafSize
-  TrainVisitor(arma::mat&& referenceSet,
-               const size_t leafSize);
-};
-
-/**
- * ReferenceSetVisitor exposes the referenceSet of the given RSType.
- */
-class ReferenceSetVisitor : public boost::static_visitor<const arma::mat&>
-{
- public:
-  //! Return the reference set.
-  template<typename RSType>
-  const arma::mat& operator()(RSType* rs) const;
-};
-
-/**
- * DeleteVisitor deletes the given RSType instance.
- */
-class DeleteVisitor : public boost::static_visitor<void>
-{
- public:
-  //! Delete the RSType object.
-  template<typename RSType>
-  void operator()(RSType* rs) const;
-};
-
-/**
- * SingleModeVisitor exposes the SingleMode() method of the given RSType.
- */
-class SingleModeVisitor : public boost::static_visitor<bool&>
-{
- public:
-  /**
-   * Get a reference to the singleMode parameter of the given RangeSeach
-   * object.
-   */
-  template<typename RSType>
-  bool& operator()(RSType* rs) const;
-};
-
-/**
- * NaiveVisitor exposes the Naive() method of the given RSType.
- */
-class NaiveVisitor : public boost::static_visitor<bool&>
-{
- public:
-  /**
-   * Get a reference to the naive parameter of the given RangeSearch object.
-   */
-  template<typename RSType>
-  bool& operator()(RSType* rs) const;
-};
-
 class RSModel
 {
  public:
@@ -232,7 +226,10 @@ class RSModel
   };
 
  private:
+  //! The type of tree we are using.
   TreeTypes treeType;
+  //! (Only used for some tree types.)  The leaf size to use when building a
+  //! tree.
   size_t leafSize;
 
   //! If true, we randomly project the data into a new basis before search.
@@ -243,22 +240,8 @@ class RSModel
   /**
    * rSearch holds an instance of the RangeSearch class for the current
    * treeType. It is initialized every time BuildModel is executed.
-   * We access to the contained value through the visitor classes defined above.
    */
-  boost::variant<RSType<tree::KDTree>*,
-                 RSType<tree::StandardCoverTree>*,
-                 RSType<tree::RTree>*,
-                 RSType<tree::RStarTree>*,
-                 RSType<tree::BallTree>*,
-                 RSType<tree::XTree>*,
-                 RSType<tree::HilbertRTree>*,
-                 RSType<tree::RPlusTree>*,
-                 RSType<tree::RPlusPlusTree>*,
-                 RSType<tree::VPTree>*,
-                 RSType<tree::RPTree>*,
-                 RSType<tree::MaxRPTree>*,
-                 RSType<tree::UBTree>*,
-                 RSType<tree::Octree>*> rSearch;
+  RSWrapperBase* rSearch;
 
  public:
   /**
@@ -304,17 +287,17 @@ class RSModel
   void serialize(Archive& ar, const uint32_t /* version */);
 
   //! Expose the dataset.
-  const arma::mat& Dataset() const;
+  const arma::mat& Dataset() const { return rSearch->Dataset(); }
 
   //! Get whether the model is in single-tree search mode.
-  bool SingleMode() const;
+  bool SingleMode() const { return rSearch->SingleMode(); }
   //! Modify whether the model is in single-tree search mode.
-  bool& SingleMode();
+  bool& SingleMode() { return rSearch->SingleMode(); }
 
   //! Get whether the model is in naive search mode.
-  bool Naive() const;
+  bool Naive() const { return rSearch->Naive(); }
   //! Modify whether the model is in naive search mode.
-  bool& Naive();
+  bool& Naive() { return rSearch->Naive(); }
 
   //! Get the leaf size (applicable to everything but the cover tree).
   size_t LeafSize() const { return leafSize; }
@@ -390,7 +373,7 @@ class RSModel
 } // namespace range
 } // namespace mlpack
 
-// Include implementation (of serialize() and inline functions).
+// Include implementation (of serialize() and templated wrapper classes).
 #include "rs_model_impl.hpp"
 
 #endif
diff --git a/src/mlpack/methods/range_search/rs_model_impl.hpp b/src/mlpack/methods/range_search/rs_model_impl.hpp
index ea94903104..983029c4fb 100644
--- a/src/mlpack/methods/range_search/rs_model_impl.hpp
+++ b/src/mlpack/methods/range_search/rs_model_impl.hpp
@@ -24,27 +24,28 @@ namespace range {
  * Initialize the RSModel with the given tree type and whether or not a random
  * basis should be used.
  */
-inline RSModel::RSModel(TreeTypes treeType, bool randomBasis) :
+RSModel::RSModel(TreeTypes treeType, bool randomBasis) :
     treeType(treeType),
     leafSize(0),
-    randomBasis(randomBasis)
+    randomBasis(randomBasis),
+    rSearch(NULL)
 {
   // Nothing to do.
 }
 
 // Copy constructor.
-inline RSModel::RSModel(const RSModel& other) :
+RSModel::RSModel(const RSModel& other) :
     treeType(other.treeType),
     leafSize(other.leafSize),
     randomBasis(other.randomBasis),
     q(other.q),
-    rSearch(other.rSearch)
+    rSearch(other.rSearch->Clone())
 {
   // Nothing to do.
 }
 
 // Move constructor.
-inline RSModel::RSModel(RSModel&& other) :
+RSModel::RSModel(RSModel&& other) :
     treeType(other.treeType),
     leafSize(other.leafSize),
     randomBasis(other.randomBasis),
@@ -55,32 +56,56 @@ inline RSModel::RSModel(RSModel&& other) :
   other.treeType = TreeTypes::KD_TREE;
   other.leafSize = 0;
   other.randomBasis = false;
-  other.rSearch = decltype(other.rSearch)();
 }
 
-inline RSModel& RSModel::operator=(RSModel other)
+// Copy operator.
+RSModel& RSModel::operator=(const RSModel& other)
 {
-  boost::apply_visitor(DeleteVisitor(), rSearch);
+  if (this != &other)
+  {
+    delete rSearch;
 
-  treeType = other.treeType;
-  leafSize = other.leafSize;
-  randomBasis = other.randomBasis;
-  q = std::move(other.q);
-  rSearch = std::move(other.rSearch);
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = other.q;
+    rSearch = other.rSearch->Clone();
+  }
+
+  return *this;
+}
+
+// Move operator.
+RSModel& RSModel::operator=(RSModel&& other)
+{
+  if (this != &other)
+  {
+    delete rSearch;
+
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = std::move(other.q);
+    rSearch = std::move(other.rSearch);
+
+    other.treeType = TreeTypes::KD_TREE;
+    other.leafSize = 0;
+    other.randomBasis = false;
+  }
 
   return *this;
 }
 
 // Clean memory, if necessary.
-inline RSModel::~RSModel()
+RSModel::~RSModel()
 {
-  boost::apply_visitor(DeleteVisitor(), rSearch);
+  delete rSearch;
 }
 
-inline void RSModel::BuildModel(arma::mat&& referenceSet,
-                                const size_t leafSize,
-                                const bool naive,
-                                const bool singleMode)
+void RSModel::BuildModel(arma::mat&& referenceSet,
+                         const size_t leafSize,
+                         const bool naive,
+                         const bool singleMode)
 {
   // Initialize random basis if necessary.
   if (randomBasis)
@@ -92,7 +117,7 @@ inline void RSModel::BuildModel(arma::mat&& referenceSet,
   this->leafSize = leafSize;
 
   // Clean memory, if necessary.
-  boost::apply_visitor(DeleteVisitor(), rSearch);
+  delete rSearch;
 
   // Do we need to modify the reference set?
   if (randomBasis)
@@ -107,64 +132,63 @@ inline void RSModel::BuildModel(arma::mat&& referenceSet,
   switch (treeType)
   {
     case KD_TREE:
-      rSearch = new RSType<tree::KDTree> (naive, singleMode);
+      rSearch = new LeafSizeRSWrapper<tree::KDTree>(naive, singleMode);
       break;
 
     case COVER_TREE:
-      rSearch = new RSType<tree::StandardCoverTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::StandardCoverTree>(naive, singleMode);
       break;
 
     case R_TREE:
-      rSearch = new RSType<tree::RTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::RTree>(naive, singleMode);
       break;
 
     case R_STAR_TREE:
-      rSearch = new RSType<tree::RStarTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::RStarTree>(naive, singleMode);
       break;
 
     case BALL_TREE:
-      rSearch = new RSType<tree::BallTree>(naive, singleMode);
+      rSearch = new LeafSizeRSWrapper<tree::BallTree>(naive, singleMode);
       break;
 
     case X_TREE:
-      rSearch = new RSType<tree::XTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::XTree>(naive, singleMode);
       break;
 
     case HILBERT_R_TREE:
-      rSearch = new RSType<tree::HilbertRTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::HilbertRTree>(naive, singleMode);
       break;
 
     case R_PLUS_TREE:
-      rSearch = new RSType<tree::RPlusTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::RPlusTree>(naive, singleMode);
       break;
 
     case R_PLUS_PLUS_TREE:
-      rSearch = new RSType<tree::RPlusPlusTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::RPlusPlusTree>(naive, singleMode);
       break;
 
     case VP_TREE:
-      rSearch = new RSType<tree::VPTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::VPTree>(naive, singleMode);
       break;
 
     case RP_TREE:
-      rSearch = new RSType<tree::RPTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::RPTree>(naive, singleMode);
       break;
 
     case MAX_RP_TREE:
-      rSearch = new RSType<tree::MaxRPTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::MaxRPTree>(naive, singleMode);
       break;
 
     case UB_TREE:
-      rSearch = new RSType<tree::UBTree>(naive, singleMode);
+      rSearch = new RSWrapper<tree::UBTree>(naive, singleMode);
       break;
 
     case OCTREE:
-      rSearch = new RSType<tree::Octree>(naive, singleMode);
+      rSearch = new LeafSizeRSWrapper<tree::Octree>(naive, singleMode);
       break;
   }
 
-  TrainVisitor tn(std::move(referenceSet), leafSize);
-  boost::apply_visitor(tn, rSearch);
+  rSearch->Train(std::move(referenceSet), leafSize);
 
   if (!naive)
   {
@@ -174,10 +198,10 @@ inline void RSModel::BuildModel(arma::mat&& referenceSet,
 }
 
 // Perform range search.
-inline void RSModel::Search(arma::mat&& querySet,
-                            const math::Range& range,
-                            std::vector<std::vector<size_t>>& neighbors,
-                            std::vector<std::vector<double>>& distances)
+void RSModel::Search(arma::mat&& querySet,
+                     const math::Range& range,
+                     std::vector<std::vector<size_t>>& neighbors,
+                     std::vector<std::vector<double>>& distances)
 {
   // We may need to map the query set randomly.
   if (randomBasis)
@@ -192,16 +216,13 @@ inline void RSModel::Search(arma::mat&& querySet,
   else
     Log::Info << "brute-force (naive) search..." << std::endl;
 
-
-  BiSearchVisitor search(querySet, range, neighbors, distances,
-      leafSize);
-  boost::apply_visitor(search, rSearch);
+  rSearch->Search(std::move(querySet), range, neighbors, distances, leafSize);
 }
 
 // Perform range search (monochromatic case).
-inline void RSModel::Search(const math::Range& range,
-                            std::vector<std::vector<size_t>>& neighbors,
-                            std::vector<std::vector<double>>& distances)
+void RSModel::Search(const math::Range& range,
+                     std::vector<std::vector<size_t>>& neighbors,
+                     std::vector<std::vector<double>>& distances)
 {
   Log::Info << "Search for points in the range [" << range.Lo() << ", "
       << range.Hi() << "] with ";
@@ -212,12 +233,11 @@ inline void RSModel::Search(const math::Range& range,
   else
     Log::Info << "brute-force (naive) search..." << std::endl;
 
-  MonoSearchVisitor search(range, neighbors, distances);
-  boost::apply_visitor(search, rSearch);
+  rSearch->Search(range, neighbors, distances);
 }
 
 // Get the name of the tree type.
-inline std::string RSModel::TreeName() const
+std::string RSModel::TreeName() const
 {
   switch (treeType)
   {
@@ -255,34 +275,11 @@ inline std::string RSModel::TreeName() const
 }
 
 // Clean memory.
-inline void RSModel::CleanMemory()
+void RSModel::CleanMemory()
 {
-  boost::apply_visitor(DeleteVisitor(), rSearch);
+  delete rSearch;
 }
 
-//! Monochromatic range search on the given RSType instance.
-template<typename RSType>
-void MonoSearchVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    return rs->Search(range, neighbors, distances);
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Save parameters for bichromatic range search.
-inline BiSearchVisitor::BiSearchVisitor(
-    const arma::mat& querySet,
-    const math::Range& range,
-    std::vector<std::vector<size_t>>& neighbors,
-    std::vector<std::vector<double>>& distances,
-    const size_t leafSize) :
-    querySet(querySet),
-    range(range),
-    neighbors(neighbors),
-    distances(distances),
-    leafSize(leafSize)
-{}
-
 //! Default Bichromatic range search on the given RSType instance.
 template<template<typename TreeMetricType,
                   typename TreeStatType,
@@ -294,30 +291,6 @@ void BiSearchVisitor::operator()(RSTypeT<TreeType>* rs) const
   throw std::runtime_error("no range search model initialized");
 }
 
-//! Bichromatic range search on the given RSType specialized for KDTrees.
-inline void BiSearchVisitor::operator()(RSTypeT<tree::KDTree>* rs) const
-{
-  if (rs)
-    return SearchLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Bichromatic range search on the given RSType specialized for BallTrees.
-inline void BiSearchVisitor::operator()(RSTypeT<tree::BallTree>* rs) const
-{
-  if (rs)
-    return SearchLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Bichromatic range search specialized for Ocrees.
-inline void BiSearchVisitor::operator()(RSTypeT<tree::Octree>* rs) const
-{
-  if (rs)
-    return SearchLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
 //! Bichromatic range search on the given RSType considering the leafSize.
 template<typename RSType>
 void BiSearchVisitor::SearchLeaf(RSType* rs) const
@@ -368,30 +341,6 @@ void TrainVisitor::operator()(RSTypeT<TreeType>* rs) const
   throw std::runtime_error("no range search model initialized");
 }
 
-//! Train on the given RSType specialized for KDTrees.
-inline void TrainVisitor::operator()(RSTypeT<tree::KDTree>* rs) const
-{
-  if (rs)
-    return TrainLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Train on the given RSType specialized for BallTrees.
-inline void TrainVisitor::operator()(RSTypeT<tree::BallTree>* rs) const
-{
-  if (rs)
-    return TrainLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Train specialized for Octrees.
-inline void TrainVisitor::operator()(RSTypeT<tree::Octree>* rs) const
-{
-  if (rs)
-    return TrainLeaf(rs);
-  throw std::runtime_error("no range search model initialized");
-}
-
 //! Train on the given RSType considering the leafSize.
 template<typename RSType>
 void TrainVisitor::TrainLeaf(RSType* rs) const
@@ -412,41 +361,6 @@ void TrainVisitor::TrainLeaf(RSType* rs) const
   }
 }
 
-//! Expose the referenceSet of the given RSType.
-template<typename RSType>
-const arma::mat& ReferenceSetVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    return rs->ReferenceSet();
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! For cleaning memory
-template<typename RSType>
-void DeleteVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    delete rs;
-}
-
-//! Return whether single mode enabled
-template<typename RSType>
-bool& SingleModeVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    return rs->SingleMode();
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Exposes Naive() function of given RSType
-template<typename RSType>
-bool& NaiveVisitor::operator()(RSType* rs) const
-{
-  if (rs)
-    return rs->Naive();
-  throw std::runtime_error("no range search model initialized");
-}
-
 // Serialize the model.
 template<typename Archive>
 void RSModel::serialize(Archive& ar, const uint32_t /* version */)
@@ -457,37 +371,12 @@ void RSModel::serialize(Archive& ar, const uint32_t /* version */)
 
   // This should never happen, but just in case...
   if (cereal::is_loading<Archive>())
-    boost::apply_visitor(DeleteVisitor(), rSearch);
+    delete rSearch;
 
   // We'll only need to serialize one of the model objects, based on the type.
   ar(CEREAL_VARIANT_POINTER(rSearch));
 }
 
-inline const arma::mat& RSModel::Dataset() const
-{
-  return boost::apply_visitor(ReferenceSetVisitor(), rSearch);
-}
-
-inline bool RSModel::SingleMode() const
-{
-  return boost::apply_visitor(SingleModeVisitor(), rSearch);
-}
-
-inline bool& RSModel::SingleMode()
-{
-  return boost::apply_visitor(SingleModeVisitor(), rSearch);
-}
-
-inline bool RSModel::Naive() const
-{
-  return boost::apply_visitor(NaiveVisitor(), rSearch);
-}
-
-inline bool& RSModel::Naive()
-{
-  return boost::apply_visitor(NaiveVisitor(), rSearch);
-}
-
 } // namespace range
 } // namespace mlpack
 

From 0cb7e6427312a64f1b65fcd241015242b2b58f7b Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 10 Jan 2021 11:13:24 -0500
Subject: [PATCH 055/253] Remove boost::visitor from RSModel.

---
 .../methods/range_search/CMakeLists.txt       |   1 +
 .../methods/range_search/range_search.hpp     |   7 +-
 src/mlpack/methods/range_search/rs_model.cpp  | 280 ++++++++++
 src/mlpack/methods/range_search/rs_model.hpp  |  64 +--
 .../methods/range_search/rs_model_impl.hpp    | 487 +++++++-----------
 5 files changed, 495 insertions(+), 344 deletions(-)
 create mode 100644 src/mlpack/methods/range_search/rs_model.cpp

diff --git a/src/mlpack/methods/range_search/CMakeLists.txt b/src/mlpack/methods/range_search/CMakeLists.txt
index 0a1912b6b4..8a0ff5925f 100644
--- a/src/mlpack/methods/range_search/CMakeLists.txt
+++ b/src/mlpack/methods/range_search/CMakeLists.txt
@@ -8,6 +8,7 @@ set(SOURCES
   range_search_stat.hpp
   rs_model.hpp
   rs_model_impl.hpp
+  rs_model.cpp
 )
 
 # Add directory name to sources.
diff --git a/src/mlpack/methods/range_search/range_search.hpp b/src/mlpack/methods/range_search/range_search.hpp
index 06575005ac..257401d064 100644
--- a/src/mlpack/methods/range_search/range_search.hpp
+++ b/src/mlpack/methods/range_search/range_search.hpp
@@ -22,7 +22,10 @@ namespace mlpack {
 namespace range /** Range-search routines. */ {
 
 //! Forward declaration.
-class TrainVisitor;
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+class LeafSizeRSWrapper;
 
 /**
  * The RangeSearch class is a template class for performing range searches.  It
@@ -310,7 +313,7 @@ class RangeSearch
   size_t scores;
 
   //! For access to mappings when building models.
-  friend class TrainVisitor;
+  friend class LeafSizeRSWrapper<TreeType>;
 };
 
 } // namespace range
diff --git a/src/mlpack/methods/range_search/rs_model.cpp b/src/mlpack/methods/range_search/rs_model.cpp
new file mode 100644
index 0000000000..fdf3cd2128
--- /dev/null
+++ b/src/mlpack/methods/range_search/rs_model.cpp
@@ -0,0 +1,280 @@
+/**
+ * @file methods/range_search/rs_model_impl.hpp
+ * @author Ryan Curtin
+ *
+ * Implementation of serialize() and inline functions for RSModel.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include "rs_model.hpp"
+
+#include <mlpack/core/math/random_basis.hpp>
+
+namespace mlpack {
+namespace range {
+
+/**
+ * Initialize the RSModel with the given tree type and whether or not a random
+ * basis should be used.
+ */
+RSModel::RSModel(TreeTypes treeType, bool randomBasis) :
+    treeType(treeType),
+    leafSize(0),
+    randomBasis(randomBasis),
+    rSearch(NULL)
+{
+  // Nothing to do.
+}
+
+// Copy constructor.
+RSModel::RSModel(const RSModel& other) :
+    treeType(other.treeType),
+    leafSize(other.leafSize),
+    randomBasis(other.randomBasis),
+    q(other.q),
+    rSearch(other.rSearch->Clone())
+{
+  // Nothing to do.
+}
+
+// Move constructor.
+RSModel::RSModel(RSModel&& other) :
+    treeType(other.treeType),
+    leafSize(other.leafSize),
+    randomBasis(other.randomBasis),
+    q(std::move(other.q)),
+    rSearch(std::move(other.rSearch))
+{
+  // Reset other model.
+  other.treeType = TreeTypes::KD_TREE;
+  other.leafSize = 0;
+  other.randomBasis = false;
+}
+
+// Copy operator.
+RSModel& RSModel::operator=(const RSModel& other)
+{
+  if (this != &other)
+  {
+    delete rSearch;
+
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = other.q;
+    rSearch = other.rSearch->Clone();
+  }
+
+  return *this;
+}
+
+// Move operator.
+RSModel& RSModel::operator=(RSModel&& other)
+{
+  if (this != &other)
+  {
+    delete rSearch;
+
+    treeType = other.treeType;
+    leafSize = other.leafSize;
+    randomBasis = other.randomBasis;
+    q = std::move(other.q);
+    rSearch = std::move(other.rSearch);
+
+    other.treeType = TreeTypes::KD_TREE;
+    other.leafSize = 0;
+    other.randomBasis = false;
+  }
+
+  return *this;
+}
+
+// Clean memory, if necessary.
+RSModel::~RSModel()
+{
+  delete rSearch;
+}
+
+void RSModel::BuildModel(arma::mat&& referenceSet,
+                         const size_t leafSize,
+                         const bool naive,
+                         const bool singleMode)
+{
+  // Initialize random basis if necessary.
+  if (randomBasis)
+  {
+    Log::Info << "Creating random basis..." << std::endl;
+    math::RandomBasis(q, referenceSet.n_rows);
+  }
+
+  this->leafSize = leafSize;
+
+  // Clean memory, if necessary.
+  delete rSearch;
+
+  // Do we need to modify the reference set?
+  if (randomBasis)
+    referenceSet = q * referenceSet;
+
+  if (!naive)
+  {
+    Timer::Start("tree_building");
+    Log::Info << "Building reference tree..." << std::endl;
+  }
+
+  switch (treeType)
+  {
+    case KD_TREE:
+      rSearch = new LeafSizeRSWrapper<tree::KDTree>(naive, singleMode);
+      break;
+
+    case COVER_TREE:
+      rSearch = new RSWrapper<tree::StandardCoverTree>(naive, singleMode);
+      break;
+
+    case R_TREE:
+      rSearch = new RSWrapper<tree::RTree>(naive, singleMode);
+      break;
+
+    case R_STAR_TREE:
+      rSearch = new RSWrapper<tree::RStarTree>(naive, singleMode);
+      break;
+
+    case BALL_TREE:
+      rSearch = new LeafSizeRSWrapper<tree::BallTree>(naive, singleMode);
+      break;
+
+    case X_TREE:
+      rSearch = new RSWrapper<tree::XTree>(naive, singleMode);
+      break;
+
+    case HILBERT_R_TREE:
+      rSearch = new RSWrapper<tree::HilbertRTree>(naive, singleMode);
+      break;
+
+    case R_PLUS_TREE:
+      rSearch = new RSWrapper<tree::RPlusTree>(naive, singleMode);
+      break;
+
+    case R_PLUS_PLUS_TREE:
+      rSearch = new RSWrapper<tree::RPlusPlusTree>(naive, singleMode);
+      break;
+
+    case VP_TREE:
+      rSearch = new RSWrapper<tree::VPTree>(naive, singleMode);
+      break;
+
+    case RP_TREE:
+      rSearch = new RSWrapper<tree::RPTree>(naive, singleMode);
+      break;
+
+    case MAX_RP_TREE:
+      rSearch = new RSWrapper<tree::MaxRPTree>(naive, singleMode);
+      break;
+
+    case UB_TREE:
+      rSearch = new RSWrapper<tree::UBTree>(naive, singleMode);
+      break;
+
+    case OCTREE:
+      rSearch = new LeafSizeRSWrapper<tree::Octree>(naive, singleMode);
+      break;
+  }
+
+  rSearch->Train(std::move(referenceSet), leafSize);
+
+  if (!naive)
+  {
+    Timer::Stop("tree_building");
+    Log::Info << "Tree built." << std::endl;
+  }
+}
+
+// Perform range search.
+void RSModel::Search(arma::mat&& querySet,
+                     const math::Range& range,
+                     std::vector<std::vector<size_t>>& neighbors,
+                     std::vector<std::vector<double>>& distances)
+{
+  // We may need to map the query set randomly.
+  if (randomBasis)
+    querySet = q * querySet;
+
+  Log::Info << "Search for points in the range [" << range.Lo() << ", "
+      << range.Hi() << "] with ";
+  if (!Naive() && !SingleMode())
+    Log::Info << "dual-tree " << TreeName() << " search..." << std::endl;
+  else if (!Naive())
+    Log::Info << "single-tree " << TreeName() << " search..." << std::endl;
+  else
+    Log::Info << "brute-force (naive) search..." << std::endl;
+
+  rSearch->Search(std::move(querySet), range, neighbors, distances, leafSize);
+}
+
+// Perform range search (monochromatic case).
+void RSModel::Search(const math::Range& range,
+                     std::vector<std::vector<size_t>>& neighbors,
+                     std::vector<std::vector<double>>& distances)
+{
+  Log::Info << "Search for points in the range [" << range.Lo() << ", "
+      << range.Hi() << "] with ";
+  if (!Naive() && !SingleMode())
+    Log::Info << "dual-tree " << TreeName() << " search..." << std::endl;
+  else if (!Naive())
+    Log::Info << "single-tree " << TreeName() << " search..." << std::endl;
+  else
+    Log::Info << "brute-force (naive) search..." << std::endl;
+
+  rSearch->Search(range, neighbors, distances);
+}
+
+// Get the name of the tree type.
+std::string RSModel::TreeName() const
+{
+  switch (treeType)
+  {
+    case KD_TREE:
+      return "kd-tree";
+    case COVER_TREE:
+      return "cover tree";
+    case R_TREE:
+      return "R tree";
+    case R_STAR_TREE:
+      return "R* tree";
+    case BALL_TREE:
+      return "ball tree";
+    case X_TREE:
+      return "X tree";
+    case HILBERT_R_TREE:
+      return "Hilbert R tree";
+    case R_PLUS_TREE:
+      return "R+ tree";
+    case R_PLUS_PLUS_TREE:
+      return "R++ tree";
+    case VP_TREE:
+      return "vantage point tree";
+    case RP_TREE:
+      return "random projection tree (mean split)";
+    case MAX_RP_TREE:
+      return "random projection tree (max split)";
+    case UB_TREE:
+      return "UB tree";
+    case OCTREE:
+      return "octree";
+    default:
+      return "unknown tree";
+  }
+}
+
+// Clean memory.
+void RSModel::CleanMemory()
+{
+  delete rSearch;
+}
+
+} // namespace range
+} // namespace mlpack
diff --git a/src/mlpack/methods/range_search/rs_model.hpp b/src/mlpack/methods/range_search/rs_model.hpp
index bf1f6b98f4..12638c2836 100644
--- a/src/mlpack/methods/range_search/rs_model.hpp
+++ b/src/mlpack/methods/range_search/rs_model.hpp
@@ -19,7 +19,6 @@
 #include <mlpack/core/tree/cover_tree.hpp>
 #include <mlpack/core/tree/rectangle_tree.hpp>
 #include <mlpack/core/tree/octree.hpp>
-#include <boost/variant.hpp>
 
 #include "range_search.hpp"
 
@@ -47,17 +46,17 @@ class RSWrapperBase
   virtual ~RSWrapperBase() { }
 
   //! Get the dataset.
-  const arma::mat& Dataset() const = 0;
+  virtual const arma::mat& Dataset() const = 0;
 
   //! Get whether single-tree search is being used.
-  bool SingleMode() const = 0;
+  virtual bool SingleMode() const = 0;
   //! Modify whether single-tree search is being used.
-  bool& SingleMode() = 0;
+  virtual bool& SingleMode() = 0;
 
   //! Get whether naive search is being used.
-  bool Naive() const = 0;
+  virtual bool Naive() const = 0;
   //! Modify whether naive search is being used.
-  bool& Naive() = 0;
+  virtual bool& Naive() = 0;
 
   //! Train the model (build the reference tree if needed).
   virtual void Train(arma::mat&& referenceSet,
@@ -89,7 +88,7 @@ class RSWrapper : public RSWrapperBase
  public:
   //! Create the RSWrapper object.
   RSWrapper(const bool singleMode, const bool naive) :
-      ra(singleMode, naive)
+      rs(singleMode, naive)
   {
     // Nothing else to do.
   }
@@ -182,9 +181,9 @@ class LeafSizeRSWrapper : public RSWrapper<TreeType>
   //! Perform bichromatic search (e.g. search with a separate query set).  This
   //! overload takes the leaf size into account when building the query tree.
   virtual void Search(arma::mat&& querySet,
-                      const size_t k,
-                      arma::Mat<size_t>& neighbors,
-                      arma::mat& distances,
+                      const math::Range& range,
+                      std::vector<std::vector<size_t>>& neighbors,
+                      std::vector<std::vector<double>>& distances,
                       const size_t leafSize);
 
   //! Serialize the RangeSearch model.
@@ -225,25 +224,6 @@ class RSModel
     OCTREE
   };
 
- private:
-  //! The type of tree we are using.
-  TreeTypes treeType;
-  //! (Only used for some tree types.)  The leaf size to use when building a
-  //! tree.
-  size_t leafSize;
-
-  //! If true, we randomly project the data into a new basis before search.
-  bool randomBasis;
-  //! Random projection matrix.
-  arma::mat q;
-
-  /**
-   * rSearch holds an instance of the RangeSearch class for the current
-   * treeType. It is initialized every time BuildModel is executed.
-   */
-  RSWrapperBase* rSearch;
-
- public:
   /**
    * Initialize the RSModel with the given type and whether or not a random
    * basis should be used.
@@ -271,11 +251,16 @@ class RSModel
   /**
    * Copy the given RSModel.
    *
-   * Use std::move to pass in the model if the old copy is no longer needed.
+   * @param other RSModel to copy.
+   */
+  RSModel& operator=(const RSModel& other);
+
+  /**
+   * Take ownership of the given RSModel's data.
    *
    * @param other RSModel to copy.
    */
-  RSModel& operator=(RSModel other);
+  RSModel& operator=(RSModel&& other);
 
   /**
    * Clean memory, if necessary.
@@ -358,6 +343,23 @@ class RSModel
               std::vector<std::vector<double>>& distances);
 
  private:
+  //! The type of tree we are using.
+  TreeTypes treeType;
+  //! (Only used for some tree types.)  The leaf size to use when building a
+  //! tree.
+  size_t leafSize;
+
+  //! If true, we randomly project the data into a new basis before search.
+  bool randomBasis;
+  //! Random projection matrix.
+  arma::mat q;
+
+  /**
+   * rSearch holds an instance of the RangeSearch class for the current
+   * treeType. It is initialized every time BuildModel is executed.
+   */
+  RSWrapperBase* rSearch;
+
   /**
    * Return a string representing the name of the tree.  This is used for
    * logging output.
diff --git a/src/mlpack/methods/range_search/rs_model_impl.hpp b/src/mlpack/methods/range_search/rs_model_impl.hpp
index 983029c4fb..2df060f977 100644
--- a/src/mlpack/methods/range_search/rs_model_impl.hpp
+++ b/src/mlpack/methods/range_search/rs_model_impl.hpp
@@ -20,295 +20,87 @@
 namespace mlpack {
 namespace range {
 
-/**
- * Initialize the RSModel with the given tree type and whether or not a random
- * basis should be used.
- */
-RSModel::RSModel(TreeTypes treeType, bool randomBasis) :
-    treeType(treeType),
-    leafSize(0),
-    randomBasis(randomBasis),
-    rSearch(NULL)
-{
-  // Nothing to do.
-}
-
-// Copy constructor.
-RSModel::RSModel(const RSModel& other) :
-    treeType(other.treeType),
-    leafSize(other.leafSize),
-    randomBasis(other.randomBasis),
-    q(other.q),
-    rSearch(other.rSearch->Clone())
-{
-  // Nothing to do.
-}
-
-// Move constructor.
-RSModel::RSModel(RSModel&& other) :
-    treeType(other.treeType),
-    leafSize(other.leafSize),
-    randomBasis(other.randomBasis),
-    q(std::move(other.q)),
-    rSearch(std::move(other.rSearch))
-{
-  // Reset other model.
-  other.treeType = TreeTypes::KD_TREE;
-  other.leafSize = 0;
-  other.randomBasis = false;
-}
-
-// Copy operator.
-RSModel& RSModel::operator=(const RSModel& other)
-{
-  if (this != &other)
-  {
-    delete rSearch;
-
-    treeType = other.treeType;
-    leafSize = other.leafSize;
-    randomBasis = other.randomBasis;
-    q = other.q;
-    rSearch = other.rSearch->Clone();
-  }
-
-  return *this;
-}
-
-// Move operator.
-RSModel& RSModel::operator=(RSModel&& other)
-{
-  if (this != &other)
-  {
-    delete rSearch;
-
-    treeType = other.treeType;
-    leafSize = other.leafSize;
-    randomBasis = other.randomBasis;
-    q = std::move(other.q);
-    rSearch = std::move(other.rSearch);
-
-    other.treeType = TreeTypes::KD_TREE;
-    other.leafSize = 0;
-    other.randomBasis = false;
-  }
-
-  return *this;
-}
-
-// Clean memory, if necessary.
-RSModel::~RSModel()
-{
-  delete rSearch;
-}
-
-void RSModel::BuildModel(arma::mat&& referenceSet,
-                         const size_t leafSize,
-                         const bool naive,
-                         const bool singleMode)
-{
-  // Initialize random basis if necessary.
-  if (randomBasis)
-  {
-    Log::Info << "Creating random basis..." << std::endl;
-    math::RandomBasis(q, referenceSet.n_rows);
-  }
-
-  this->leafSize = leafSize;
-
-  // Clean memory, if necessary.
-  delete rSearch;
-
-  // Do we need to modify the reference set?
-  if (randomBasis)
-    referenceSet = q * referenceSet;
-
-  if (!naive)
-  {
-    Timer::Start("tree_building");
-    Log::Info << "Building reference tree..." << std::endl;
-  }
-
-  switch (treeType)
-  {
-    case KD_TREE:
-      rSearch = new LeafSizeRSWrapper<tree::KDTree>(naive, singleMode);
-      break;
-
-    case COVER_TREE:
-      rSearch = new RSWrapper<tree::StandardCoverTree>(naive, singleMode);
-      break;
-
-    case R_TREE:
-      rSearch = new RSWrapper<tree::RTree>(naive, singleMode);
-      break;
-
-    case R_STAR_TREE:
-      rSearch = new RSWrapper<tree::RStarTree>(naive, singleMode);
-      break;
-
-    case BALL_TREE:
-      rSearch = new LeafSizeRSWrapper<tree::BallTree>(naive, singleMode);
-      break;
-
-    case X_TREE:
-      rSearch = new RSWrapper<tree::XTree>(naive, singleMode);
-      break;
-
-    case HILBERT_R_TREE:
-      rSearch = new RSWrapper<tree::HilbertRTree>(naive, singleMode);
-      break;
-
-    case R_PLUS_TREE:
-      rSearch = new RSWrapper<tree::RPlusTree>(naive, singleMode);
-      break;
-
-    case R_PLUS_PLUS_TREE:
-      rSearch = new RSWrapper<tree::RPlusPlusTree>(naive, singleMode);
-      break;
-
-    case VP_TREE:
-      rSearch = new RSWrapper<tree::VPTree>(naive, singleMode);
-      break;
-
-    case RP_TREE:
-      rSearch = new RSWrapper<tree::RPTree>(naive, singleMode);
-      break;
-
-    case MAX_RP_TREE:
-      rSearch = new RSWrapper<tree::MaxRPTree>(naive, singleMode);
-      break;
-
-    case UB_TREE:
-      rSearch = new RSWrapper<tree::UBTree>(naive, singleMode);
-      break;
-
-    case OCTREE:
-      rSearch = new LeafSizeRSWrapper<tree::Octree>(naive, singleMode);
-      break;
-  }
-
-  rSearch->Train(std::move(referenceSet), leafSize);
-
-  if (!naive)
-  {
-    Timer::Stop("tree_building");
-    Log::Info << "Tree built." << std::endl;
-  }
-}
-
-// Perform range search.
-void RSModel::Search(arma::mat&& querySet,
-                     const math::Range& range,
-                     std::vector<std::vector<size_t>>& neighbors,
-                     std::vector<std::vector<double>>& distances)
-{
-  // We may need to map the query set randomly.
-  if (randomBasis)
-    querySet = q * querySet;
-
-  Log::Info << "Search for points in the range [" << range.Lo() << ", "
-      << range.Hi() << "] with ";
-  if (!Naive() && !SingleMode())
-    Log::Info << "dual-tree " << TreeName() << " search..." << std::endl;
-  else if (!Naive())
-    Log::Info << "single-tree " << TreeName() << " search..." << std::endl;
-  else
-    Log::Info << "brute-force (naive) search..." << std::endl;
-
-  rSearch->Search(std::move(querySet), range, neighbors, distances, leafSize);
-}
-
-// Perform range search (monochromatic case).
-void RSModel::Search(const math::Range& range,
-                     std::vector<std::vector<size_t>>& neighbors,
-                     std::vector<std::vector<double>>& distances)
-{
-  Log::Info << "Search for points in the range [" << range.Lo() << ", "
-      << range.Hi() << "] with ";
-  if (!Naive() && !SingleMode())
-    Log::Info << "dual-tree " << TreeName() << " search..." << std::endl;
-  else if (!Naive())
-    Log::Info << "single-tree " << TreeName() << " search..." << std::endl;
-  else
-    Log::Info << "brute-force (naive) search..." << std::endl;
-
-  rSearch->Search(range, neighbors, distances);
-}
-
-// Get the name of the tree type.
-std::string RSModel::TreeName() const
-{
-  switch (treeType)
-  {
-    case KD_TREE:
-      return "kd-tree";
-    case COVER_TREE:
-      return "cover tree";
-    case R_TREE:
-      return "R tree";
-    case R_STAR_TREE:
-      return "R* tree";
-    case BALL_TREE:
-      return "ball tree";
-    case X_TREE:
-      return "X tree";
-    case HILBERT_R_TREE:
-      return "Hilbert R tree";
-    case R_PLUS_TREE:
-      return "R+ tree";
-    case R_PLUS_PLUS_TREE:
-      return "R++ tree";
-    case VP_TREE:
-      return "vantage point tree";
-    case RP_TREE:
-      return "random projection tree (mean split)";
-    case MAX_RP_TREE:
-      return "random projection tree (max split)";
-    case UB_TREE:
-      return "UB tree";
-    case OCTREE:
-      return "octree";
-    default:
-      return "unknown tree";
-  }
-}
-
-// Clean memory.
-void RSModel::CleanMemory()
-{
-  delete rSearch;
-}
-
-//! Default Bichromatic range search on the given RSType instance.
 template<template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-void BiSearchVisitor::operator()(RSTypeT<TreeType>* rs) const
+void RSWrapper<TreeType>::Train(arma::mat&& referenceSet,
+                                const size_t /* leafSize */)
 {
-  if (rs)
-    return rs->Search(querySet, range, neighbors, distances);
-  throw std::runtime_error("no range search model initialized");
+  rs.Train(std::move(referenceSet));
 }
 
-//! Bichromatic range search on the given RSType considering the leafSize.
-template<typename RSType>
-void BiSearchVisitor::SearchLeaf(RSType* rs) const
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void RSWrapper<TreeType>::Search(arma::mat&& querySet,
+                                 const math::Range& range,
+                                 std::vector<std::vector<size_t>>& neighbors,
+                                 std::vector<std::vector<double>>& distances,
+                                 const size_t /* leafSize */)
 {
-  if (!rs->Naive() && !rs->SingleMode())
+  rs.Search(std::move(querySet), range, neighbors, distances);
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void RSWrapper<TreeType>::Search(const math::Range& range,
+                                 std::vector<std::vector<size_t>>& neighbors,
+                                 std::vector<std::vector<double>>& distances)
+{
+  rs.Search(range, neighbors, distances);
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void LeafSizeRSWrapper<TreeType>::Train(arma::mat&& referenceSet,
+                                        const size_t leafSize)
+{
+  if (rs.Naive())
+  {
+    rs.Train(std::move(referenceSet));
+  }
+  else
+  {
+    std::vector<size_t> oldFromNewReferences;
+    typename decltype(rs)::Tree* tree =
+        new typename decltype(rs)::Tree(std::move(referenceSet),
+                                        oldFromNewReferences,
+                                        leafSize);
+    rs.Train(tree);
+
+    // Give the model ownership of the tree and the mappings.
+    rs.treeOwner = true;
+    rs.oldFromNewReferences = std::move(oldFromNewReferences);
+  }
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void LeafSizeRSWrapper<TreeType>::Search(
+    arma::mat&& querySet,
+    const math::Range& range,
+    std::vector<std::vector<size_t>>& neighbors,
+    std::vector<std::vector<double>>& distances,
+    const size_t leafSize)
+{
+  if (!rs.Naive() && !rs.SingleMode())
   {
     // Build a second tree and search.
     Timer::Start("tree_building");
     Log::Info << "Building query tree..." << std::endl;
     std::vector<size_t> oldFromNewQueries;
-    typename RSType::Tree queryTree(std::move(querySet), oldFromNewQueries,
-        leafSize);
+    typename decltype(rs)::Tree queryTree(std::move(querySet),
+                                          oldFromNewQueries,
+                                          leafSize);
     Log::Info << "Tree built." << std::endl;
     Timer::Stop("tree_building");
 
     std::vector<std::vector<size_t>> neighborsOut;
     std::vector<std::vector<double>> distancesOut;
-    rs->Search(&queryTree, range, neighborsOut, distancesOut);
+    rs.Search(&queryTree, range, neighborsOut, distancesOut);
 
     // Remap the query points.
     neighbors.resize(queryTree.Dataset().n_cols);
@@ -319,45 +111,9 @@ void BiSearchVisitor::SearchLeaf(RSType* rs) const
       distances[oldFromNewQueries[i]] = distancesOut[i];
     }
   }
-  else
-    rs->Search(querySet, range, neighbors, distances);
-}
-
-//! Save parameters for Train.
-inline TrainVisitor::TrainVisitor(arma::mat&& referenceSet,
-                                  const size_t leafSize) :
-    referenceSet(std::move(referenceSet)),
-    leafSize(leafSize)
-{}
-
-//! Default Train on the given RSType instance.
-template<template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void TrainVisitor::operator()(RSTypeT<TreeType>* rs) const
-{
-  if (rs)
-    return rs->Train(std::move(referenceSet));
-  throw std::runtime_error("no range search model initialized");
-}
-
-//! Train on the given RSType considering the leafSize.
-template<typename RSType>
-void TrainVisitor::TrainLeaf(RSType* rs) const
-{
-  if (rs->Naive())
-    rs->Train(std::move(referenceSet));
   else
   {
-    std::vector<size_t> oldFromNewReferences;
-    typename RSType::Tree* tree =
-        new typename RSType::Tree(std::move(referenceSet), oldFromNewReferences,
-        leafSize);
-    rs->Train(tree);
-
-    // Give the model ownership of the tree and the mappings.
-    rs->treeOwner = true;
-    rs->oldFromNewReferences = std::move(oldFromNewReferences);
+    rs.Search(std::move(querySet), range, neighbors, distances);
   }
 }
 
@@ -373,8 +129,117 @@ void RSModel::serialize(Archive& ar, const uint32_t /* version */)
   if (cereal::is_loading<Archive>())
     delete rSearch;
 
-  // We'll only need to serialize one of the model objects, based on the type.
-  ar(CEREAL_VARIANT_POINTER(rSearch));
+  // Avoid polymorphic serialization by explicitly serializing the correct type.
+  switch (treeType)
+  {
+    case KD_TREE:
+      {
+        LeafSizeRSWrapper<tree::KDTree>& typedSearch =
+            dynamic_cast<LeafSizeRSWrapper<tree::KDTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case COVER_TREE:
+      {
+        RSWrapper<tree::StandardCoverTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::StandardCoverTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case R_TREE:
+      {
+        RSWrapper<tree::RTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::RTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case R_STAR_TREE:
+      {
+        RSWrapper<tree::RStarTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::RStarTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case BALL_TREE:
+      {
+        LeafSizeRSWrapper<tree::BallTree>& typedSearch =
+            dynamic_cast<LeafSizeRSWrapper<tree::BallTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case X_TREE:
+      {
+        RSWrapper<tree::XTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::XTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case HILBERT_R_TREE:
+      {
+        RSWrapper<tree::HilbertRTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::HilbertRTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case R_PLUS_TREE:
+      {
+        RSWrapper<tree::RPlusTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::RPlusTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case R_PLUS_PLUS_TREE:
+      {
+        RSWrapper<tree::RPlusPlusTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::RPlusPlusTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case VP_TREE:
+      {
+        RSWrapper<tree::VPTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::VPTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case RP_TREE:
+      {
+        RSWrapper<tree::RPTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::RPTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+
+    case MAX_RP_TREE:
+      {
+        RSWrapper<tree::MaxRPTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::MaxRPTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case UB_TREE:
+      {
+        RSWrapper<tree::UBTree>& typedSearch =
+            dynamic_cast<RSWrapper<tree::UBTree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+    case OCTREE:
+      {
+        LeafSizeRSWrapper<tree::Octree>& typedSearch =
+            dynamic_cast<LeafSizeRSWrapper<tree::Octree>&>(*rSearch);
+        ar(CEREAL_NVP(typedSearch));
+        break;
+      }
+  }
 }
 
 } // namespace range

From c83c6421cf37c74118183e7231d0b00e0faef685 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 10 Jan 2021 12:22:29 -0500
Subject: [PATCH 056/253] Fix name of file in comment.

---
 src/mlpack/methods/range_search/rs_model.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/range_search/rs_model.cpp b/src/mlpack/methods/range_search/rs_model.cpp
index fdf3cd2128..807a347ee4 100644
--- a/src/mlpack/methods/range_search/rs_model.cpp
+++ b/src/mlpack/methods/range_search/rs_model.cpp
@@ -1,5 +1,5 @@
 /**
- * @file methods/range_search/rs_model_impl.hpp
+ * @file methods/range_search/rs_model.cpp
  * @author Ryan Curtin
  *
  * Implementation of serialize() and inline functions for RSModel.

From f216b9b3ef3ff259f0d6fdcf0759efae56d594bc Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 10 Jan 2021 13:05:14 -0500
Subject: [PATCH 057/253] Remove boost::visitor from KDEModel.

---
 src/mlpack/methods/kde/CMakeLists.txt     |   1 +
 src/mlpack/methods/kde/kde_model.cpp      | 312 ++++++++++
 src/mlpack/methods/kde/kde_model.hpp      | 464 +++++----------
 src/mlpack/methods/kde/kde_model_impl.hpp | 673 ++++------------------
 4 files changed, 572 insertions(+), 878 deletions(-)
 create mode 100644 src/mlpack/methods/kde/kde_model.cpp

diff --git a/src/mlpack/methods/kde/CMakeLists.txt b/src/mlpack/methods/kde/CMakeLists.txt
index 31dacaee43..81bee212e3 100644
--- a/src/mlpack/methods/kde/CMakeLists.txt
+++ b/src/mlpack/methods/kde/CMakeLists.txt
@@ -8,6 +8,7 @@ set(SOURCES
   kde_stat.hpp
   kde_model.hpp
   kde_model_impl.hpp
+  kde_model.cpp
 )
 
 # Add directory name to sources.
diff --git a/src/mlpack/methods/kde/kde_model.cpp b/src/mlpack/methods/kde/kde_model.cpp
new file mode 100644
index 0000000000..552f1b4058
--- /dev/null
+++ b/src/mlpack/methods/kde/kde_model.cpp
@@ -0,0 +1,312 @@
+/**
+ * @file methods/kde/kde_model.cpp
+ * @author Roberto Hueso
+ *
+ * Implementation of KDE Model.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include "kde_model.hpp"
+
+namespace mlpack {
+namespace kde {
+
+//! Initialize the KDEModel with the given parameters.
+KDEModel::KDEModel(const double bandwidth,
+                   const double relError,
+                   const double absError,
+                   const KernelTypes kernelType,
+                   const TreeTypes treeType,
+                   const bool monteCarlo,
+                   const double mcProb,
+                   const size_t initialSampleSize,
+                   const double mcEntryCoef,
+                   const double mcBreakCoef) :
+    bandwidth(bandwidth),
+    relError(relError),
+    absError(absError),
+    kernelType(kernelType),
+    treeType(treeType),
+    monteCarlo(monteCarlo),
+    mcProb(mcProb),
+    initialSampleSize(initialSampleSize),
+    mcEntryCoef(mcEntryCoef),
+    mcBreakCoef(mcBreakCoef),
+    kdeModel(NULL)
+{
+  // Nothing to do.
+}
+
+// Copy constructor.
+KDEModel::KDEModel(const KDEModel& other) :
+    bandwidth(other.bandwidth),
+    relError(other.relError),
+    absError(other.absError),
+    kernelType(other.kernelType),
+    treeType(other.treeType),
+    monteCarlo(other.monteCarlo),
+    mcProb(other.mcProb),
+    initialSampleSize(other.initialSampleSize),
+    mcEntryCoef(other.mcEntryCoef),
+    mcBreakCoef(other.mcBreakCoef),
+    kdeModel(other.kdeModel->Clone())
+{
+  // Nothing to do.
+}
+
+// Move constructor.
+KDEModel::KDEModel(KDEModel&& other) :
+    bandwidth(other.bandwidth),
+    relError(other.relError),
+    absError(other.absError),
+    kernelType(other.kernelType),
+    treeType(other.treeType),
+    monteCarlo(other.monteCarlo),
+    mcProb(other.mcProb),
+    initialSampleSize(other.initialSampleSize),
+    mcEntryCoef(other.mcEntryCoef),
+    mcBreakCoef(other.mcBreakCoef),
+    kdeModel(std::move(other.kdeModel))
+{
+  // Reset other model.
+  other.bandwidth = 1.0;
+  other.relError = KDEDefaultParams::relError;
+  other.absError = KDEDefaultParams::absError;
+  other.kernelType = KernelTypes::GAUSSIAN_KERNEL;
+  other.treeType = TreeTypes::KD_TREE;
+  other.monteCarlo = KDEDefaultParams::monteCarlo;
+  other.mcProb = KDEDefaultParams::mcProb;
+  other.initialSampleSize = KDEDefaultParams::initialSampleSize;
+  other.mcEntryCoef = KDEDefaultParams::mcEntryCoef;
+  other.mcBreakCoef = KDEDefaultParams::mcBreakCoef;
+}
+
+KDEModel& KDEModel::operator=(const KDEModel& other)
+{
+  if (this != &other)
+  {
+    delete kdeModel;
+
+    bandwidth = other.bandwidth;
+    relError = other.relError;
+    absError = other.absError;
+    kernelType = other.kernelType;
+    treeType = other.treeType;
+    monteCarlo = other.monteCarlo;
+    mcProb = other.mcProb;
+    initialSampleSize = other.initialSampleSize;
+    mcEntryCoef = other.mcEntryCoef;
+    mcBreakCoef = other.mcBreakCoef;
+    kdeModel = other.kdeModel->Clone();
+  }
+
+  return *this;
+}
+
+KDEModel& KDEModel::operator=(KDEModel&& other)
+{
+  if (this != &other)
+  {
+    delete kdeModel;
+
+    bandwidth = other.bandwidth;
+    relError = other.relError;
+    absError = other.absError;
+    kernelType = other.kernelType;
+    treeType = other.treeType;
+    monteCarlo = other.monteCarlo;
+    mcProb = other.mcProb;
+    initialSampleSize = other.initialSampleSize;
+    mcEntryCoef = other.mcEntryCoef;
+    mcBreakCoef = other.mcBreakCoef;
+    kdeModel = std::move(other.kdeModel);
+
+    // Reset other model.
+    other.bandwidth = 1.0;
+    other.relError = KDEDefaultParams::relError;
+    other.absError = KDEDefaultParams::absError;
+    other.kernelType = KernelTypes::GAUSSIAN_KERNEL;
+    other.treeType = TreeTypes::KD_TREE;
+    other.monteCarlo = KDEDefaultParams::monteCarlo;
+    other.mcProb = KDEDefaultParams::mcProb;
+    other.initialSampleSize = KDEDefaultParams::initialSampleSize;
+    other.mcEntryCoef = KDEDefaultParams::mcEntryCoef;
+    other.mcBreakCoef = KDEDefaultParams::mcBreakCoef;
+  }
+
+  return *this;
+}
+
+// Clean memory.
+KDEModel::~KDEModel()
+{
+  delete kdeModel;
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeMatType,
+                  typename TreeStatType> class TreeType>
+KDEWrapperBase* BuildModelHelper(const KDEModel::KernelTypes kernelType,
+                                 const double relError,
+                                 const double absError,
+                                 const double bandwidth)
+{
+  switch (kernelType)
+  {
+    case KDEModel::GAUSSIAN_KERNEL:
+      return new KDEWrapper<kernel::GaussianKernel, TreeType>(
+          relError, absError, kernel::GaussianKernel(bandwidth));
+
+    case KDEModel::EPANECHNIKOV_KERNEL:
+      return new KDEWrapper<kernel::EpanechnikovKernel, TreeType>(
+          relError, absError, kernel::EpanechnikovKernel(bandwidth));
+
+    case KDEModel::LAPLACIAN_KERNEL:
+      return new KDEWrapper<kernel::LaplacianKernel, TreeType>(
+          relError, absError, kernel::LaplacianKernel(bandwidth));
+
+    case KDEModel::SPHERICAL_KERNEL:
+      return new KDEWrapper<kernel::SphericalKernel, TreeType>(
+          relError, absError, kernel::SphericalKernel(bandwidth));
+
+    case KDEModel::TRIANGULAR_KERNEL:
+      return new KDEWrapper<kernel::TriangularKernel, TreeType>(
+          relError, absError, kernel::TriangularKernel(bandwidth));
+  }
+
+  // This should never happen.
+  return NULL;
+}
+
+void KDEModel::BuildModel(arma::mat&& referenceSet)
+{
+  // Clean memory, if necessary.
+  delete kdeModel;
+
+  // Build the actual model.
+  switch (treeType)
+  {
+    case KD_TREE:
+      kdeModel = BuildModelHelper<tree::KDTree>(kernelType, relError, absError,
+          bandwidth);
+      break;
+
+    case BALL_TREE:
+      kdeModel = BuildModelHelper<tree::BallTree>(kernelType, relError,
+          absError, bandwidth);
+      break;
+
+    case COVER_TREE:
+      kdeModel = BuildModelHelper<tree::StandardCoverTree>(kernelType, relError,
+          absError, bandwidth);
+      break;
+
+    case OCTREE:
+      kdeModel = BuildModelHelper<tree::Octree>(kernelType, relError, absError,
+          bandwidth);
+      break;
+
+    case R_TREE:
+      kdeModel = BuildModelHelper<tree::RTree>(kernelType, relError, absError,
+          bandwidth);
+      break;
+  }
+
+  // Set whether to use Monte Carlo estimations or not.
+  kdeModel->MonteCarlo() = monteCarlo;
+
+  // Set Monte Carlo probability.
+  kdeModel->MCProb(mcProb);
+
+  // Set Monte Carlo initial sample size.
+  kdeModel->MCInitialSampleSize() = initialSampleSize;
+
+  // Set Monte Carlo entry coefficient.
+  kdeModel->MCEntryCoef(mcEntryCoef);
+
+  // Set Monte Carlo break coefficient.
+  kdeModel->MCBreakCoef(mcBreakCoef);
+
+  // Train the model.
+  kdeModel->Train(std::move(referenceSet));
+}
+
+// Perform bichromatic evaluation.
+void KDEModel::Evaluate(arma::mat&& querySet, arma::vec& estimates)
+{
+  kdeModel->Evaluate(std::move(querySet), estimates);
+}
+
+// Perform monochromatic evaluation.
+void KDEModel::Evaluate(arma::vec& estimates)
+{
+  kdeModel->Evaluate(estimates);
+}
+
+// Clean memory.
+void KDEModel::CleanMemory()
+{
+  delete kdeModel;
+}
+
+// Modify model kernel bandwidth.
+void KDEModel::Bandwidth(const double newBandwidth)
+{
+  bandwidth = newBandwidth;
+  kdeModel->Bandwidth(bandwidth);
+}
+
+// Modify model relative error tolerance.
+void KDEModel::RelativeError(const double newRelError)
+{
+  relError = newRelError;
+  kdeModel->RelativeError(relError);
+}
+
+// Modify model absolute error tolerance.
+void KDEModel::AbsoluteError(const double newAbsError)
+{
+  absError = newAbsError;
+  kdeModel->AbsoluteError(absError);
+}
+
+// Modify whether Monte Carlo estimations will be used.
+void KDEModel::MonteCarlo(const bool newMonteCarlo)
+{
+  monteCarlo = newMonteCarlo;
+  kdeModel->MonteCarlo() = monteCarlo;
+}
+
+// Modify model Monte Carlo probability.
+void KDEModel::MCProbability(const double newMCProb)
+{
+  mcProb = newMCProb;
+  kdeModel->MCProb(mcProb);
+}
+
+// Modify model Monte Carlo initial sample size.
+void KDEModel::MCInitialSampleSize(const size_t newSampleSize)
+{
+  initialSampleSize = newSampleSize;
+  kdeModel->MCInitialSampleSize() = initialSampleSize;
+}
+
+// Modify model Monte Carlo entry coefficient.
+void KDEModel::MCEntryCoefficient(const double newEntryCoef)
+{
+  mcEntryCoef = newEntryCoef;
+  kdeModel->MCEntryCoef(mcEntryCoef);
+}
+
+// Modify model Monte Carlo break coefficient.
+void KDEModel::MCBreakCoefficient(const double newBreakCoef)
+{
+  mcBreakCoef = newBreakCoef;
+  kdeModel->MCBreakCoef(mcBreakCoef);
+}
+
+} // namespace kde
+} // namespace mlpack
diff --git a/src/mlpack/methods/kde/kde_model.hpp b/src/mlpack/methods/kde/kde_model.hpp
index 220213ba5e..c2f93ba181 100644
--- a/src/mlpack/methods/kde/kde_model.hpp
+++ b/src/mlpack/methods/kde/kde_model.hpp
@@ -22,28 +22,11 @@
 #include <mlpack/core.hpp>
 
 // Remaining includes.
-#include <boost/variant.hpp>
 #include "kde.hpp"
 
 namespace mlpack {
 namespace kde {
 
-//! Alias template.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-using KDEType = KDE<KernelType,
-                    metric::EuclideanDistance,
-                    arma::mat,
-                    TreeType,
-                    TreeType<metric::EuclideanDistance,
-                             kde::KDEStat,
-                             arma::mat>::template DualTreeTraverser,
-                    TreeType<metric::EuclideanDistance,
-                             kde::KDEStat,
-                             arma::mat>::template SingleTreeTraverser>;
-
 /**
  * KernelNormalizer holds a set of methods to normalize estimations applying
  * in each case the appropiate kernel normalizer function.
@@ -81,284 +64,168 @@ class KernelNormalizer
 };
 
 /**
- * DualMonoKDE computes a Kernel Density Estimation on the given KDEType.
- * It performs a monochromatic KDE.
+ * KDEWrapperBase is a base wrapper class for holding all KDE types supported by
+ * KDEModel.  All KDE type wrappers inheirt from this class, allowing a simple
+ * interface via inheritance for all the different types we want to support.
  */
-class DualMonoKDE : public boost::static_visitor<void>
+class KDEWrapperBase
 {
- private:
-  //! Vector to store the KDE results.
-  arma::vec& estimations;
-
  public:
-  //! Alias template necessary for Visual C++ compiler.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using KDETypeT = KDEType<KernelType, TreeType>;
+  //! Create the KDEWrapperBase object.  The base class does not hold anything,
+  //! so this constructor does nothing.
+  KDEWrapperBase() { }
 
-  //! Default DualMonoKDE on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDETypeT<KernelType, TreeType>* kde) const;
+  //! Create a new KDEWrapperBase that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual KDEWrapperBase* Clone() const = 0;
 
-  // TODO Implement specific cases where a leaf size can be selected.
+  //! Destruct the KDEWrapperBase (nothing to do).
+  virtual ~KDEWrapperBase() { }
 
-  //! DualMonoKDE constructor.
-  DualMonoKDE(arma::vec& estimations);
+  //! Modify the bandwidth of the kernel.
+  virtual void Bandwidth(const double bw) = 0;
+
+  //! Modify the relative error tolerance.
+  virtual void RelativeError(const double relError) = 0;
+
+  //! Modify the absolute error tolerance.
+  virtual void AbsoluteError(const double absError) = 0;
+
+  //! Get whether Monte Carlo search is being used.
+  virtual bool MonteCarlo() const = 0;
+  //! Modify whether Monte Carlo search is being used.
+  virtual bool& MonteCarlo() = 0;
+
+  //! Modify the Monte Carlo probability.
+  virtual void MCProb(const double mcProb) = 0;
+
+  //! Get the Monte Carlo sample size.
+  virtual size_t MCInitialSampleSize() const = 0;
+  //! Modify the Monte Carlo sample size.
+  virtual size_t& MCInitialSampleSize() = 0;
+
+  //! Modify the Monte Carlo entry coefficient.
+  virtual void MCEntryCoef(const double entryCoef) = 0;
+
+  //! Modify the Monte Carlo break coefficient.
+  virtual void MCBreakCoef(const double breakCoef) = 0;
+
+  //! Get the search mode.
+  virtual KDEMode Mode() const = 0;
+  //! Modify the search mode.
+  virtual KDEMode& Mode() = 0;
+
+  //! Train the model (build the tree).
+  virtual void Train(arma::mat&& referenceSet) = 0;
+
+  //! Perform bichromatic KDE (i.e. KDE with a separate query set).
+  virtual void Evaluate(arma::mat&& querySet,
+                        arma::vec& estimates) = 0;
+
+  //! Perform monochromatic KDE (i.e. with the reference set as the query set).
+  virtual void Evaluate(arma::vec& estimates) = 0;
 };
 
 /**
- * DualBiKDE computes a Kernel Density Estimation on the given KDEType.
- * It performs a bichromatic KDE.
+ * KDEWrapper is a wrapper class for all KDE types supported by KDEModel.  It
+ * can be extended with new child classes if new functionality for certain types
+ * is needed.
  */
-class DualBiKDE : public boost::static_visitor<void>
+template<typename KernelType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+class KDEWrapper : public KDEWrapperBase
 {
- private:
-  //! Query set dimensionality.
-  const size_t dimension;
-
-  //! The query set for the KDE.
-  const arma::mat& querySet;
-
-  //! Vector to store the KDE results.
-  arma::vec& estimations;
-
  public:
-  //! Alias template necessary for Visual C++ compiler.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  using KDETypeT = KDEType<KernelType, TreeType>;
+  //! Create the KDEWrapper object, initializing the internally-held KDE object.
+  KDEWrapper(const double relError,
+             const double absError,
+             const KernelType& kernel) :
+      kde(relError, absError, kernel)
+  {
+    // Nothing left to do.
+  }
 
-  //! Default DualBiKDE on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDETypeT<KernelType, TreeType>* kde) const;
+  //! Create a new KDEWrapper that is the same as this one.  This function
+  //! will properly handle polymorphism.
+  virtual KDEWrapper* Clone() const { return new KDEWrapper(*this); }
 
-  // TODO Implement specific cases where a leaf size can be selected.
+  //! Destruct the KDEWrapper (nothing to do).
+  virtual ~KDEWrapper() { }
 
-  //! DualBiKDE constructor. Takes ownership of the given querySet.
-  DualBiKDE(arma::mat&& querySet, arma::vec& estimations);
+  //! Modify the bandwidth of the kernel.
+  virtual void Bandwidth(const double bw) { kde.Kernel() = KernelType(bw); }
+
+  //! Modify the relative error tolerance.
+  virtual void RelativeError(const double eps) { kde.RelativeError(eps); }
+
+  //! Modify the absolute error tolerance.
+  virtual void AbsoluteError(const double eps) { kde.AbsoluteError(eps); }
+
+  //! Get whether Monte Carlo search is being used.
+  virtual bool MonteCarlo() const { return kde.MonteCarlo(); }
+  //! Modify whether Monte Carlo search is being used.
+  virtual bool& MonteCarlo() { return kde.MonteCarlo(); }
+
+  //! Modify the Monte Carlo probability.
+  virtual void MCProb(const double mcProb) { kde.MCProb(mcProb); }
+
+  //! Get the Monte Carlo sample size.
+  virtual size_t MCInitialSampleSize() const
+  {
+    return kde.MCInitialSampleSize();
+  }
+  //! Modify the Monte Carlo sample size.
+  virtual size_t& MCInitialSampleSize()
+  {
+    return kde.MCInitialSampleSize();
+  }
+
+  //! Modify the Monte Carlo entry coefficient.
+  virtual void MCEntryCoef(const double e) { kde.MCEntryCoef(e); }
+
+  //! Modify the Monte Carlo break coefficient.
+  virtual void MCBreakCoef(const double b) { kde.MCBreakCoef(b); }
+
+  //! Get the search mode.
+  virtual KDEMode Mode() const { return kde.Mode(); }
+  //! Modify the search mode.
+  virtual KDEMode& Mode() { return kde.Mode(); }
+
+  //! Train the model (build the tree).
+  virtual void Train(arma::mat&& referenceSet);
+
+  //! Perform bichromatic KDE (i.e. KDE with a separate query set).
+  virtual void Evaluate(arma::mat&& querySet,
+                        arma::vec& estimates);
+
+  //! Perform monochromatic KDE (i.e. with the reference set as the query set).
+  virtual void Evaluate(arma::vec& estimates);
+
+  //! Serialize the KDE model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(kde));
+  }
+
+ protected:
+  typedef KDE<KernelType,
+              metric::EuclideanDistance,
+              arma::mat,
+              TreeType> KDEType;
+
+  //! The instantiated KDE object that we are wrapping.
+  KDEType kde;
 };
 
 /**
- * TrainVisitor trains a given KDEType using a reference set.
+ * The KDEModel provides an abstraction for the KDE class, abstracting away the
+ * KernelType and TreeType parameters and allowing those to be specified at
+ * runtime.  This class is written for the sake of the `kde` binding, but it is
+ * not necessarily restricted to that usage.
  */
-class TrainVisitor : public boost::static_visitor<void>
-{
- private:
-  //! The reference set used for training.
-  arma::mat&& referenceSet;
-
- public:
-  //! Default TrainVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  // TODO Implement specific cases where a leaf size can be selected.
-
-  //! TrainVisitor constructor. Takes ownership of the given referenceSet.
-  TrainVisitor(arma::mat&& referenceSet);
-};
-
-/**
- * BandwidthVisitor modifies the bandwidth of a KDEType kernel.
- */
-class BandwidthVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Relative error tolerance.
-  const double bandwidth;
-
- public:
-  //! Default BandwidthVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! BandwidthVisitor constructor.
-  BandwidthVisitor(const double bandwidth);
-};
-
-/**
- * RelErrorVisitor modifies relative error tolerance for a KDEType.
- */
-class RelErrorVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Relative error tolerance.
-  const double relError;
-
- public:
-  //! Default RelErrorVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! RelErrorVisitor constructor.
-  RelErrorVisitor(const double relError);
-};
-
-/**
- * AbsErrorVisitor modifies absolute error tolerance for a KDEType.
- */
-class AbsErrorVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Absolute error tolerance.
-  const double absError;
-
- public:
-  //! Default AbsErrorVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! AbsErrorVisitor constructor.
-  AbsErrorVisitor(const double absError);
-};
-
-/**
- * MonteCarloVisitor activates or deactivates Monte Carlo for a given KDEType.
- */
-class MonteCarloVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Whether to use Monte Carlo estimations or not.
-  const bool monteCarlo;
-
- public:
-  //! Default MonteCarloVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! MonteCarloVisitor constructor.
-  MonteCarloVisitor(const bool monteCarlo);
-};
-
-/**
- * MCProbabilityVisitor sets the Monte Carlo probability for a given KDEType.
- */
-class MCProbabilityVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Monte Carlo probability.
-  const double probability;
-
- public:
-  //! Default MCProbabilityVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! MCProbabilityVisitor constructor.
-  MCProbabilityVisitor(const double probability);
-};
-
-/**
- * MCSampleSizeVisitor sets the Monte Carlo intial sample size for a given
- * KDEType.
- */
-class MCSampleSizeVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Monte Carlo sample size.
-  const size_t sampleSize;
-
- public:
-  //! Default MCSampleSizeVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! MCSampleSizeVisitor constructor.
-  MCSampleSizeVisitor(const size_t sampleSize);
-};
-
-/**
- * MCEntryCoefVisitor sets the Monte Carlo entry coefficient.
- */
-class MCEntryCoefVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Monte Carlo entry coefficient.
-  const double entryCoef;
-
- public:
-  //! Default MCEntryCoefVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! MCEntryCoefVisitor constructor.
-  MCEntryCoefVisitor(const double entryCoef);
-};
-
-/**
- * MCBreakCoefVisitor sets the Monte Carlo break coefficient.
- */
-class MCBreakCoefVisitor : public boost::static_visitor<void>
-{
- private:
-  //! Monte Carlo break coefficient.
-  const double breakCoef;
-
- public:
-  //! Default MCBreakCoefVisitor on some KDEType.
-  template<typename KernelType,
-           template<typename TreeMetricType,
-                    typename TreeStatType,
-                    typename TreeMatType> class TreeType>
-  void operator()(KDEType<KernelType, TreeType>* kde) const;
-
-  //! MCBreakCoefVisitor constructor.
-  MCBreakCoefVisitor(const double breakCoef);
-};
-
-/**
- * ModeVisitor exposes the Mode() method of the KDEType.
- */
-class ModeVisitor : public boost::static_visitor<KDEMode&>
-{
- public:
-  //! Return mode of KDEType instance.
-  template<typename KDEType>
-  KDEMode& operator()(KDEType* kde) const;
-};
-
-class DeleteVisitor : public boost::static_visitor<void>
-{
- public:
-  //! Delete KDEType instance.
-  template<typename KDEType>
-  void operator()(KDEType* kde) const;
-};
-
 class KDEModel
 {
  public:
@@ -413,34 +280,10 @@ class KDEModel
   double mcBreakCoef;
 
   /**
-   * kdeModel holds an instance of each possible combination of KernelType and
-   * TreeType. It is initialized using BuildModel.
+   * kdeModel holds whatever KDE type we are using.  It is initialized using the
+   * `BuildModel()` method.
    */
-  boost::variant<KDEType<kernel::GaussianKernel, tree::KDTree>*,
-                 KDEType<kernel::GaussianKernel, tree::BallTree>*,
-                 KDEType<kernel::GaussianKernel, tree::StandardCoverTree>*,
-                 KDEType<kernel::GaussianKernel, tree::Octree>*,
-                 KDEType<kernel::GaussianKernel, tree::RTree>*,
-                 KDEType<kernel::EpanechnikovKernel, tree::KDTree>*,
-                 KDEType<kernel::EpanechnikovKernel, tree::BallTree>*,
-                 KDEType<kernel::EpanechnikovKernel, tree::StandardCoverTree>*,
-                 KDEType<kernel::EpanechnikovKernel, tree::Octree>*,
-                 KDEType<kernel::EpanechnikovKernel, tree::RTree>*,
-                 KDEType<kernel::LaplacianKernel, tree::KDTree>*,
-                 KDEType<kernel::LaplacianKernel, tree::BallTree>*,
-                 KDEType<kernel::LaplacianKernel, tree::StandardCoverTree>*,
-                 KDEType<kernel::LaplacianKernel, tree::Octree>*,
-                 KDEType<kernel::LaplacianKernel, tree::RTree>*,
-                 KDEType<kernel::SphericalKernel, tree::KDTree>*,
-                 KDEType<kernel::SphericalKernel, tree::BallTree>*,
-                 KDEType<kernel::SphericalKernel, tree::StandardCoverTree>*,
-                 KDEType<kernel::SphericalKernel, tree::Octree>*,
-                 KDEType<kernel::SphericalKernel, tree::RTree>*,
-                 KDEType<kernel::TriangularKernel, tree::KDTree>*,
-                 KDEType<kernel::TriangularKernel, tree::BallTree>*,
-                 KDEType<kernel::TriangularKernel, tree::StandardCoverTree>*,
-                 KDEType<kernel::TriangularKernel, tree::Octree>*,
-                 KDEType<kernel::TriangularKernel, tree::RTree>*> kdeModel;
+  KDEWrapperBase* kdeModel;
 
  public:
   /**
@@ -487,11 +330,16 @@ class KDEModel
   /**
    * Copy the given model.
    *
-   * Use std::move if the object to copy is no longer needed.
-   *
    * @param other KDEModel to copy.
    */
-  KDEModel& operator=(KDEModel other);
+  KDEModel& operator=(const KDEModel& other);
+
+  /**
+   * Take ownership of the contents of the given model.
+   *
+   * @param other KDEModel to take ownership of.
+   */
+  KDEModel& operator=(KDEModel&& other);
 
   //! Destroy the KDEModel object.
   ~KDEModel();
@@ -561,10 +409,10 @@ class KDEModel
   void MCBreakCoefficient(const double newBreakCoef);
 
   //! Get the mode of the model.
-  KDEMode Mode() const;
+  KDEMode Mode() const { return kdeModel->Mode(); }
 
   //! Modify the mode of the model.
-  KDEMode& Mode();
+  KDEMode& Mode() { return kdeModel->Mode(); }
 
   /**
    * Build the KDE model with the given parameters and then trains it with the
diff --git a/src/mlpack/methods/kde/kde_model_impl.hpp b/src/mlpack/methods/kde/kde_model_impl.hpp
index 4b59e7657a..bc00f1d50b 100644
--- a/src/mlpack/methods/kde/kde_model_impl.hpp
+++ b/src/mlpack/methods/kde/kde_model_impl.hpp
@@ -18,521 +18,96 @@
 namespace mlpack {
 namespace kde {
 
-//! Initialize the KDEModel with the given parameters.
-inline KDEModel::KDEModel(const double bandwidth,
-                          const double relError,
-                          const double absError,
-                          const KernelTypes kernelType,
-                          const TreeTypes treeType,
-                          const bool monteCarlo,
-                          const double mcProb,
-                          const size_t initialSampleSize,
-                          const double mcEntryCoef,
-                          const double mcBreakCoef) :
-  bandwidth(bandwidth),
-  relError(relError),
-  absError(absError),
-  kernelType(kernelType),
-  treeType(treeType),
-  monteCarlo(monteCarlo),
-  mcProb(mcProb),
-  initialSampleSize(initialSampleSize),
-  mcEntryCoef(mcEntryCoef),
-  mcBreakCoef(mcBreakCoef)
-{
-  // Nothing to do.
-}
-
-// Copy constructor.
-inline KDEModel::KDEModel(const KDEModel& other) :
-  bandwidth(other.bandwidth),
-  relError(other.relError),
-  absError(other.absError),
-  kernelType(other.kernelType),
-  treeType(other.treeType),
-  monteCarlo(other.monteCarlo),
-  mcProb(other.mcProb),
-  initialSampleSize(other.initialSampleSize),
-  mcEntryCoef(other.mcEntryCoef),
-  mcBreakCoef(other.mcBreakCoef)
-{
-  // Nothing to do.
-}
-
-// Move constructor.
-inline KDEModel::KDEModel(KDEModel&& other) :
-  bandwidth(other.bandwidth),
-  relError(other.relError),
-  absError(other.absError),
-  kernelType(other.kernelType),
-  treeType(other.treeType),
-  monteCarlo(other.monteCarlo),
-  mcProb(other.mcProb),
-  initialSampleSize(other.initialSampleSize),
-  mcEntryCoef(other.mcEntryCoef),
-  mcBreakCoef(other.mcBreakCoef),
-  kdeModel(std::move(other.kdeModel))
-{
-  // Reset other model.
-  other.bandwidth = 1.0;
-  other.relError = KDEDefaultParams::relError;
-  other.absError = KDEDefaultParams::absError;
-  other.kernelType = KernelTypes::GAUSSIAN_KERNEL;
-  other.treeType = TreeTypes::KD_TREE;
-  other.monteCarlo = KDEDefaultParams::monteCarlo;
-  other.mcProb = KDEDefaultParams::mcProb;
-  other.initialSampleSize = KDEDefaultParams::initialSampleSize;
-  other.mcEntryCoef = KDEDefaultParams::mcEntryCoef;
-  other.mcBreakCoef = KDEDefaultParams::mcBreakCoef;
-  other.kdeModel = decltype(other.kdeModel)();
-}
-
-inline KDEModel& KDEModel::operator=(KDEModel other)
-{
-  boost::apply_visitor(DeleteVisitor(), kdeModel);
-  bandwidth = other.bandwidth;
-  relError = other.relError;
-  absError = other.absError;
-  kernelType = other.kernelType;
-  treeType = other.treeType;
-  monteCarlo = other.monteCarlo;
-  mcProb = other.mcProb;
-  initialSampleSize = other.initialSampleSize;
-  mcEntryCoef = other.mcEntryCoef;
-  mcBreakCoef = other.mcBreakCoef;
-  kdeModel = std::move(other.kdeModel);
-  return *this;
-}
-
-// Clean memory.
-inline KDEModel::~KDEModel()
-{
-  boost::apply_visitor(DeleteVisitor(), kdeModel);
-}
-
-inline void KDEModel::BuildModel(arma::mat&& referenceSet)
-{
-  // Clean memory, if necessary.
-  boost::apply_visitor(DeleteVisitor(), kdeModel);
-
-  // Build the actual model.
-  if (kernelType == GAUSSIAN_KERNEL && treeType == KD_TREE)
-  {
-    kdeModel = new KDEType<kernel::GaussianKernel, tree::KDTree>
-        (relError, absError, kernel::GaussianKernel(bandwidth));
-  }
-  else if (kernelType == GAUSSIAN_KERNEL && treeType == BALL_TREE)
-  {
-    kdeModel = new KDEType<kernel::GaussianKernel, tree::BallTree>
-        (relError, absError, kernel::GaussianKernel(bandwidth));
-  }
-  else if (kernelType == GAUSSIAN_KERNEL && treeType == COVER_TREE)
-  {
-    kdeModel = new KDEType<kernel::GaussianKernel, tree::StandardCoverTree>
-        (relError, absError, kernel::GaussianKernel(bandwidth));
-  }
-  else if (kernelType == GAUSSIAN_KERNEL && treeType == OCTREE)
-  {
-    kdeModel = new KDEType<kernel::GaussianKernel, tree::Octree>
-        (relError, absError, kernel::GaussianKernel(bandwidth));
-  }
-  else if (kernelType == GAUSSIAN_KERNEL && treeType == R_TREE)
-  {
-    kdeModel = new KDEType<kernel::GaussianKernel, tree::RTree>
-        (relError, absError, kernel::GaussianKernel(bandwidth));
-  }
-  else if (kernelType == EPANECHNIKOV_KERNEL && treeType == KD_TREE)
-  {
-    kdeModel = new KDEType<kernel::EpanechnikovKernel, tree::KDTree>
-        (relError, absError, kernel::EpanechnikovKernel(bandwidth));
-  }
-  else if (kernelType == EPANECHNIKOV_KERNEL && treeType == BALL_TREE)
-  {
-    kdeModel = new KDEType<kernel::EpanechnikovKernel, tree::BallTree>
-        (relError, absError, kernel::EpanechnikovKernel(bandwidth));
-  }
-  else if (kernelType == EPANECHNIKOV_KERNEL && treeType == COVER_TREE)
-  {
-    kdeModel = new KDEType<kernel::EpanechnikovKernel, tree::StandardCoverTree>
-        (relError, absError, kernel::EpanechnikovKernel(bandwidth));
-  }
-  else if (kernelType == EPANECHNIKOV_KERNEL && treeType == OCTREE)
-  {
-    kdeModel = new KDEType<kernel::EpanechnikovKernel, tree::Octree>
-        (relError, absError, kernel::EpanechnikovKernel(bandwidth));
-  }
-  else if (kernelType == EPANECHNIKOV_KERNEL && treeType == R_TREE)
-  {
-    kdeModel = new KDEType<kernel::EpanechnikovKernel, tree::RTree>
-        (relError, absError, kernel::EpanechnikovKernel(bandwidth));
-  }
-  else if (kernelType == LAPLACIAN_KERNEL && treeType == KD_TREE)
-  {
-    kdeModel = new KDEType<kernel::LaplacianKernel, tree::KDTree>
-        (relError, absError, kernel::LaplacianKernel(bandwidth));
-  }
-  else if (kernelType == LAPLACIAN_KERNEL && treeType == BALL_TREE)
-  {
-    kdeModel = new KDEType<kernel::LaplacianKernel, tree::BallTree>
-        (relError, absError, kernel::LaplacianKernel(bandwidth));
-  }
-  else if (kernelType == LAPLACIAN_KERNEL && treeType == COVER_TREE)
-  {
-    kdeModel = new KDEType<kernel::LaplacianKernel, tree::StandardCoverTree>
-        (relError, absError, kernel::LaplacianKernel(bandwidth));
-  }
-  else if (kernelType == LAPLACIAN_KERNEL && treeType == OCTREE)
-  {
-    kdeModel = new KDEType<kernel::LaplacianKernel, tree::Octree>
-        (relError, absError, kernel::LaplacianKernel(bandwidth));
-  }
-  else if (kernelType == LAPLACIAN_KERNEL && treeType == R_TREE)
-  {
-    kdeModel = new KDEType<kernel::LaplacianKernel, tree::RTree>
-        (relError, absError, kernel::LaplacianKernel(bandwidth));
-  }
-  else if (kernelType == SPHERICAL_KERNEL && treeType == KD_TREE)
-  {
-    kdeModel = new KDEType<kernel::SphericalKernel, tree::KDTree>
-        (relError, absError, kernel::SphericalKernel(bandwidth));
-  }
-  else if (kernelType == SPHERICAL_KERNEL && treeType == BALL_TREE)
-  {
-    kdeModel = new KDEType<kernel::SphericalKernel, tree::BallTree>
-        (relError, absError, kernel::SphericalKernel(bandwidth));
-  }
-  else if (kernelType == SPHERICAL_KERNEL && treeType == COVER_TREE)
-  {
-    kdeModel = new KDEType<kernel::SphericalKernel, tree::StandardCoverTree>
-        (relError, absError, kernel::SphericalKernel(bandwidth));
-  }
-  else if (kernelType == SPHERICAL_KERNEL && treeType == OCTREE)
-  {
-    kdeModel = new KDEType<kernel::SphericalKernel, tree::Octree>
-        (relError, absError, kernel::SphericalKernel(bandwidth));
-  }
-  else if (kernelType == SPHERICAL_KERNEL && treeType == R_TREE)
-  {
-    kdeModel = new KDEType<kernel::SphericalKernel, tree::RTree>
-        (relError, absError, kernel::SphericalKernel(bandwidth));
-  }
-  else if (kernelType == TRIANGULAR_KERNEL && treeType == KD_TREE)
-  {
-    kdeModel = new KDEType<kernel::TriangularKernel, tree::KDTree>
-        (relError, absError, kernel::TriangularKernel(bandwidth));
-  }
-  else if (kernelType == TRIANGULAR_KERNEL && treeType == BALL_TREE)
-  {
-    kdeModel = new KDEType<kernel::TriangularKernel, tree::BallTree>
-        (relError, absError, kernel::TriangularKernel(bandwidth));
-  }
-  else if (kernelType == TRIANGULAR_KERNEL && treeType == COVER_TREE)
-  {
-    kdeModel = new KDEType<kernel::TriangularKernel, tree::StandardCoverTree>
-        (relError, absError, kernel::TriangularKernel(bandwidth));
-  }
-  else if (kernelType == TRIANGULAR_KERNEL && treeType == OCTREE)
-  {
-    kdeModel = new KDEType<kernel::TriangularKernel, tree::Octree>
-        (relError, absError, kernel::TriangularKernel(bandwidth));
-  }
-  else if (kernelType == TRIANGULAR_KERNEL && treeType == R_TREE)
-  {
-    kdeModel = new KDEType<kernel::TriangularKernel, tree::RTree>
-        (relError, absError, kernel::TriangularKernel(bandwidth));
-  }
-
-  // Set whether to use Monte Carlo estimations or not.
-  MonteCarloVisitor MCVisitor(monteCarlo);
-  boost::apply_visitor(MCVisitor, kdeModel);
-
-  // Set Monte Carlo probability.
-  MCProbabilityVisitor probabilityVisitor(mcProb);
-  boost::apply_visitor(probabilityVisitor, kdeModel);
-
-  // Set Monte Carlo initial sample size.
-  MCSampleSizeVisitor sampleSizeVisitor(initialSampleSize);
-  boost::apply_visitor(sampleSizeVisitor, kdeModel);
-
-  // Set Monte Carlo entry coefficient.
-  MCEntryCoefVisitor entryCoefficientVisitor(mcEntryCoef);
-  boost::apply_visitor(entryCoefficientVisitor, kdeModel);
-
-  // Set Monte Carlo break coefficient.
-  MCBreakCoefVisitor breakCoefficientVisitor(mcBreakCoef);
-  boost::apply_visitor(breakCoefficientVisitor, kdeModel);
-
-  // Train the model.
-  TrainVisitor train(std::move(referenceSet));
-  boost::apply_visitor(train, kdeModel);
-}
-
-// Perform bichromatic evaluation.
-inline void KDEModel::Evaluate(arma::mat&& querySet, arma::vec& estimations)
-{
-  Log::Info << "Evaluating KDE..." << std::endl;
-  DualBiKDE eval(std::move(querySet), estimations);
-  boost::apply_visitor(eval, kdeModel);
-}
-
-// Perform monochromatic evaluation.
-inline void KDEModel::Evaluate(arma::vec& estimations)
-{
-  Log::Info << "Evaluating KDE..." << std::endl;
-  DualMonoKDE eval(estimations);
-  boost::apply_visitor(eval, kdeModel);
-}
-
-// Clean memory.
-inline void KDEModel::CleanMemory()
-{
-  boost::apply_visitor(DeleteVisitor(), kdeModel);
-}
-
-// Parameters for KDE evaluation.
-DualMonoKDE::DualMonoKDE(arma::vec& estimations):
-    estimations(estimations)
-{}
-
-// Default KDE evaluation.
+//! Train the model (build the tree).
 template<typename KernelType,
          template<typename TreeMetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
-void DualMonoKDE::operator()(KDETypeT<KernelType, TreeType>* kde) const
+void KDEWrapper<KernelType, TreeType>::Train(arma::mat&& referenceSet)
 {
-  if (kde)
+  kde.Train(std::move(referenceSet));
+}
+
+//! Perform bichromatic KDE (i.e. KDE with a separate query set).
+template<typename KernelType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void KDEWrapper<KernelType, TreeType>::Evaluate(arma::mat&& querySet,
+                                                arma::vec& estimates)
+{
+  const size_t dimension = querySet.n_rows;
+  kde.Evaluate(std::move(querySet), estimates);
+  KernelNormalizer::ApplyNormalizer<KernelType>(kde.Kernel(),
+                                                dimension,
+                                                estimates);
+}
+
+//! Perform monochromatic KDE (i.e. with the reference set as the query set).
+template<typename KernelType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+void KDEWrapper<KernelType, TreeType>::Evaluate(arma::vec& estimates)
+{
+  kde.Evaluate(estimates);
+  const size_t dimension = kde.ReferenceTree()->Dataset().n_rows;
+  KernelNormalizer::ApplyNormalizer<KernelType>(kde.Kernel(),
+                                                dimension,
+                                                estimates);
+}
+
+template<template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         typename Archive>
+void SerializationHelper(Archive& ar,
+                         KDEWrapperBase* kdeModel,
+                         const KDEModel::KernelTypes kernelType)
+{
+  switch (kernelType)
   {
-    kde->Evaluate(estimations);
-    const size_t dimension = (kde->ReferenceTree())->Dataset().n_rows;
-    KernelNormalizer::ApplyNormalizer<KernelType>(kde->Kernel(),
-                                                  dimension,
-                                                  estimations);
+    case KDEModel::GAUSSIAN_KERNEL:
+      {
+        KDEWrapper<kernel::GaussianKernel, TreeType>& typedModel =
+            dynamic_cast<KDEWrapper<kernel::GaussianKernel,
+                                    TreeType>&>(*kdeModel);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+    case KDEModel::EPANECHNIKOV_KERNEL:
+      {
+        KDEWrapper<kernel::EpanechnikovKernel, TreeType>& typedModel =
+            dynamic_cast<KDEWrapper<kernel::EpanechnikovKernel,
+                                    TreeType>&>(*kdeModel);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+    case KDEModel::LAPLACIAN_KERNEL:
+      {
+        KDEWrapper<kernel::LaplacianKernel, TreeType>& typedModel =
+            dynamic_cast<KDEWrapper<kernel::LaplacianKernel,
+                                    TreeType>&>(*kdeModel);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+    case KDEModel::SPHERICAL_KERNEL:
+      {
+        KDEWrapper<kernel::SphericalKernel, TreeType>& typedModel =
+            dynamic_cast<KDEWrapper<kernel::SphericalKernel,
+                                    TreeType>&>(*kdeModel);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+    case KDEModel::TRIANGULAR_KERNEL:
+      {
+        KDEWrapper<kernel::TriangularKernel, TreeType>& typedModel =
+            dynamic_cast<KDEWrapper<kernel::TriangularKernel,
+                                    TreeType>&>(*kdeModel);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
   }
-  else
-  {
-    throw std::runtime_error("no KDE model initialized");
-  }
-}
-
-// Parameters for KDE evaluation.
-DualBiKDE::DualBiKDE(arma::mat&& querySet, arma::vec& estimations):
-    dimension(querySet.n_rows),
-    querySet(std::move(querySet)),
-    estimations(estimations)
-{}
-
-// Default KDE evaluation.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void DualBiKDE::operator()(KDETypeT<KernelType, TreeType>* kde) const
-{
-  if (kde)
-  {
-    kde->Evaluate(std::move(querySet), estimations);
-    KernelNormalizer::ApplyNormalizer<KernelType>(kde->Kernel(),
-                                                  dimension,
-                                                  estimations);
-  }
-  else
-  {
-    throw std::runtime_error("no KDE model initialized");
-  }
-}
-
-// Parameters for Train.
-TrainVisitor::TrainVisitor(arma::mat&& referenceSet) :
-    referenceSet(std::move(referenceSet))
-{}
-
-// Default Train.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void TrainVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  Log::Info << "Training KDE model..." << std::endl;
-  if (kde)
-    kde->Train(std::move(referenceSet));
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Modify kernel bandwidth.
-BandwidthVisitor::BandwidthVisitor(const double bandwidth) :
-    bandwidth(bandwidth)
-{}
-
-// Default modify kernel bandwidth.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void BandwidthVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->Kernel() = KernelType(bandwidth);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Modify relative error tolerance.
-RelErrorVisitor::RelErrorVisitor(const double relError) :
-    relError(relError)
-{}
-
-// Default modify relative error tolerance.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void RelErrorVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->RelativeError(relError);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Modify absolute error tolerance.
-AbsErrorVisitor::AbsErrorVisitor(const double absError) :
-    absError(absError)
-{}
-
-// Default modify absolute error tolerance.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void AbsErrorVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->AbsoluteError(absError);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Activate or deactivate Monte Carlo.
-MonteCarloVisitor::MonteCarloVisitor(const bool monteCarlo) :
-    monteCarlo(monteCarlo)
-{}
-
-// Default activate or deactivate Monte Carlo.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void MonteCarloVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->MonteCarlo() = monteCarlo;
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Set Monte Carlo probability.
-MCProbabilityVisitor::MCProbabilityVisitor(const double probability) :
-    probability(probability)
-{}
-
-// Default probability for Monte Carlo.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void MCProbabilityVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->MCProb(probability);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Set Monte Carlo sample size.
-MCSampleSizeVisitor::MCSampleSizeVisitor(const size_t sampleSize) :
-    sampleSize(sampleSize)
-{}
-
-// Default sample size for Monte Carlo.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void MCSampleSizeVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->MCInitialSampleSize() = sampleSize;
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Set Monte Carlo entry coefficient.
-MCEntryCoefVisitor::MCEntryCoefVisitor(const double entryCoef) :
-    entryCoef(entryCoef)
-{}
-
-// Default entry coefficient for Monte Carlo.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void MCEntryCoefVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->MCEntryCoef(entryCoef);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Set Monte Carlo break coefficient.
-MCBreakCoefVisitor::MCBreakCoefVisitor(const double breakCoef) :
-    breakCoef(breakCoef)
-{}
-
-// Default break coefficient for Monte Carlo.
-template<typename KernelType,
-         template<typename TreeMetricType,
-                  typename TreeStatType,
-                  typename TreeMatType> class TreeType>
-void MCBreakCoefVisitor::operator()(KDEType<KernelType, TreeType>* kde) const
-{
-  if (kde)
-    kde->MCBreakCoef(breakCoef);
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Delete model.
-template<typename KDEType>
-void DeleteVisitor::operator()(KDEType* kde) const
-{
-  if (kde)
-    delete kde;
-}
-
-// Mode of model.
-template<typename KDEType>
-KDEMode& ModeVisitor::operator()(KDEType* kde) const
-{
-  if (kde)
-    return kde->Mode();
-  else
-    throw std::runtime_error("no KDE model initialized");
-}
-
-// Get mode of model.
-KDEMode KDEModel::Mode() const
-{
-  return boost::apply_visitor(ModeVisitor(), kdeModel);
-}
-
-// Modify mode of model.
-KDEMode& KDEModel::Mode()
-{
-  return boost::apply_visitor(ModeVisitor(), kdeModel);
 }
 
 // Serialize the model.
@@ -560,73 +135,31 @@ void KDEModel::serialize(Archive& ar, const uint32_t /* version */)
   }
 
   if (cereal::is_loading<Archive>())
-    boost::apply_visitor(DeleteVisitor(), kdeModel);
+    delete kdeModel;
 
-  ar(CEREAL_VARIANT_POINTER(kdeModel));
-}
+  // Avoid polymorphism in serialization by serializing directly by the type.
+  switch (treeType)
+  {
+    case KD_TREE:
+      SerializationHelper<tree::KDTree>(ar, kdeModel, kernelType);
+      break;
 
-// Modify model kernel bandwidth.
-void KDEModel::Bandwidth(const double newBandwidth)
-{
-  bandwidth = newBandwidth;
-  BandwidthVisitor bandwidthVisitor(newBandwidth);
-  boost::apply_visitor(bandwidthVisitor, kdeModel);
-}
+    case BALL_TREE:
+      SerializationHelper<tree::BallTree>(ar, kdeModel, kernelType);
+      break;
 
-// Modify model relative error tolerance.
-void KDEModel::RelativeError(const double newRelError)
-{
-  relError = newRelError;
-  RelErrorVisitor relErrorVisitor(newRelError);
-  boost::apply_visitor(relErrorVisitor, kdeModel);
-}
+    case COVER_TREE:
+      SerializationHelper<tree::StandardCoverTree>(ar, kdeModel, kernelType);
+      break;
 
-// Modify model absolute error tolerance.
-void KDEModel::AbsoluteError(const double newAbsError)
-{
-  absError = newAbsError;
-  AbsErrorVisitor absErrorVisitor(newAbsError);
-  boost::apply_visitor(absErrorVisitor, kdeModel);
-}
+    case OCTREE:
+      SerializationHelper<tree::Octree>(ar, kdeModel, kernelType);
+      break;
 
-// Modify whether Monte Carlo estimations will be used.
-void KDEModel::MonteCarlo(const bool newMonteCarlo)
-{
-  monteCarlo = newMonteCarlo;
-  MonteCarloVisitor monteCarloVisitor(newMonteCarlo);
-  boost::apply_visitor(monteCarloVisitor, kdeModel);
-}
-
-// Modify model Monte Carlo probability.
-void KDEModel::MCProbability(const double newMCProb)
-{
-  mcProb = newMCProb;
-  MCProbabilityVisitor mcProbVisitor(newMCProb);
-  boost::apply_visitor(mcProbVisitor, kdeModel);
-}
-
-// Modify model Monte Carlo initial sample size.
-void KDEModel::MCInitialSampleSize(const size_t newSampleSize)
-{
-  initialSampleSize = newSampleSize;
-  MCSampleSizeVisitor mcSampleSizeVisitor(newSampleSize);
-  boost::apply_visitor(mcSampleSizeVisitor, kdeModel);
-}
-
-// Modify model Monte Carlo entry coefficient.
-void KDEModel::MCEntryCoefficient(const double newEntryCoef)
-{
-  mcEntryCoef = newEntryCoef;
-  MCEntryCoefVisitor mcEntryCoefVisitor(newEntryCoef);
-  boost::apply_visitor(mcEntryCoefVisitor, kdeModel);
-}
-
-// Modify model Monte Carlo break coefficient.
-void KDEModel::MCBreakCoefficient(const double newBreakCoef)
-{
-  mcBreakCoef = newBreakCoef;
-  MCBreakCoefVisitor mcBreakCoefVisitor(newBreakCoef);
-  boost::apply_visitor(mcBreakCoefVisitor, kdeModel);
+    case R_TREE:
+      SerializationHelper<tree::RTree>(ar, kdeModel, kernelType);
+      break;
+  }
 }
 
 } // namespace kde

From 47c340bf1fe511ec5f900057ce92eacb6f4949cd Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 09:44:44 -0500
Subject: [PATCH 058/253] Fix serialization initialization.

---
 src/mlpack/methods/kde/kde_model.cpp          | 33 +++++++-----
 src/mlpack/methods/kde/kde_model.hpp          |  5 ++
 src/mlpack/methods/kde/kde_model_impl.hpp     |  2 +-
 src/mlpack/methods/range_search/rs_model.cpp  | 51 ++++++++++---------
 src/mlpack/methods/range_search/rs_model.hpp  |  5 ++
 .../methods/range_search/rs_model_impl.hpp    |  2 +-
 src/mlpack/methods/rann/ra_model.cpp          | 49 ++++++++++--------
 src/mlpack/methods/rann/ra_model.hpp          |  3 ++
 src/mlpack/methods/rann/ra_model_impl.hpp     |  4 +-
 9 files changed, 90 insertions(+), 64 deletions(-)

diff --git a/src/mlpack/methods/kde/kde_model.cpp b/src/mlpack/methods/kde/kde_model.cpp
index 552f1b4058..7a78c78df5 100644
--- a/src/mlpack/methods/kde/kde_model.cpp
+++ b/src/mlpack/methods/kde/kde_model.cpp
@@ -149,10 +149,10 @@ KDEModel::~KDEModel()
 template<template<typename TreeMetricType,
                   typename TreeMatType,
                   typename TreeStatType> class TreeType>
-KDEWrapperBase* BuildModelHelper(const KDEModel::KernelTypes kernelType,
-                                 const double relError,
-                                 const double absError,
-                                 const double bandwidth)
+KDEWrapperBase* InitializeModelHelper(const KDEModel::KernelTypes kernelType,
+                                      const double relError,
+                                      const double absError,
+                                      const double bandwidth)
 {
   switch (kernelType)
   {
@@ -181,7 +181,7 @@ KDEWrapperBase* BuildModelHelper(const KDEModel::KernelTypes kernelType,
   return NULL;
 }
 
-void KDEModel::BuildModel(arma::mat&& referenceSet)
+void KDEModel::InitializeModel()
 {
   // Clean memory, if necessary.
   delete kdeModel;
@@ -190,30 +190,35 @@ void KDEModel::BuildModel(arma::mat&& referenceSet)
   switch (treeType)
   {
     case KD_TREE:
-      kdeModel = BuildModelHelper<tree::KDTree>(kernelType, relError, absError,
-          bandwidth);
+      kdeModel = InitializeModelHelper<tree::KDTree>(kernelType, relError,
+          absError, bandwidth);
       break;
 
     case BALL_TREE:
-      kdeModel = BuildModelHelper<tree::BallTree>(kernelType, relError,
+      kdeModel = InitializeModelHelper<tree::BallTree>(kernelType, relError,
           absError, bandwidth);
       break;
 
     case COVER_TREE:
-      kdeModel = BuildModelHelper<tree::StandardCoverTree>(kernelType, relError,
-          absError, bandwidth);
+      kdeModel = InitializeModelHelper<tree::StandardCoverTree>(kernelType,
+          relError, absError, bandwidth);
       break;
 
     case OCTREE:
-      kdeModel = BuildModelHelper<tree::Octree>(kernelType, relError, absError,
-          bandwidth);
+      kdeModel = InitializeModelHelper<tree::Octree>(kernelType, relError,
+          absError, bandwidth);
       break;
 
     case R_TREE:
-      kdeModel = BuildModelHelper<tree::RTree>(kernelType, relError, absError,
-          bandwidth);
+      kdeModel = InitializeModelHelper<tree::RTree>(kernelType, relError,
+          absError, bandwidth);
       break;
   }
+}
+
+void KDEModel::BuildModel(arma::mat&& referenceSet)
+{
+  InitializeModel();
 
   // Set whether to use Monte Carlo estimations or not.
   kdeModel->MonteCarlo() = monteCarlo;
diff --git a/src/mlpack/methods/kde/kde_model.hpp b/src/mlpack/methods/kde/kde_model.hpp
index c2f93ba181..48b06c6382 100644
--- a/src/mlpack/methods/kde/kde_model.hpp
+++ b/src/mlpack/methods/kde/kde_model.hpp
@@ -414,6 +414,11 @@ class KDEModel
   //! Modify the mode of the model.
   KDEMode& Mode() { return kdeModel->Mode(); }
 
+  /**
+   * Initialize the KDE model.
+   */
+  void InitializeModel();
+
   /**
    * Build the KDE model with the given parameters and then trains it with the
    * given reference data.
diff --git a/src/mlpack/methods/kde/kde_model_impl.hpp b/src/mlpack/methods/kde/kde_model_impl.hpp
index bc00f1d50b..325b071cb3 100644
--- a/src/mlpack/methods/kde/kde_model_impl.hpp
+++ b/src/mlpack/methods/kde/kde_model_impl.hpp
@@ -135,7 +135,7 @@ void KDEModel::serialize(Archive& ar, const uint32_t /* version */)
   }
 
   if (cereal::is_loading<Archive>())
-    delete kdeModel;
+    InitializeModel(); // Values will be overwritten.
 
   // Avoid polymorphism in serialization by serializing directly by the type.
   switch (treeType)
diff --git a/src/mlpack/methods/range_search/rs_model.cpp b/src/mlpack/methods/range_search/rs_model.cpp
index 807a347ee4..33308cee35 100644
--- a/src/mlpack/methods/range_search/rs_model.cpp
+++ b/src/mlpack/methods/range_search/rs_model.cpp
@@ -98,33 +98,11 @@ RSModel::~RSModel()
   delete rSearch;
 }
 
-void RSModel::BuildModel(arma::mat&& referenceSet,
-                         const size_t leafSize,
-                         const bool naive,
-                         const bool singleMode)
+void RSModel::InitializeModel(const bool naive, const bool singleMode)
 {
-  // Initialize random basis if necessary.
-  if (randomBasis)
-  {
-    Log::Info << "Creating random basis..." << std::endl;
-    math::RandomBasis(q, referenceSet.n_rows);
-  }
-
-  this->leafSize = leafSize;
-
   // Clean memory, if necessary.
   delete rSearch;
 
-  // Do we need to modify the reference set?
-  if (randomBasis)
-    referenceSet = q * referenceSet;
-
-  if (!naive)
-  {
-    Timer::Start("tree_building");
-    Log::Info << "Building reference tree..." << std::endl;
-  }
-
   switch (treeType)
   {
     case KD_TREE:
@@ -183,6 +161,33 @@ void RSModel::BuildModel(arma::mat&& referenceSet,
       rSearch = new LeafSizeRSWrapper<tree::Octree>(naive, singleMode);
       break;
   }
+}
+
+void RSModel::BuildModel(arma::mat&& referenceSet,
+                         const size_t leafSize,
+                         const bool naive,
+                         const bool singleMode)
+{
+  // Initialize random basis if necessary.
+  if (randomBasis)
+  {
+    Log::Info << "Creating random basis..." << std::endl;
+    math::RandomBasis(q, referenceSet.n_rows);
+  }
+
+  this->leafSize = leafSize;
+
+  // Do we need to modify the reference set?
+  if (randomBasis)
+    referenceSet = q * referenceSet;
+
+  if (!naive)
+  {
+    Timer::Start("tree_building");
+    Log::Info << "Building reference tree..." << std::endl;
+  }
+
+  InitializeModel(naive, singleMode);
 
   rSearch->Train(std::move(referenceSet), leafSize);
 
diff --git a/src/mlpack/methods/range_search/rs_model.hpp b/src/mlpack/methods/range_search/rs_model.hpp
index 12638c2836..430274cd9b 100644
--- a/src/mlpack/methods/range_search/rs_model.hpp
+++ b/src/mlpack/methods/range_search/rs_model.hpp
@@ -300,6 +300,11 @@ class RSModel
   //! been built).
   bool& RandomBasis() { return randomBasis; }
 
+  /**
+   * Allocate the memory for the range search model.
+   */
+  void InitializeModel(const bool naive, const bool singleMode);
+
   /**
    * Build the reference tree on the given dataset with the given parameters.
    * This takes possession of the reference set to avoid a copy.
diff --git a/src/mlpack/methods/range_search/rs_model_impl.hpp b/src/mlpack/methods/range_search/rs_model_impl.hpp
index 2df060f977..a59180e1b2 100644
--- a/src/mlpack/methods/range_search/rs_model_impl.hpp
+++ b/src/mlpack/methods/range_search/rs_model_impl.hpp
@@ -127,7 +127,7 @@ void RSModel::serialize(Archive& ar, const uint32_t /* version */)
 
   // This should never happen, but just in case...
   if (cereal::is_loading<Archive>())
-    delete rSearch;
+    InitializeModel(false, false); // Values will be overwritten.
 
   // Avoid polymorphic serialization by explicitly serializing the correct type.
   switch (treeType)
diff --git a/src/mlpack/methods/rann/ra_model.cpp b/src/mlpack/methods/rann/ra_model.cpp
index a6a997a22c..6342acf6b4 100644
--- a/src/mlpack/methods/rann/ra_model.cpp
+++ b/src/mlpack/methods/rann/ra_model.cpp
@@ -95,32 +95,11 @@ RAModel::~RAModel()
   delete raSearch;
 }
 
-void RAModel::BuildModel(arma::mat&& referenceSet,
-                                     const size_t leafSize,
-                                     const bool naive,
-                                     const bool singleMode)
+void RAModel::InitializeModel(const bool naive, const bool singleMode)
 {
-  // Initialize random basis, if necessary.
-  if (randomBasis)
-  {
-    Log::Info << "Creating random basis..." << std::endl;
-    math::RandomBasis(q, referenceSet.n_rows);
-  }
-
   // Clean memory, if necessary.
   delete raSearch;
 
-  this->leafSize = leafSize;
-
-  if (randomBasis)
-    referenceSet = q * referenceSet;
-
-  if (!naive)
-  {
-    Timer::Start("tree_building");
-    Log::Info << "Building reference tree..." << std::endl;
-  }
-
   switch (treeType)
   {
     case KD_TREE:
@@ -154,6 +133,32 @@ void RAModel::BuildModel(arma::mat&& referenceSet,
       raSearch = new LeafSizeRAWrapper<tree::Octree>(naive, singleMode);
       break;
   }
+}
+
+void RAModel::BuildModel(arma::mat&& referenceSet,
+                         const size_t leafSize,
+                         const bool naive,
+                         const bool singleMode)
+{
+  // Initialize random basis, if necessary.
+  if (randomBasis)
+  {
+    Log::Info << "Creating random basis..." << std::endl;
+    math::RandomBasis(q, referenceSet.n_rows);
+  }
+
+  this->leafSize = leafSize;
+
+  if (randomBasis)
+    referenceSet = q * referenceSet;
+
+  if (!naive)
+  {
+    Timer::Start("tree_building");
+    Log::Info << "Building reference tree..." << std::endl;
+  }
+
+  InitializeModel(naive, singleMode);
 
   raSearch->Train(std::move(referenceSet), leafSize);
 
diff --git a/src/mlpack/methods/rann/ra_model.hpp b/src/mlpack/methods/rann/ra_model.hpp
index 8ed91a9c9b..572d599a0d 100644
--- a/src/mlpack/methods/rann/ra_model.hpp
+++ b/src/mlpack/methods/rann/ra_model.hpp
@@ -385,6 +385,9 @@ class RAModel
   //! the model using BuildModel().
   bool& RandomBasis() { return randomBasis; }
 
+  //! Initialize the model's memory.
+  void InitializeModel(const bool naive, const bool singleMode);
+
   //! Build the reference tree.
   void BuildModel(arma::mat&& referenceSet,
                   const size_t leafSize,
diff --git a/src/mlpack/methods/rann/ra_model_impl.hpp b/src/mlpack/methods/rann/ra_model_impl.hpp
index 6955bd9f46..c986c4570c 100644
--- a/src/mlpack/methods/rann/ra_model_impl.hpp
+++ b/src/mlpack/methods/rann/ra_model_impl.hpp
@@ -126,9 +126,7 @@ void RAModel::serialize(Archive& ar, const uint32_t /* version */)
 
   // This should never happen, but just in case, be clean with memory.
   if (cereal::is_loading<Archive>())
-  {
-    delete raSearch;
-  }
+    InitializeModel(false, false); // Values will be overwritten.
 
   // Avoid polymorphic serialization by explicitly serializing the correct type.
   switch (treeType)

From 06950dd1b581a9f6968e12d1e0e217b1ffa91620 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 09:45:18 -0500
Subject: [PATCH 059/253] Remove boost::visitor from mlpack::cf.

---
 src/mlpack/methods/cf/CMakeLists.txt    |   1 +
 src/mlpack/methods/cf/cf_main.cpp       | 437 ++++++++-------------
 src/mlpack/methods/cf/cf_model.cpp      | 207 ++++++++++
 src/mlpack/methods/cf/cf_model.hpp      | 325 +++++++++-------
 src/mlpack/methods/cf/cf_model_impl.hpp | 496 ++++++++++++++++--------
 src/mlpack/tests/main_tests/cf_test.cpp |  63 ++-
 6 files changed, 925 insertions(+), 604 deletions(-)
 create mode 100644 src/mlpack/methods/cf/cf_model.cpp

diff --git a/src/mlpack/methods/cf/CMakeLists.txt b/src/mlpack/methods/cf/CMakeLists.txt
index a7c552ae28..c59a4f12ed 100644
--- a/src/mlpack/methods/cf/CMakeLists.txt
+++ b/src/mlpack/methods/cf/CMakeLists.txt
@@ -5,6 +5,7 @@ set(SOURCES
   cf_impl.hpp
   cf_model.hpp
   cf_model_impl.hpp
+  cf_model.cpp
   svd_wrapper.hpp
   svd_wrapper_impl.hpp
 )
diff --git a/src/mlpack/methods/cf/cf_main.cpp b/src/mlpack/methods/cf/cf_main.cpp
index 760ddf107d..f4aa8e14b7 100644
--- a/src/mlpack/methods/cf/cf_main.cpp
+++ b/src/mlpack/methods/cf/cf_main.cpp
@@ -194,279 +194,6 @@ PARAM_STRING_IN("interpolation", "Algorithm used for weight interpolation.",
 PARAM_STRING_IN("neighbor_search", "Algorithm used for neighbor search.",
     "S", "euclidean");
 
-template <typename NeighborSearchType,
-          typename InterpolationType>
-void ComputeRecommendations(CFModel* cf,
-                            const size_t numRecs,
-                            arma::Mat<size_t>& recommendations)
-{
-  // Reading users.
-  if (IO::HasParam("query"))
-  {
-    // User matrix.
-    arma::Mat<size_t> users =
-        std::move(IO::GetParam<arma::Mat<size_t>>("query"));
-    if (users.n_rows > 1)
-      users = users.t();
-    if (users.n_rows > 1)
-      Log::Fatal << "List of query users must be one-dimensional!"
-                 << std::endl;
-
-    Log::Info << "Generating recommendations for "
-              << users.n_elem << " users."
-              << endl;
-
-    cf->GetRecommendations<NeighborSearchType, InterpolationType>
-        (numRecs, recommendations, users.row(0).t());
-  }
-  else
-  {
-    Log::Info << "Generating recommendations for all users." << endl;
-    cf->GetRecommendations<NeighborSearchType, InterpolationType>
-        (numRecs, recommendations);
-  }
-}
-
-template <typename NeighborSearchType>
-void ComputeRecommendations(CFModel* cf,
-                            const size_t numRecs,
-                            arma::Mat<size_t>& recommendations)
-{
-  // Verify the Interpolation algorithms.
-  RequireParamInSet<string>("interpolation", { "average",
-      "regression", "similarity" }, true, "unknown interpolation algorithm");
-
-  // Taking Interpolation Alternatives
-  const string interpolationAlgorithm = IO::GetParam<string>("interpolation");
-
-  // Determining the Interpolation Algorithm
-  if (interpolationAlgorithm == "average")
-  {
-    ComputeRecommendations<NeighborSearchType, AverageInterpolation>
-        (cf, numRecs, recommendations);
-  }
-  else if (interpolationAlgorithm == "regression")
-  {
-    ComputeRecommendations<NeighborSearchType, RegressionInterpolation>
-        (cf, numRecs, recommendations);
-  }
-  else if (interpolationAlgorithm == "similarity")
-  {
-    ComputeRecommendations<NeighborSearchType, SimilarityInterpolation>
-        (cf, numRecs, recommendations);
-  }
-}
-
-void ComputeRecommendations(CFModel* cf,
-                            const size_t numRecs,
-                            arma::Mat<size_t>& recommendations)
-{
-  //  Verifying the Neighbor Search algorithms
-  RequireParamInSet<string>("neighbor_search", { "cosine",
-      "euclidean", "pearson" }, true, "unknown neighbor search algorithm");
-
-  //  Taking Neighbor Search alternatives
-  const string neighborSearchAlgorithm = IO::GetParam<string>
-      ("neighbor_search");
-
-
-  // Determining the Neighbor Search Algorithms
-  if (neighborSearchAlgorithm == "cosine")
-  {
-    ComputeRecommendations<CosineSearch>(cf, numRecs, recommendations);
-  }
-  else if (neighborSearchAlgorithm == "euclidean")
-  {
-    ComputeRecommendations<EuclideanSearch>(cf, numRecs, recommendations);
-  }
-  else if (neighborSearchAlgorithm == "pearson")
-  {
-    ComputeRecommendations<PearsonSearch>(cf, numRecs, recommendations);
-  }
-}
-
-template <typename NeighborSearchType,
-          typename InterpolationType>
-void ComputeRMSE(CFModel* cf)
-{
-  // Now, compute each test point.
-  arma::mat testData = std::move(IO::GetParam<arma::mat>("test"));
-
-  // Assemble the combination matrix to get RMSE value.
-  arma::Mat<size_t> combinations(2, testData.n_cols);
-  for (size_t i = 0; i < testData.n_cols; ++i)
-  {
-    combinations(0, i) = size_t(testData(0, i));
-    combinations(1, i) = size_t(testData(1, i));
-  }
-
-  // Now compute the RMSE.
-  arma::vec predictions;
-  cf->Predict<NeighborSearchType, InterpolationType>
-      (combinations, predictions);
-
-  // Compute the root of the sum of the squared errors, divide by the number of
-  // points to get the RMSE.  It turns out this is just the L2-norm divided by
-  // the square root of the number of points, if we interpret the predictions
-  // and the true values as vectors.
-  const double rmse = arma::norm(predictions - testData.row(2).t(), 2) /
-      std::sqrt((double) testData.n_cols);
-
-  Log::Info << "RMSE is " << rmse << "." << endl;
-}
-
-template <typename NeighborSearchType>
-void ComputeRMSE(CFModel* cf)
-{
-  //  Verifying the Interpolation algorithms
-  RequireParamInSet<string>("interpolation", { "average",
-      "regression", "similarity" }, true, "unknown interpolation algorithm");
-
-  //  Taking Interpolation Alternatives
-  const string interpolationAlgorithm = IO::GetParam<string>("interpolation");
-
-  if (interpolationAlgorithm == "average")
-  {
-    ComputeRMSE<NeighborSearchType, AverageInterpolation>(cf);
-  }
-  else if (interpolationAlgorithm == "regression")
-  {
-    ComputeRMSE<NeighborSearchType, RegressionInterpolation>(cf);
-  }
-  else if (interpolationAlgorithm == "similarity")
-  {
-    ComputeRMSE<NeighborSearchType, SimilarityInterpolation>(cf);
-  }
-}
-
-void ComputeRMSE(CFModel* cf)
-{
-  //  Verifying the Neighbor Search algorithms
-  RequireParamInSet<string>("neighbor_search", { "cosine",
-      "euclidean", "pearson" }, true, "unknown neighbor search algorithm");
-
-  //  Taking Neighbor Search alternatives
-  const string neighborSearchAlgorithm = IO::GetParam<string>
-    ("neighbor_search");
-
-  if (neighborSearchAlgorithm == "cosine")
-  {
-    ComputeRMSE<CosineSearch>(cf);
-  }
-  else if (neighborSearchAlgorithm == "euclidean")
-  {
-    ComputeRMSE<EuclideanSearch>(cf);
-  }
-  else if (neighborSearchAlgorithm == "pearson")
-  {
-    ComputeRMSE<PearsonSearch>(cf);
-  }
-}
-
-void PerformAction(CFModel* c)
-{
-  if (IO::HasParam("query") || IO::HasParam("all_user_recommendations"))
-  {
-    // Get parameters for generating recommendations.
-    const size_t numRecs = (size_t) IO::GetParam<int>("recommendations");
-
-    // Get the recommendations.
-    arma::Mat<size_t> recommendations;
-    ComputeRecommendations(c, numRecs, recommendations);
-
-    // Save the output.
-    IO::GetParam<arma::Mat<size_t>>("output") = recommendations;
-  }
-
-  if (IO::HasParam("test"))
-    ComputeRMSE(c);
-
-  IO::GetParam<CFModel*>("output_model") = c;
-}
-
-template<typename DecompositionPolicy>
-void PerformAction(arma::mat& dataset,
-                   const size_t rank,
-                   const size_t maxIterations,
-                   const double minResidue)
-{
-  const size_t neighborhood = (size_t) IO::GetParam<int>("neighborhood");
-
-  // Make sure the normalization strategy is valid.
-  RequireParamInSet<string>("normalization", { "overall_mean", "item_mean",
-      "user_mean", "z_score", "none" }, true, "unknown normalization type");
-
-  CFModel* c = new CFModel();
-
-  const string normalizationType = IO::GetParam<string>("normalization");
-
-  c->template Train<DecompositionPolicy>(dataset, neighborhood, rank,
-      maxIterations, minResidue, IO::HasParam("iteration_only_termination"),
-      normalizationType);
-
-  try
-  {
-    PerformAction(c);
-  }
-  catch (std::exception& e)
-  {
-    // Clean the memory before throwing completely.
-    delete c;
-    throw;
-  }
-}
-
-void AssembleFactorizerType(const std::string& algorithm,
-                            arma::mat& dataset,
-                            const size_t rank)
-{
-  const size_t maxIterations = (size_t) IO::GetParam<int>("max_iterations");
-  const double minResidue = IO::GetParam<double>("min_residue");
-
-  if (algorithm == "NMF")
-  {
-    PerformAction<NMFPolicy>(dataset, rank, maxIterations, minResidue);
-  }
-  else if (algorithm == "BatchSVD")
-  {
-    PerformAction<BatchSVDPolicy>(dataset, rank, maxIterations, minResidue);
-  }
-  else if (algorithm == "SVDIncompleteIncremental")
-  {
-    PerformAction<SVDIncompletePolicy>(dataset, rank, maxIterations,
-        minResidue);
-  }
-  else if (algorithm == "SVDCompleteIncremental")
-  {
-    PerformAction<SVDCompletePolicy>(dataset, rank, maxIterations, minResidue);
-  }
-  else if (algorithm == "RegSVD")
-  {
-    ReportIgnoredParam("min_residue", "Regularized SVD terminates only "
-        "when max_iterations is reached");
-    PerformAction<RegSVDPolicy>(dataset, rank, maxIterations, minResidue);
-  }
-  else if (algorithm == "RandSVD")
-  {
-    ReportIgnoredParam("min_residue", "Randomized SVD terminates only "
-        "when max_iterations is reached");
-    PerformAction<RandomizedSVDPolicy>(dataset, rank, maxIterations,
-        minResidue);
-  }
-  else if (algorithm == "BiasSVD")
-  {
-    ReportIgnoredParam("min_residue", "Bias SVD terminates only "
-        "when max_iterations is reached");
-    PerformAction<BiasSVDPolicy>(dataset, rank, maxIterations, minResidue);
-  }
-  else if (algorithm == "SVDPP")
-  {
-    ReportIgnoredParam("min_residue", "SVD++ terminates only "
-        "when max_iterations is reached");
-    PerformAction<SVDPlusPlusPolicy>(dataset, rank, maxIterations, minResidue);
-  }
-}
-
 static void mlpackMain()
 {
   if (IO::GetParam<int>("seed") == 0)
@@ -496,6 +223,7 @@ static void mlpackMain()
         "recommendations must be positive");
 
   // Either load from a model, or train a model.
+  CFModel* cf;
   if (IO::HasParam("training"))
   {
     // Train a model.
@@ -523,23 +251,174 @@ static void mlpackMain()
     // Get parameters.
     const size_t rank = (size_t) IO::GetParam<int>("rank");
 
+    cf = new CFModel();
+
     // Perform decomposition to prepare for recommendations.
     Log::Info << "Performing CF matrix decomposition on dataset..." << endl;
 
     const string algo = IO::GetParam<string>("algorithm");
+    if (algo == "NMF")
+    {
+      cf->DecompositionType() = CFModel::NMF;
+    }
+    else if (algo == "BatchSVD")
+    {
+      cf->DecompositionType() = CFModel::BATCH_SVD;
+    }
+    else if (algo == "SVDIncompleteIncremental")
+    {
+      cf->DecompositionType() = CFModel::SVD_INCOMPLETE;
+    }
+    else if (algo == "SVDCompleteIncremental")
+    {
+      cf->DecompositionType() = CFModel::SVD_COMPLETE;
+    }
+    else if (algo == "RegSVD")
+    {
+      ReportIgnoredParam("min_residue", "Regularized SVD terminates only "
+          "when max_iterations is reached");
+      cf->DecompositionType() = CFModel::REG_SVD;
+    }
+    else if (algo == "RandSVD")
+    {
+      ReportIgnoredParam("min_residue", "Randomized SVD terminates only "
+          "when max_iterations is reached");
+      cf->DecompositionType() = CFModel::RANDOMIZED_SVD;
+    }
+    else if (algo == "BiasSVD")
+    {
+      ReportIgnoredParam("min_residue", "Bias SVD terminates only "
+          "when max_iterations is reached");
+      cf->DecompositionType() = CFModel::BIAS_SVD;
+    }
+    else if (algo == "SVDPP")
+    {
+      ReportIgnoredParam("min_residue", "SVD++ terminates only "
+          "when max_iterations is reached");
+      cf->DecompositionType() = CFModel::SVD_PLUS_PLUS;
+    }
 
     // Perform the factorization and do whatever the user wanted.
-    AssembleFactorizerType(algo, dataset, rank);
+    const size_t neighborhood = (size_t) IO::GetParam<int>("neighborhood");
+
+    // Make sure the normalization strategy is valid.
+    RequireParamInSet<string>("normalization", { "overall_mean", "item_mean",
+        "user_mean", "z_score", "none" }, true, "unknown normalization type");
+
+    const string normalizationType = IO::GetParam<string>("normalization");
+    if (normalizationType == "none")
+      cf->NormalizationType() = CFModel::NO_NORMALIZATION;
+    else if (normalizationType == "item_mean")
+      cf->NormalizationType() = CFModel::ITEM_MEAN_NORMALIZATION;
+    else if (normalizationType == "user_mean")
+      cf->NormalizationType() = CFModel::USER_MEAN_NORMALIZATION;
+    else if (normalizationType == "overall_mean")
+      cf->NormalizationType() = CFModel::OVERALL_MEAN_NORMALIZATION;
+    else if (normalizationType == "z_score")
+      cf->NormalizationType() = CFModel::Z_SCORE_NORMALIZATION;
+
+    cf->Train(dataset,
+              neighborhood,
+              rank,
+              size_t(IO::GetParam<int>("max_iterations")),
+              IO::GetParam<double>("min_residue"),
+              IO::HasParam("iteration_only_termination"));
   }
   else
   {
     // Load from a model after validating parameters.
-    RequireAtLeastOnePassed({ "query", "all_user_recommendations",
-        "test" }, true);
+    RequireAtLeastOnePassed({ "query", "all_user_recommendations", "test" },
+        true);
 
     // Load an input model.
-    CFModel* c = std::move(IO::GetParam<CFModel*>("input_model"));
-
-    PerformAction(c);
+    cf = std::move(IO::GetParam<CFModel*>("input_model"));
   }
+
+  // Get the types of the neighbor search method and the interpolation.  (These
+  // may or may not be used.)
+  NeighborSearchTypes nsType;
+  RequireParamInSet<string>("neighbor_search", { "cosine",
+      "euclidean", "pearson" }, true, "unknown neighbor search algorithm");
+  if (IO::GetParam<std::string>("neighbor_search") == "cosine")
+    nsType = COSINE_SEARCH;
+  else if (IO::GetParam<std::string>("neighbor_search") == "euclidean")
+    nsType = EUCLIDEAN_SEARCH;
+  else if (IO::GetParam<std::string>("neighbor_search") == "pearson")
+    nsType = PEARSON_SEARCH;
+
+  InterpolationTypes interpolationType;
+  RequireParamInSet<string>("interpolation", { "average",
+      "regression", "similarity" }, true, "unknown interpolation algorithm");
+  if (IO::GetParam<std::string>("interpolation") == "average")
+    interpolationType = AVERAGE_INTERPOLATION;
+  else if (IO::GetParam<std::string>("interpolation") == "regression")
+    interpolationType = REGRESSION_INTERPOLATION;
+  else if (IO::GetParam<std::string>("interpolation") == "similarity")
+    interpolationType = SIMILARITY_INTERPOLATION;
+
+  if (IO::HasParam("query") || IO::HasParam("all_user_recommendations"))
+  {
+    // Get parameters for generating recommendations.
+    const size_t numRecs = (size_t) IO::GetParam<int>("recommendations");
+
+    // Get the recommendations.
+    arma::Mat<size_t> recommendations;
+
+    // Reading users.
+    if (IO::HasParam("query"))
+    {
+      // User matrix.
+      arma::Mat<size_t> users =
+          std::move(IO::GetParam<arma::Mat<size_t>>("query"));
+      if (users.n_rows > 1)
+        users = users.t();
+      if (users.n_rows > 1)
+        Log::Fatal << "List of query users must be one-dimensional!"
+                   << std::endl;
+
+      Log::Info << "Generating recommendations for " << users.n_elem
+          << " users." << endl;
+
+      cf->GetRecommendations(nsType, interpolationType, numRecs,
+          recommendations, users.row(0).t());
+    }
+    else
+    {
+      Log::Info << "Generating recommendations for all users." << endl;
+      cf->GetRecommendations(nsType, interpolationType, numRecs,
+          recommendations);
+    }
+
+    // Save the output.
+    IO::GetParam<arma::Mat<size_t>>("output") = recommendations;
+  }
+
+  if (IO::HasParam("test"))
+  {
+    // Now, compute each test point.
+    arma::mat testData = std::move(IO::GetParam<arma::mat>("test"));
+
+    // Assemble the combination matrix to get RMSE value.
+    arma::Mat<size_t> combinations(2, testData.n_cols);
+    for (size_t i = 0; i < testData.n_cols; ++i)
+    {
+      combinations(0, i) = size_t(testData(0, i));
+      combinations(1, i) = size_t(testData(1, i));
+    }
+
+    // Now compute the RMSE.
+    arma::vec predictions;
+    cf->Predict(nsType, interpolationType, combinations, predictions);
+
+    // Compute the root of the sum of the squared errors, divide by the number
+    // of points to get the RMSE.  It turns out this is just the L2-norm divided
+    // by the square root of the number of points, if we interpret the
+    // predictions and the true values as vectors.
+    const double rmse = arma::norm(predictions - testData.row(2).t(), 2) /
+        std::sqrt((double) testData.n_cols);
+
+    Log::Info << "RMSE is " << rmse << "." << endl;
+  }
+
+  IO::GetParam<CFModel*>("output_model") = cf;
 }
diff --git a/src/mlpack/methods/cf/cf_model.cpp b/src/mlpack/methods/cf/cf_model.cpp
new file mode 100644
index 0000000000..226edcf1be
--- /dev/null
+++ b/src/mlpack/methods/cf/cf_model.cpp
@@ -0,0 +1,207 @@
+/**
+ * @file methods/cf/cf_model_impl.hpp
+ * @author Wenhao Huang
+ *
+ * A serializable CF model, used by the main program.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include "cf_model.hpp"
+
+namespace mlpack {
+namespace cf {
+
+CFModel::CFModel() :
+    decompositionType(NMF),
+    normalizationType(NO_NORMALIZATION),
+    cf(NULL)
+{
+  // Nothing else to do.
+}
+
+CFModel::CFModel(const CFModel& other) :
+    decompositionType(other.decompositionType),
+    normalizationType(other.normalizationType),
+    cf(other.cf->Clone())
+{
+  // Nothing else to do.
+}
+
+CFModel::CFModel(CFModel&& other) :
+    decompositionType(other.decompositionType),
+    normalizationType(other.normalizationType),
+    cf(std::move(other.cf))
+{
+  // Reset properties of the other one.
+  other.decompositionType = NMF;
+  other.normalizationType = NO_NORMALIZATION;
+}
+
+CFModel& CFModel::operator=(const CFModel& other)
+{
+  if (this != &other)
+  {
+    decompositionType = other.decompositionType;
+    normalizationType = other.normalizationType;
+    cf = other.cf->Clone();
+  }
+
+  return *this;
+}
+
+CFModel& CFModel::operator=(CFModel&& other)
+{
+  if (this != &other)
+  {
+    decompositionType = other.decompositionType;
+    normalizationType = other.normalizationType;
+    cf = std::move(other.cf);
+
+    // Reset the other object.
+    other.decompositionType = NMF;
+    other.normalizationType = NO_NORMALIZATION;
+  }
+
+  return *this;
+}
+
+CFModel::~CFModel()
+{
+  delete cf;
+}
+
+template<typename DecompositionPolicy>
+CFWrapperBase* TrainHelper(const DecompositionPolicy& decomposition,
+                           const CFModel::NormalizationTypes normalizationType,
+                           const arma::mat& data,
+                           const size_t numUsersForSimilarity,
+                           const size_t rank,
+                           const size_t maxIterations,
+                           const double minResidue,
+                           const bool mit)
+{
+  switch (normalizationType)
+  {
+    case CFModel::NO_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, NoNormalization>(data,
+          decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
+          mit);
+      break;
+
+    case CFModel::ITEM_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, ItemMeanNormalization>(data,
+          decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
+          mit);
+      break;
+
+    case CFModel::USER_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, UserMeanNormalization>(data,
+          decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
+          mit);
+      break;
+
+    case CFModel::OVERALL_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, OverallMeanNormalization>(data,
+          decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
+          mit);
+      break;
+
+    case CFModel::Z_SCORE_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, ZScoreNormalization>(data,
+          decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
+          mit);
+      break;
+  }
+
+  // This shouldn't ever happen.
+  return NULL;
+}
+
+void CFModel::Train(const arma::mat& data,
+                    const size_t numUsersForSimilarity,
+                    const size_t rank,
+                    const size_t maxIterations,
+                    const double minResidue,
+                    const bool mit)
+{
+  // Delete the current CFType object, if there is one.
+  delete cf;
+
+  switch (decompositionType)
+  {
+    case NMF:
+      cf = TrainHelper(NMFPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case BATCH_SVD:
+      cf = TrainHelper(BatchSVDPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case RANDOMIZED_SVD:
+      cf = TrainHelper(RandomizedSVDPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case REG_SVD:
+      cf = TrainHelper(RegSVDPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case SVD_COMPLETE:
+      cf = TrainHelper(SVDCompletePolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case SVD_INCOMPLETE:
+      cf = TrainHelper(SVDIncompletePolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case BIAS_SVD:
+      cf = TrainHelper(BiasSVDPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+
+    case SVD_PLUS_PLUS:
+      cf = TrainHelper(SVDPlusPlusPolicy(), normalizationType, data,
+          numUsersForSimilarity, rank, maxIterations, minResidue, mit);
+      break;
+  }
+}
+
+//! Make predictions.
+void CFModel::Predict(const NeighborSearchTypes nsType,
+                      const InterpolationTypes interpolationType,
+                      const arma::Mat<size_t>& combinations,
+                      arma::vec& predictions)
+{
+  cf->Predict(nsType, interpolationType, combinations, predictions);
+}
+
+//! Compute recommendations for queried users.
+void CFModel::GetRecommendations(const NeighborSearchTypes nsType,
+                                 const InterpolationTypes interpolationType,
+                                 const size_t numRecs,
+                                 arma::Mat<size_t>& recommendations,
+                                 const arma::Col<size_t>& users)
+{
+  cf->GetRecommendations(nsType, interpolationType, numRecs, recommendations,
+      users);
+}
+
+//! Compute recommendations for all users.
+void CFModel::GetRecommendations(const NeighborSearchTypes nsType,
+                                 const InterpolationTypes interpolationType,
+                                 const size_t numRecs,
+                                 arma::Mat<size_t>& recommendations)
+{
+  cf->GetRecommendations(nsType, interpolationType, numRecs, recommendations);
+}
+
+} // namespace cf
+} // namespace mlpack
diff --git a/src/mlpack/methods/cf/cf_model.hpp b/src/mlpack/methods/cf/cf_model.hpp
index 93ff371a02..354f8b51b5 100644
--- a/src/mlpack/methods/cf/cf_model.hpp
+++ b/src/mlpack/methods/cf/cf_model.hpp
@@ -14,105 +14,146 @@
 #define MLPACK_METHODS_CF_CF_MODEL_HPP
 
 #include <mlpack/core.hpp>
-#include <boost/variant.hpp>
 #include "cf.hpp"
 
-#include <mlpack/methods/cf/decomposition_policies/batch_svd_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/randomized_svd_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/regularized_svd_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/svd_complete_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/svd_incomplete_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/bias_svd_method.hpp>
-#include <mlpack/methods/cf/decomposition_policies/svdplusplus_method.hpp>
-
-#include <mlpack/methods/cf/normalization/no_normalization.hpp>
-#include <mlpack/methods/cf/normalization/overall_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/user_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/item_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/z_score_normalization.hpp>
-
 namespace mlpack {
 namespace cf {
 
 /**
- * DeleteVisitor deletes the CFType<> object which is pointed to by the
- * variable cf in class CFModel.
+ * NeighborSearchTypes contains the set of NeighborSearchPolicy classes that are
+ * usable by CFModel at prediction time.
  */
-class DeleteVisitor : public boost::static_visitor<void>
+enum NeighborSearchTypes
 {
- public:
-  //! Delete CFType object.
-  template <typename DecompositionPolicy,
-            typename NormalizationType = NoNormalization>
-  void operator()(CFType<DecompositionPolicy, NormalizationType>* c) const;
+  COSINE_SEARCH,
+  EUCLIDEAN_SEARCH,
+  PEARSON_SEARCH
 };
 
 /**
- * GetValueVisitor returns the pointer which points to the CFType object.
+ * InterpolationTypes contains the set of InterpolationPolicy classes that are
+ * usable by CFModel at prediction time.
  */
-class GetValueVisitor : public boost::static_visitor<void*>
+enum InterpolationTypes
 {
- public:
-  //! Return stored pointer as void* type.
-  template <typename DecompositionPolicy,
-            typename NormalizationType = NoNormalization>
-  void* operator()(CFType<DecompositionPolicy, NormalizationType>* c) const;
+  AVERAGE_INTERPOLATION,
+  REGRESSION_INTERPOLATION,
+  SIMILARITY_INTERPOLATION
 };
 
 /**
- * PredictVisitor uses the CFType object to make predictions on the given
- * combinations of users and items.
+ * The CFWrapperBase class provides a unified interface that can be used by the
+ * CFModel class to interact with all different CF types at runtime.  All CF
+ * wrapper types inherit from this base class.
  */
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-class PredictVisitor : public boost::static_visitor<void>
+class CFWrapperBase
 {
- private:
-  //! User/item combinations to predict.
-  const arma::Mat<size_t>& combinations;
-  //! Predicted ratings for each user/item combination.
-  arma::vec& predictions;
-
  public:
-  //! Predict ratings for each user-item combination.
-  template <typename DecompositionPolicy,
-            typename NormalizationType = NoNormalization>
-  void operator()(CFType<DecompositionPolicy, NormalizationType>* c) const;
+  //! Create the object.  The base class has nothing to hold.
+  CFWrapperBase() { }
 
-  //! Visitor constructor.
-  PredictVisitor(const arma::Mat<size_t>& combinations,
-                 arma::vec& predictions);
+  //! Make a copy of the object.
+  virtual CFWrapperBase* Clone() const = 0;
+
+  //! Delete the object.
+  virtual ~CFWrapperBase() { }
+
+  //! Compute predictions for users.
+  virtual void Predict(const NeighborSearchTypes nsType,
+                       const InterpolationTypes interpolationType,
+                       const arma::Mat<size_t>& combinations,
+                       arma::vec& predictions) = 0;
+
+  //! Compute recommendations for all users.
+  virtual void GetRecommendations(
+      const NeighborSearchTypes nsType,
+      const InterpolationTypes interpolationType,
+      const size_t numRecs,
+      arma::Mat<size_t>& recommendations) = 0;
+
+  //! Compute recommendations.
+  virtual void GetRecommendations(
+      const NeighborSearchTypes nsType,
+      const InterpolationTypes interpolationType,
+      const size_t numRecs,
+      arma::Mat<size_t>& recommendations,
+      const arma::Col<size_t>& users) = 0;
 };
 
 /**
- * RecommendationVisitor uses the CFType object to get recommendations for the
- * given users.
+ * The CFWrapper class wraps the functionality of all CF types.  If special
+ * handling is needed for a future CF type, this class can be extended.
  */
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-class RecommendationVisitor : public boost::static_visitor<void>
+template<typename DecompositionPolicy, typename NormalizationPolicy>
+class CFWrapper : public CFWrapperBase
 {
- private:
-  //! Number of Recommendations.
-  const size_t numRecs;
-  //! Recommendations matrix to save recommendations.
-  arma::Mat<size_t>& recommendations;
-  //! Users for which recommendations are to be generated.
-  const arma::Col<size_t>& users;
-  //! Whether users are given.
-  const bool usersGiven;
+ protected:
+  typedef CFType<DecompositionPolicy, NormalizationPolicy> CFModelType;
 
  public:
-  //! Visitor constructor.
-  RecommendationVisitor(const size_t numRecs,
-                        arma::Mat<size_t>& recommendations,
-                        const arma::Col<size_t>& users,
-                        const bool usersGiven);
+  //! Create the CFWrapper object, using default parameters to initialize the
+  //! held CF object.
+  CFWrapper() { }
 
-  //! Generates the given number of recommendations.
-  template <typename DecompositionPolicy,
-            typename NormalizationType = NoNormalization>
-  void operator()(CFType<DecompositionPolicy, NormalizationType>* c) const;
+  //! Create the CFWrapper object, initializing the held CF object.
+  CFWrapper(const arma::mat& data,
+            const DecompositionPolicy& decomposition,
+            const size_t numUsersForSimilarity,
+            const size_t rank,
+            const size_t maxIterations,
+            const size_t minResidue,
+            const bool mit) :
+      cf(data,
+         decomposition,
+         numUsersForSimilarity,
+         rank,
+         maxIterations,
+         minResidue,
+         mit)
+  {
+    // Nothing else to do.
+  }
+
+  //! Clone the CFWrapper object.  This handles polymorphism correctly.
+  virtual CFWrapper* Clone() const { return new CFWrapper(*this); }
+
+  //! Destroy the CFWrapper object.
+  virtual ~CFWrapper() { }
+
+  //! Get the CFType object.
+  CFModelType& CF() { return cf; }
+
+  //! Compute predictions for users.
+  virtual void Predict(const NeighborSearchTypes nsType,
+                       const InterpolationTypes interpolationType,
+                       const arma::Mat<size_t>& combinations,
+                       arma::vec& predictions);
+
+  //! Compute recommendations for all users.
+  virtual void GetRecommendations(
+      const NeighborSearchTypes nsType,
+      const InterpolationTypes interpolationType,
+      const size_t numRecs,
+      arma::Mat<size_t>& recommendations);
+
+  //! Compute recommendations.
+  virtual void GetRecommendations(
+      const NeighborSearchTypes nsType,
+      const InterpolationTypes interpolationType,
+      const size_t numRecs,
+      arma::Mat<size_t>& recommendations,
+      const arma::Col<size_t>& users);
+
+  //! Serialize the model.
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */)
+  {
+    ar(CEREAL_NVP(cf));
+  }
+
+ protected:
+  //! This is the CF object that we are wrapping.
+  CFModelType cf;
 };
 
 /**
@@ -120,98 +161,110 @@ class RecommendationVisitor : public boost::static_visitor<void>
  */
 class CFModel
 {
+ public:
+  enum DecompositionTypes
+  {
+    NMF,
+    BATCH_SVD,
+    RANDOMIZED_SVD,
+    REG_SVD,
+    SVD_COMPLETE,
+    SVD_INCOMPLETE,
+    BIAS_SVD,
+    SVD_PLUS_PLUS
+  };
+
+  enum NormalizationTypes
+  {
+    NO_NORMALIZATION,
+    ITEM_MEAN_NORMALIZATION,
+    USER_MEAN_NORMALIZATION,
+    OVERALL_MEAN_NORMALIZATION,
+    Z_SCORE_NORMALIZATION
+  };
+
  private:
+  //! The current decomposition policy type.
+  DecompositionTypes decompositionType;
+  //! The current normalization policy type.
+  NormalizationTypes normalizationType;
+
   /**
    * cf holds an instance of the CFType class for the current
    * decompositionPolicy and normalizationType. It is initialized every time
-   * Train() is executed. We access to the contained value through the visitor
-   * classes defined above.
+   * Train() is executed.
    */
-  boost::variant<CFType<NMFPolicy, NoNormalization>*,
-                 CFType<BatchSVDPolicy, NoNormalization>*,
-                 CFType<RandomizedSVDPolicy, NoNormalization>*,
-                 CFType<RegSVDPolicy, NoNormalization>*,
-                 CFType<SVDCompletePolicy, NoNormalization>*,
-                 CFType<SVDIncompletePolicy, NoNormalization>*,
-                 CFType<BiasSVDPolicy, NoNormalization>*,
-                 CFType<SVDPlusPlusPolicy, NoNormalization>*,
-
-                 CFType<NMFPolicy, ItemMeanNormalization>*,
-                 CFType<BatchSVDPolicy, ItemMeanNormalization>*,
-                 CFType<RandomizedSVDPolicy, ItemMeanNormalization>*,
-                 CFType<RegSVDPolicy, ItemMeanNormalization>*,
-                 CFType<SVDCompletePolicy, ItemMeanNormalization>*,
-                 CFType<SVDIncompletePolicy, ItemMeanNormalization>*,
-                 CFType<BiasSVDPolicy, ItemMeanNormalization>*,
-                 CFType<SVDPlusPlusPolicy, ItemMeanNormalization>*,
-
-                 CFType<NMFPolicy, UserMeanNormalization>*,
-                 CFType<BatchSVDPolicy, UserMeanNormalization>*,
-                 CFType<RandomizedSVDPolicy, UserMeanNormalization>*,
-                 CFType<RegSVDPolicy, UserMeanNormalization>*,
-                 CFType<SVDCompletePolicy, UserMeanNormalization>*,
-                 CFType<SVDIncompletePolicy, UserMeanNormalization>*,
-                 CFType<BiasSVDPolicy, UserMeanNormalization>*,
-                 CFType<SVDPlusPlusPolicy, UserMeanNormalization>*,
-
-                 CFType<NMFPolicy, OverallMeanNormalization>*,
-                 CFType<BatchSVDPolicy, OverallMeanNormalization>*,
-                 CFType<RandomizedSVDPolicy, OverallMeanNormalization>*,
-                 CFType<RegSVDPolicy, OverallMeanNormalization>*,
-                 CFType<SVDCompletePolicy, OverallMeanNormalization>*,
-                 CFType<SVDIncompletePolicy, OverallMeanNormalization>*,
-                 CFType<BiasSVDPolicy, OverallMeanNormalization>*,
-                 CFType<SVDPlusPlusPolicy, OverallMeanNormalization>*,
-
-                 CFType<NMFPolicy, ZScoreNormalization>*,
-                 CFType<BatchSVDPolicy, ZScoreNormalization>*,
-                 CFType<RandomizedSVDPolicy, ZScoreNormalization>*,
-                 CFType<RegSVDPolicy, ZScoreNormalization>*,
-                 CFType<SVDCompletePolicy, ZScoreNormalization>*,
-                 CFType<SVDIncompletePolicy, ZScoreNormalization>*,
-                 CFType<BiasSVDPolicy, ZScoreNormalization>*,
-                 CFType<SVDPlusPlusPolicy, ZScoreNormalization>*> cf;
+  CFWrapperBase* cf;
 
  public:
   //! Create an empty CF model.
-  CFModel() { }
+  CFModel();
+
+  //! Create a CF model by copying the given model.
+  CFModel(const CFModel& other);
+
+  //! Create a CF model by taking ownership of the data of the other model.
+  CFModel(CFModel&& other);
+
+  //! Make this CF model a copy of the other model.
+  CFModel& operator=(const CFModel& other);
+
+  //! Make this CF model take ownership of the data of the other model.
+  CFModel& operator=(CFModel&& other);
 
   //! Clean up memory.
   ~CFModel();
 
-  //! Get the pointer to CFType<> object.
-  template <typename DecompositionPolicy,
-            typename NormalizationType = NoNormalization>
-  const CFType<DecompositionPolicy, NormalizationType>* CFPtr() const;
+  //! Get the CFWrapperBase object.  (Be careful!)
+  CFWrapperBase* CF() const { return cf; }
+
+  //! Get the decomposition type.
+  const DecompositionTypes& DecompositionType() const
+  {
+    return decompositionType;
+  }
+  //! Set the decomposition type.
+  DecompositionTypes& DecompositionType()
+  {
+    return decompositionType;
+  }
+
+  //! Get the normalization type.
+  const NormalizationTypes& NormalizationType() const
+  {
+    return normalizationType;
+  }
+  //! Set the normalization type.
+  NormalizationTypes& NormalizationType()
+  {
+    return normalizationType;
+  }
 
   //! Train the model.
-  template<typename DecompositionPolicy,
-           typename MatType>
-  void Train(const MatType& data,
+  void Train(const arma::mat& data,
              const size_t numUsersForSimilarity,
              const size_t rank,
              const size_t maxIterations,
              const double minResidue,
-             const bool mit,
-             const std::string& normalizationType = "none");
+             const bool mit);
 
   //! Make predictions.
-  template <typename NeighborSearchPolicy,
-            typename InterpolationPolicy>
-  void Predict(const arma::Mat<size_t>& combinations,
+  void Predict(const NeighborSearchTypes nsType,
+               const InterpolationTypes interpolationType,
+               const arma::Mat<size_t>& combinations,
                arma::vec& predictions);
 
   //! Compute recommendations for query users.
-  template<typename NeighborSearchPolicy,
-           typename InterpolationPolicy>
-  void GetRecommendations(const size_t numRecs,
+  void GetRecommendations(const NeighborSearchTypes nsType,
+                          const InterpolationTypes interpolationType,
+                          const size_t numRecs,
                           arma::Mat<size_t>& recommendations,
                           const arma::Col<size_t>& users);
 
   //! Compute recommendations for all users.
-  template<typename NeighborSearchPolicy,
-           typename InterpolationPolicy>
-  void GetRecommendations(const size_t numRecs,
+  void GetRecommendations(const NeighborSearchTypes nsType,
+                          const InterpolationTypes interpolationType,
+                          const size_t numRecs,
                           arma::Mat<size_t>& recommendations);
 
   //! Serialize the model.
diff --git a/src/mlpack/methods/cf/cf_model_impl.hpp b/src/mlpack/methods/cf/cf_model_impl.hpp
index 6df3491e59..fa2634a823 100644
--- a/src/mlpack/methods/cf/cf_model_impl.hpp
+++ b/src/mlpack/methods/cf/cf_model_impl.hpp
@@ -14,204 +14,364 @@
 
 #include "cf_model.hpp"
 
-#include <mlpack/methods/cf/normalization/no_normalization.hpp>
-#include <mlpack/methods/cf/normalization/overall_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/user_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/item_mean_normalization.hpp>
-#include <mlpack/methods/cf/normalization/z_score_normalization.hpp>
+#include "interpolation_policies/average_interpolation.hpp"
+#include "interpolation_policies/regression_interpolation.hpp"
+#include "interpolation_policies/similarity_interpolation.hpp"
 
-using namespace mlpack::cf;
+#include "neighbor_search_policies/cosine_search.hpp"
+#include "neighbor_search_policies/lmetric_search.hpp"
+#include "neighbor_search_policies/pearson_search.hpp"
 
-template <typename DecompositionPolicy,
-          typename NormalizationType>
-void DeleteVisitor::
-operator()(CFType<DecompositionPolicy, NormalizationType>* c) const
+#include "decomposition_policies/batch_svd_method.hpp"
+#include "decomposition_policies/bias_svd_method.hpp"
+#include "decomposition_policies/nmf_method.hpp"
+#include "decomposition_policies/randomized_svd_method.hpp"
+#include "decomposition_policies/regularized_svd_method.hpp"
+#include "decomposition_policies/svd_complete_method.hpp"
+#include "decomposition_policies/svd_incomplete_method.hpp"
+#include "decomposition_policies/svdplusplus_method.hpp"
+
+#include "normalization/no_normalization.hpp"
+#include "normalization/overall_mean_normalization.hpp"
+#include "normalization/user_mean_normalization.hpp"
+#include "normalization/item_mean_normalization.hpp"
+#include "normalization/z_score_normalization.hpp"
+
+namespace mlpack {
+namespace cf {
+
+template<typename NeighborSearchPolicy, typename CFType>
+void PredictHelper(CFType& cf,
+                   const InterpolationTypes interpolationType,
+                   const arma::Mat<size_t>& combinations,
+                   arma::vec& predictions)
 {
-  if (c)
-    delete c;
-}
-
-template <typename DecompositionPolicy,
-          typename NormalizationType>
-void* GetValueVisitor::
-operator()(CFType<DecompositionPolicy, NormalizationType>* c) const
-{
-  if (!c)
-    throw std::runtime_error("no cf model initialized");
-
-  return (void*) c;
-}
-
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-PredictVisitor<NeighborSearchPolicy, InterpolationPolicy>::PredictVisitor(
-    const arma::Mat<size_t>& combinations,
-    arma::vec& predictions) :
-    combinations(combinations),
-    predictions(predictions)
-{ }
-
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-template <typename DecompositionPolicy,
-          typename NormalizationType>
-void PredictVisitor<NeighborSearchPolicy, InterpolationPolicy>
-        ::operator()(CFType<DecompositionPolicy, NormalizationType>* c) const
-{
-  if (!c)
+  switch (interpolationType)
   {
-    throw std::runtime_error("no cf model initialized");
-    return;
-  }
+    case AVERAGE_INTERPOLATION:
+      cf.template Predict<NeighborSearchPolicy,
+                          AverageInterpolation>(combinations, predictions);
+      break;
 
-  c->template Predict<NeighborSearchPolicy,
-      InterpolationPolicy>(combinations, predictions);
-}
+    case REGRESSION_INTERPOLATION:
+      cf.template Predict<NeighborSearchPolicy,
+                          RegressionInterpolation>(combinations, predictions);
+      break;
 
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-RecommendationVisitor<NeighborSearchPolicy, InterpolationPolicy>
-        ::RecommendationVisitor(
-    const size_t numRecs,
-    arma::Mat<size_t>& recommendations,
-    const arma::Col<size_t>& users,
-    const bool usersGiven) :
-    numRecs(numRecs),
-    recommendations(recommendations),
-    users(users),
-    usersGiven(usersGiven)
-{ }
-
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-template <typename DecompositionPolicy,
-          typename NormalizationType>
-void RecommendationVisitor<NeighborSearchPolicy, InterpolationPolicy>
-        ::operator()(CFType<DecompositionPolicy, NormalizationType>* c) const
-{
-  if (!c)
-  {
-    throw std::runtime_error("no cf model initialized");
-    return;
-  }
-
-  if (usersGiven)
-    c->template GetRecommendations<NeighborSearchPolicy, InterpolationPolicy>
-        (numRecs, recommendations, users);
-  else
-    c->template GetRecommendations<NeighborSearchPolicy, InterpolationPolicy>
-        (numRecs, recommendations);
-}
-
-CFModel::~CFModel()
-{
-  boost::apply_visitor(DeleteVisitor(), cf);
-}
-
-template<typename DecompositionPolicy,
-         typename MatType>
-void CFModel::Train(const MatType& data,
-                    const size_t numUsersForSimilarity,
-                    const size_t rank,
-                    const size_t maxIterations,
-                    const double minResidue,
-                    const bool mit,
-                    const std::string& normalization)
-{
-  // Delete the current CFType object, if there is one.
-  boost::apply_visitor(DeleteVisitor(), cf);
-
-  // Instantiate a new CFType object.
-  DecompositionPolicy decomposition;
-  if (normalization == "overall_mean")
-  {
-    cf = new CFType<DecompositionPolicy, OverallMeanNormalization>(data,
-        decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
-        mit);
-  }
-  else if (normalization == "item_mean")
-  {
-    cf = new CFType<DecompositionPolicy, ItemMeanNormalization>(data,
-        decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
-        mit);
-  }
-  else if (normalization == "user_mean")
-  {
-    cf = new CFType<DecompositionPolicy, UserMeanNormalization>(data,
-        decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
-        mit);
-  }
-  else if (normalization == "z_score")
-  {
-    cf = new CFType<DecompositionPolicy, ZScoreNormalization>(data,
-        decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
-        mit);
-  }
-  else if (normalization == "none")
-  {
-    cf = new CFType<DecompositionPolicy, NoNormalization>(data,
-        decomposition, numUsersForSimilarity, rank, maxIterations, minResidue,
-        mit);
-  }
-  else
-  {
-    throw std::runtime_error("Unsupported normalization algorithm."
-                             " It should be one of none, overall_mean, "
-                             "item_mean, user_mean or z_score");
+    case SIMILARITY_INTERPOLATION:
+      cf.template Predict<NeighborSearchPolicy,
+                          SimilarityInterpolation>(combinations, predictions);
+      break;
   }
 }
 
 //! Make predictions.
-template <typename NeighborSearchPolicy,
-          typename InterpolationPolicy>
-void CFModel::Predict(const arma::Mat<size_t>& combinations,
-                      arma::vec& predictions)
+template<typename DecompositionPolicy, typename NormalizationPolicy>
+void CFWrapper<DecompositionPolicy, NormalizationPolicy>::Predict(
+    const NeighborSearchTypes nsType,
+    const InterpolationTypes interpolationType,
+    const arma::Mat<size_t>& combinations,
+    arma::vec& predictions)
 {
-  PredictVisitor<NeighborSearchPolicy, InterpolationPolicy>
-      predict(combinations, predictions);
-  boost::apply_visitor(predict, cf);
+  switch (nsType)
+  {
+    case COSINE_SEARCH:
+      PredictHelper<CosineSearch>(cf, interpolationType, combinations,
+          predictions);
+      break;
+
+    case EUCLIDEAN_SEARCH:
+      PredictHelper<EuclideanSearch>(cf, interpolationType, combinations,
+          predictions);
+      break;
+
+    case PEARSON_SEARCH:
+      PredictHelper<PearsonSearch>(cf, interpolationType, combinations,
+          predictions);
+      break;
+  }
+}
+
+template<typename NeighborSearchPolicy, typename CFType>
+void GetRecommendationsHelper(
+    CFType& cf,
+    const InterpolationTypes interpolationType,
+    const size_t numRecs,
+    arma::Mat<size_t>& recommendations,
+    const arma::Col<size_t>& users)
+{
+  switch (interpolationType)
+  {
+    case AVERAGE_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     AverageInterpolation>(
+          numRecs, recommendations, users);
+      break;
+
+    case REGRESSION_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     RegressionInterpolation>(
+          numRecs, recommendations, users);
+      break;
+
+    case SIMILARITY_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     SimilarityInterpolation>(
+          numRecs, recommendations, users);
+      break;
+  }
 }
 
 //! Compute recommendations for queried users.
-template<typename NeighborSearchPolicy,
-         typename InterpolationPolicy>
-void CFModel::GetRecommendations(const size_t numRecs,
-                                 arma::Mat<size_t>& recommendations,
-                                 const arma::Col<size_t>& users)
+template<typename DecompositionPolicy, typename NormalizationPolicy>
+void CFWrapper<DecompositionPolicy, NormalizationPolicy>::GetRecommendations(
+    const NeighborSearchTypes nsType,
+    const InterpolationTypes interpolationType,
+    const size_t numRecs,
+    arma::Mat<size_t>& recommendations,
+    const arma::Col<size_t>& users)
 {
-  RecommendationVisitor<NeighborSearchPolicy, InterpolationPolicy>
-      recommendation(numRecs, recommendations, users, true);
-  boost::apply_visitor(recommendation, cf);
+  switch (nsType)
+  {
+    case COSINE_SEARCH:
+      GetRecommendationsHelper<CosineSearch>(cf, interpolationType, numRecs,
+          recommendations, users);
+      break;
+
+    case EUCLIDEAN_SEARCH:
+      GetRecommendationsHelper<EuclideanSearch>(cf, interpolationType, numRecs,
+          recommendations, users);
+      break;
+
+    case PEARSON_SEARCH:
+      GetRecommendationsHelper<PearsonSearch>(cf, interpolationType, numRecs,
+          recommendations, users);
+      break;
+  }
+}
+
+template<typename NeighborSearchPolicy, typename CFType>
+void GetRecommendationsHelper(
+    CFType& cf,
+    const InterpolationTypes interpolationType,
+    const size_t numRecs,
+    arma::Mat<size_t>& recommendations)
+{
+  switch (interpolationType)
+  {
+    case AVERAGE_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     AverageInterpolation>(
+          numRecs, recommendations);
+      break;
+
+    case REGRESSION_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     RegressionInterpolation>(
+          numRecs, recommendations);
+      break;
+
+    case SIMILARITY_INTERPOLATION:
+      cf.template GetRecommendations<NeighborSearchPolicy,
+                                     SimilarityInterpolation>(
+          numRecs, recommendations);
+      break;
+  }
 }
 
 //! Compute recommendations for all users.
-template<typename NeighborSearchPolicy,
-         typename InterpolationPolicy>
-void CFModel::GetRecommendations(const size_t numRecs,
-                                 arma::Mat<size_t>& recommendations)
+template<typename DecompositionPolicy, typename NormalizationPolicy>
+void CFWrapper<DecompositionPolicy, NormalizationPolicy>::GetRecommendations(
+    const NeighborSearchTypes nsType,
+    const InterpolationTypes interpolationType,
+    const size_t numRecs,
+    arma::Mat<size_t>& recommendations)
 {
-  arma::Col<size_t> users;
-  RecommendationVisitor<NeighborSearchPolicy, InterpolationPolicy>
-      recommendation(numRecs, recommendations, users, false);
-  boost::apply_visitor(recommendation, cf);
+  switch (nsType)
+  {
+    case COSINE_SEARCH:
+      GetRecommendationsHelper<CosineSearch>(cf, interpolationType, numRecs,
+          recommendations);
+      break;
+
+    case EUCLIDEAN_SEARCH:
+      GetRecommendationsHelper<EuclideanSearch>(cf, interpolationType, numRecs,
+          recommendations);
+      break;
+
+    case PEARSON_SEARCH:
+      GetRecommendationsHelper<PearsonSearch>(cf, interpolationType, numRecs,
+          recommendations);
+      break;
+  }
 }
 
-template <typename DecompositionPolicy,
-          typename NormalizationType>
-const CFType<DecompositionPolicy, NormalizationType>* CFModel::CFPtr() const
+template<typename DecompositionPolicy>
+CFWrapperBase* InitializeModelHelper(
+    CFModel::NormalizationTypes normalizationType)
 {
-  void* pointer = boost::apply_visitor(GetValueVisitor(), cf);
-  return (CFType<DecompositionPolicy, NormalizationType>*) pointer;
+  switch (normalizationType)
+  {
+    case CFModel::NO_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, NoNormalization>();
+
+    case CFModel::ITEM_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, ItemMeanNormalization>();
+
+    case CFModel::USER_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, UserMeanNormalization>();
+
+    case CFModel::OVERALL_MEAN_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, OverallMeanNormalization>();
+
+    case CFModel::Z_SCORE_NORMALIZATION:
+      return new CFWrapper<DecompositionPolicy, ZScoreNormalization>();
+  }
+
+  // This shouldn't ever happen.
+  return NULL;
+}
+
+inline CFWrapperBase* InitializeModel(
+    CFModel::DecompositionTypes decompositionType,
+    CFModel::NormalizationTypes normalizationType)
+{
+  switch (decompositionType)
+  {
+    case CFModel::NMF:
+      return InitializeModelHelper<NMFPolicy>(normalizationType);
+
+    case CFModel::BATCH_SVD:
+      return InitializeModelHelper<BatchSVDPolicy>(normalizationType);
+
+    case CFModel::RANDOMIZED_SVD:
+      return InitializeModelHelper<RandomizedSVDPolicy>(normalizationType);
+
+    case CFModel::REG_SVD:
+      return InitializeModelHelper<RegSVDPolicy>(normalizationType);
+
+    case CFModel::SVD_COMPLETE:
+      return InitializeModelHelper<SVDCompletePolicy>(normalizationType);
+
+    case CFModel::SVD_INCOMPLETE:
+      return InitializeModelHelper<SVDIncompletePolicy>(normalizationType);
+
+    case CFModel::BIAS_SVD:
+      return InitializeModelHelper<BiasSVDPolicy>(normalizationType);
+
+    case CFModel::SVD_PLUS_PLUS:
+      return InitializeModelHelper<SVDPlusPlusPolicy>(normalizationType);
+  }
+
+  // This shouldn't ever happen.
+  return NULL;
+};
+
+template<typename DecompositionPolicy, typename Archive>
+void SerializeHelper(Archive& ar,
+                     CFWrapperBase* cf,
+                     CFModel::NormalizationTypes normalizationType)
+{
+  switch (normalizationType)
+  {
+    case CFModel::NO_NORMALIZATION:
+      {
+        CFWrapper<DecompositionPolicy, NoNormalization>& typedModel =
+            dynamic_cast<CFWrapper<DecompositionPolicy,
+                                   NoNormalization>&>(*cf);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+
+    case CFModel::ITEM_MEAN_NORMALIZATION:
+      {
+        CFWrapper<DecompositionPolicy, ItemMeanNormalization>& typedModel =
+            dynamic_cast<CFWrapper<DecompositionPolicy,
+                                   ItemMeanNormalization>&>(*cf);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+
+    case CFModel::USER_MEAN_NORMALIZATION:
+      {
+        CFWrapper<DecompositionPolicy, UserMeanNormalization>& typedModel =
+            dynamic_cast<CFWrapper<DecompositionPolicy,
+                                   UserMeanNormalization>&>(*cf);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+
+    case CFModel::OVERALL_MEAN_NORMALIZATION:
+      {
+        CFWrapper<DecompositionPolicy, OverallMeanNormalization>& typedModel =
+            dynamic_cast<CFWrapper<DecompositionPolicy,
+                                   OverallMeanNormalization>&>(*cf);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+
+    case CFModel::Z_SCORE_NORMALIZATION:
+      {
+        CFWrapper<DecompositionPolicy, ZScoreNormalization>& typedModel =
+            dynamic_cast<CFWrapper<DecompositionPolicy,
+                                   ZScoreNormalization>&>(*cf);
+        ar(CEREAL_NVP(typedModel));
+        break;
+      }
+  }
 }
 
 template<typename Archive>
 void CFModel::serialize(Archive& ar, const uint32_t /* version */)
 {
+  ar(CEREAL_NVP(decompositionType));
+  ar(CEREAL_NVP(normalizationType));
+
   // This should never happen, but just in case, be clean with memory.
   if (cereal::is_loading<Archive>())
-    boost::apply_visitor(DeleteVisitor(), cf);
+  {
+    delete cf;
+    cf = InitializeModel(decompositionType, normalizationType);
+  }
 
-  ar(CEREAL_VARIANT_POINTER(cf));
+  // Avoid polymorphic serialization by determining the type directly.
+  switch (decompositionType)
+  {
+    case NMF:
+      SerializeHelper<NMFPolicy>(ar, cf, normalizationType);
+      break;
+
+    case BATCH_SVD:
+      SerializeHelper<BatchSVDPolicy>(ar, cf, normalizationType);
+      break;
+
+    case RANDOMIZED_SVD:
+      SerializeHelper<RandomizedSVDPolicy>(ar, cf, normalizationType);
+      break;
+
+    case REG_SVD:
+      SerializeHelper<RegSVDPolicy>(ar, cf, normalizationType);
+      break;
+
+    case SVD_COMPLETE:
+      SerializeHelper<SVDCompletePolicy>(ar, cf, normalizationType);
+      break;
+
+    case SVD_INCOMPLETE:
+      SerializeHelper<SVDIncompletePolicy>(ar, cf, normalizationType);
+      break;
+
+    case BIAS_SVD:
+      SerializeHelper<BiasSVDPolicy>(ar, cf, normalizationType);
+      break;
+
+    case SVD_PLUS_PLUS:
+      SerializeHelper<SVDPlusPlusPolicy>(ar, cf, normalizationType);
+      break;
+  }
 }
 
+} // namespace cf
+} // namespace mlpack
+
 #endif
diff --git a/src/mlpack/tests/main_tests/cf_test.cpp b/src/mlpack/tests/main_tests/cf_test.cpp
index b136d9b730..da1c8c77fc 100644
--- a/src/mlpack/tests/main_tests/cf_test.cpp
+++ b/src/mlpack/tests/main_tests/cf_test.cpp
@@ -213,13 +213,13 @@ TEST_CASE_METHOD(CFTestFixture, "CFModelReuseTest",
     IO::GetSingleton().Parameters()["algorithm"].wasPassed = false;
 
     // Reuse the model to get recommendations.
-    int recommendations = 3;
-    const int querySize = 7;
+    size_t recommendations = 3;
+    const size_t querySize = 7;
     Mat<size_t> query =
         arma::linspace<Mat<size_t>>(0, querySize - 1, querySize);
 
     SetInputParam("query", std::move(query));
-    SetInputParam("recommendations", recommendations);
+    SetInputParam("recommendations", int(recommendations));
     SetInputParam("input_model",
         std::move(IO::GetParam<CFModel*>("output_model")));
 
@@ -261,18 +261,21 @@ TEST_CASE_METHOD(CFTestFixture, "CFRankTest",
 {
   mat dataset;
   data::Load("GroupLensSmall.csv", dataset);
-  int rank = 7;
+  size_t rank = 7;
 
   SetInputParam("training", std::move(dataset));
-  SetInputParam("rank", rank);
+  SetInputParam("rank", int(rank));
   SetInputParam("max_iterations", int(10));
   SetInputParam("algorithm", std::string("NMF"));
 
   mlpackMain();
 
   const CFModel* outputModel = IO::GetParam<CFModel*>("output_model");
+  CFType<NMFPolicy, NoNormalization>& cf =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
 
-  REQUIRE(outputModel->template CFPtr<NMFPolicy>()->Rank() == rank);
+  REQUIRE(cf.Rank() == rank);
 }
 
 /**
@@ -295,10 +298,13 @@ TEST_CASE_METHOD(CFTestFixture, "CFMinResidueTest",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  outputModel =  IO::GetParam<CFModel*>("output_model");
+  outputModel = IO::GetParam<CFModel*>("output_model");
   // By default the main program use NMFPolicy.
-  const mat w1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w1 = cf.Decomposition().W();
+  const mat h1 = cf.Decomposition().H();
 
   ResetSettings();
 
@@ -314,15 +320,18 @@ TEST_CASE_METHOD(CFTestFixture, "CFMinResidueTest",
 
   outputModel = IO::GetParam<CFModel*>("output_model");
   // By default the main program use NMFPolicy.
-  const mat w2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf2 =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w2 = cf2.Decomposition().W();
+  const mat h2 = cf2.Decomposition().H();
 
   // The resulting matrices should be different.
   REQUIRE((arma::norm(w1 - w2) > 1e-5 || arma::norm(h1 - h2) > 1e-5));
 }
 
 /**
- * Test that itertaion_only_termination is used.
+ * Test that iteration_only_termination is used.
  */
 TEST_CASE_METHOD(CFTestFixture, "CFIterationOnlyTerminationTest",
                 "[CFMainTest][BindingTests]")
@@ -341,10 +350,13 @@ TEST_CASE_METHOD(CFTestFixture, "CFIterationOnlyTerminationTest",
   mlpack::math::FixedRandomSeed();
   mlpackMain();
 
-  outputModel =  IO::GetParam<CFModel*>("output_model");
+  outputModel = IO::GetParam<CFModel*>("output_model");
   // By default, the main program use NMFPolicy.
-  const mat w1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w1 = cf.Decomposition().W();
+  const mat h1 = cf.Decomposition().H();
 
   ResetSettings();
 
@@ -359,8 +371,11 @@ TEST_CASE_METHOD(CFTestFixture, "CFIterationOnlyTerminationTest",
 
   outputModel = IO::GetParam<CFModel*>("output_model");
   // By default, the main program use NMFPolicy.
-  const mat w2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf2 =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w2 = cf2.Decomposition().W();
+  const mat h2 = cf2.Decomposition().H();
 
   // The resulting matrices should be different.
   REQUIRE((arma::norm(w1 - w2) > 1e-5 || arma::norm(h1 - h2) > 1e-5));
@@ -387,8 +402,11 @@ TEST_CASE_METHOD(CFTestFixture, "CFMaxIterationsTest",
 
   outputModel =  IO::GetParam<CFModel*>("output_model");
   // By default, the main program use NMFPolicy.
-  const mat w1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h1 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w1 = cf.Decomposition().W();
+  const mat h1 = cf.Decomposition().H();
 
   ResetSettings();
 
@@ -403,8 +421,11 @@ TEST_CASE_METHOD(CFTestFixture, "CFMaxIterationsTest",
 
   outputModel = IO::GetParam<CFModel*>("output_model");
   // By default the main program use NMFPolicy.
-  const mat w2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().W();
-  const mat h2 = outputModel->template CFPtr<NMFPolicy>()->Decomposition().H();
+  CFType<NMFPolicy, NoNormalization>& cf2 =
+      dynamic_cast<CFWrapper<NMFPolicy,
+                   NoNormalization>&>(*(outputModel->CF())).CF();
+  const mat w2 = cf2.Decomposition().W();
+  const mat h2 = cf2.Decomposition().H();
 
   // The resulting matrices should be different.
   REQUIRE((arma::norm(w1 - w2) > 1e-5 || arma::norm(h1 - h2) > 1e-5));

From 3ffbfcb4d5b8d0cd4f2e09a100c9d445af246240 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 10:55:47 -0500
Subject: [PATCH 060/253] Fix warning.

---
 src/mlpack/methods/cf/cf_main.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/cf/cf_main.cpp b/src/mlpack/methods/cf/cf_main.cpp
index f4aa8e14b7..ce083c8c4a 100644
--- a/src/mlpack/methods/cf/cf_main.cpp
+++ b/src/mlpack/methods/cf/cf_main.cpp
@@ -343,7 +343,7 @@ static void mlpackMain()
     nsType = COSINE_SEARCH;
   else if (IO::GetParam<std::string>("neighbor_search") == "euclidean")
     nsType = EUCLIDEAN_SEARCH;
-  else if (IO::GetParam<std::string>("neighbor_search") == "pearson")
+  else // if (IO::GetParam<std::string>("neighbor_search") == "pearson")
     nsType = PEARSON_SEARCH;
 
   InterpolationTypes interpolationType;
@@ -353,7 +353,7 @@ static void mlpackMain()
     interpolationType = AVERAGE_INTERPOLATION;
   else if (IO::GetParam<std::string>("interpolation") == "regression")
     interpolationType = REGRESSION_INTERPOLATION;
-  else if (IO::GetParam<std::string>("interpolation") == "similarity")
+  else // if (IO::GetParam<std::string>("interpolation") == "similarity")
     interpolationType = SIMILARITY_INTERPOLATION;
 
   if (IO::HasParam("query") || IO::HasParam("all_user_recommendations"))

From 38d000059afb3e9a3d13e23b3d67b0acd3dfda6e Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 11:08:24 -0500
Subject: [PATCH 061/253] Update history.

---
 HISTORY.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index 7529a3ee86..a5e2fd7732 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -13,6 +13,9 @@
 
   * Add finalizers to Julia binding model types to fix memory handling (#2756).
 
+  * Removed `boost::visitor` from model classes for `knn`, `kfn`, `cf`,
+    `range_search`, `krann`, and `kde` bindings (#2803).
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.

From e2a0ac48fae1a1c63b2f4662d64dabcac664aa24 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 11:08:38 -0500
Subject: [PATCH 062/253] Oh, also, it's a new year.

---
 COPYRIGHT.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/COPYRIGHT.txt b/COPYRIGHT.txt
index a3581e1d03..d2d177da71 100644
--- a/COPYRIGHT.txt
+++ b/COPYRIGHT.txt
@@ -7,7 +7,7 @@ Source:
 
 Files: *
 Copyright:
-  Copyright 2008-2020, Ryan Curtin <ryan@ratml.org>
+  Copyright 2008-2021, Ryan Curtin <ryan@ratml.org>
   Copyright 2008-2013, Bill March <march@gatech.edu>
   Copyright 2008-2012, Dongryeol Lee <dongryel@cc.gatech.edu>
   Copyright 2008-2013, Nishant Mehta <niche@cc.gatech.edu>

From cd48b339d31a5451e7a77669e0523a44c1b26368 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 11 Jan 2021 17:43:20 -0500
Subject: [PATCH 063/253] Use CMake to automatically configure LICENSE file.

---
 src/mlpack/bindings/R/CMakeLists.txt          | 36 +++++++++----------
 .../bindings/R/mlpack/{LICENSE => LICENSE.in} |  2 +-
 2 files changed, 18 insertions(+), 20 deletions(-)
 rename src/mlpack/bindings/R/mlpack/{LICENSE => LICENSE.in} (69%)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index 830833b614..7352b92918 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -223,9 +223,11 @@ if (BUILD_R_BINDINGS)
     "${CMAKE_CURRENT_SOURCE_DIR}/mlpack/tests/testthat.R"
   )
 
-  set(LICENSE_SOURCES
-    "${CMAKE_CURRENT_SOURCE_DIR}/mlpack/LICENSE"
-  )
+  # Configure the license file.
+  string(TIMESTAMP LICENSE_YEAR "%Y")
+  configure_file("${CMAKE_CURRENT_SOURCE_DIR}/mlpack/LICENSE.in"
+                 "${CMAKE_CURRENT_BINARY_DIR}/mlpack/LICENSE")
+
   add_custom_target(r_copy ALL)
 
   # First we have to create all the required directories for copy.
@@ -247,22 +249,22 @@ if (BUILD_R_BINDINGS)
 
   # Copy all necessary files for building package.
   foreach(cpp_file ${CPP_SOURCES})
-  add_custom_command(TARGET r_copy PRE_BUILD
-      COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
-          ${cpp_file}
-          ${CMAKE_CURRENT_BINARY_DIR}/mlpack/src/)
+    add_custom_command(TARGET r_copy PRE_BUILD
+        COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
+            ${cpp_file}
+            ${CMAKE_CURRENT_BINARY_DIR}/mlpack/src/)
   endforeach()
   foreach(r_file ${R_SOURCES})
-  add_custom_command(TARGET r_copy PRE_BUILD
-      COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
-          ${r_file}
-          ${CMAKE_CURRENT_BINARY_DIR}/mlpack/R/)
+    add_custom_command(TARGET r_copy PRE_BUILD
+        COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
+            ${r_file}
+            ${CMAKE_CURRENT_BINARY_DIR}/mlpack/R/)
   endforeach()
   foreach(bindings_file ${BINDINGS_SOURCES})
-  add_custom_command(TARGET r_copy PRE_BUILD
-      COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
-          ${bindings_file}
-          ${CMAKE_CURRENT_BINARY_DIR}/mlpack/src/mlpack/bindings/R)
+    add_custom_command(TARGET r_copy PRE_BUILD
+        COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
+            ${bindings_file}
+            ${CMAKE_CURRENT_BINARY_DIR}/mlpack/src/mlpack/bindings/R)
   endforeach()
   add_custom_command(TARGET r_copy PRE_BUILD
       COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
@@ -272,10 +274,6 @@ if (BUILD_R_BINDINGS)
       COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
           ${R_TESTS_SOURCES}
           ${CMAKE_CURRENT_BINARY_DIR}/mlpack/tests)
-  add_custom_command(TARGET r_copy PRE_BUILD
-      COMMAND ${CMAKE_COMMAND} ARGS -E copy_if_different
-          ${LICENSE_SOURCES}
-          ${CMAKE_CURRENT_BINARY_DIR}/mlpack)
   # This file will take care of multiple definition of functions in .cpp files.
   add_custom_command(TARGET r_copy PRE_BUILD
       COMMAND ${CMAKE_COMMAND} ARGS -E touch
diff --git a/src/mlpack/bindings/R/mlpack/LICENSE b/src/mlpack/bindings/R/mlpack/LICENSE.in
similarity index 69%
rename from src/mlpack/bindings/R/mlpack/LICENSE
rename to src/mlpack/bindings/R/mlpack/LICENSE.in
index 774e59e170..188ac6207d 100644
--- a/src/mlpack/bindings/R/mlpack/LICENSE
+++ b/src/mlpack/bindings/R/mlpack/LICENSE.in
@@ -1,3 +1,3 @@
-YEAR: 2020
+YEAR: ${LICENSE_YEAR}
 COPYRIGHT HOLDER: mlpack Team
 ORGANIZATION: mlpack

From 33fb5d255fd400f1b1b181afdbc30e83df7e2f39 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 12 Jan 2021 08:59:28 -0500
Subject: [PATCH 064/253] Try to work around static code analysis issues.

---
 src/mlpack/methods/rann/ra_model_impl.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/rann/ra_model_impl.hpp b/src/mlpack/methods/rann/ra_model_impl.hpp
index e66b3b268a..443964b91a 100644
--- a/src/mlpack/methods/rann/ra_model_impl.hpp
+++ b/src/mlpack/methods/rann/ra_model_impl.hpp
@@ -83,8 +83,8 @@ void RABiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
     Timer::Start("tree_building");
     Log::Info << "Building query tree...."<< std::endl;
     std::vector<size_t> oldFromNewQueries;
-    typename RAType::Tree queryTree(std::move(querySet), oldFromNewQueries,
-        leafSize);
+    typedef typename RAType::Tree TreeType
+    TreeType queryTree(std::move(querySet), oldFromNewQueries, leafSize);
     Log::Info << "Tree Built." << std::endl;
     Timer::Stop("tree_building");
 

From aeb0f49e9f66282065c6c2b1a2b4e91b16419e6a Mon Sep 17 00:00:00 2001
From: Nippun Sharma <nippun@pop-os.localdomain>
Date: Tue, 12 Jan 2021 20:10:18 +0530
Subject: [PATCH 065/253] added inf functionality and tests

---
 .../python/tests/test_python_binding.py       | 32 +++++++++++++++
 src/mlpack/core/util/io.cpp                   | 39 +++++++++++++++----
 src/mlpack/core/util/io.hpp                   |  2 +-
 src/mlpack/core/util/mlpack_main.hpp          |  2 +-
 4 files changed, 65 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index 4d8206b16c..82ddf3dc88 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1336,5 +1336,37 @@ class TestPythonBinding(unittest.TestCase):
     self.assertEqual(output2['model_bw_out'], 20.0)
     self.assertEqual(output3['model_bw_out'], 20.0)
 
+  def testCheckInputMatricesNaN(self):
+    """
+    Checks that an exception is thrown if the input matrix contains
+    NaN values.
+    """
+    x = np.random.rand(100, 5)
+    x[0][0] = np.nan
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   matrix_in=x,
+                                                   check_input_matrices=True))
+
+  def testCheckInputMatricesInf(self):
+    """
+    Checks that an exception is thrown if the input matrix contains
+    inf values.
+    """
+    x = np.random.rand(100, 5)
+    x[0][0] = np.inf
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   matrix_in=x,
+                                                   check_input_matrices=True))
+
 if __name__ == '__main__':
   unittest.main()
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 4e1771e705..25d800a89d 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -277,41 +277,64 @@ void IO::CheckInputMatrices()
   {
     std::string paramName = itr->first;
     std::string paramType = itr->second.cppType;
-    std::string errMsg = "The input " + paramName + " has NaN values.";
+    std::string errMsg1 = "The input " + paramName + " has NaN values.";
+    std::string errMsg2 = "The input " + paramName + " has inf values.";
+
     if (paramType == "arma::mat")
     {
       if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+      if (IO::GetParam<arma::Mat<double>>(paramName).has_inf())
+      	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Mat<size_t>")
     {
       if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (IO::GetParam<arma::Mat<size_t>>(paramName).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::colvec")
     {
       if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (IO::GetParam<arma::Col<double>>(paramName).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Col<size_t>")
     {
       if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (IO::GetParam<arma::Col<size_t>>(paramName).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::rowvec")
     {
       if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (IO::GetParam<arma::Row<double>>(paramName).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Row<size_t>")
     {
       if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (IO::GetParam<arma::Row<size_t>>(paramName).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
     {
       if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_nan())
-        Log::Fatal << errMsg << std::endl;
+        Log::Fatal << errMsg1 << std::endl;
+
+	  if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_inf())
+	  	Log::Fatal << errMsg2 << std::endl;
     }
   }
 }
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index d4f5cc7a17..a435fc0121 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -286,7 +286,7 @@ class IO
   static void ClearSettings();
 
   /**
-   * Checks all input matrices for NaN values, if found throws an exception.
+   * Checks all input matrices for NaN and inf values, if found throws an exception.
    */
   static void CheckInputMatrices();
 
diff --git a/src/mlpack/core/util/mlpack_main.hpp b/src/mlpack/core/util/mlpack_main.hpp
index 0d65513225..34f8689e1a 100644
--- a/src/mlpack/core/util/mlpack_main.hpp
+++ b/src/mlpack/core/util/mlpack_main.hpp
@@ -231,7 +231,7 @@ PARAM_FLAG("copy_all_inputs", "If specified, all input parameters will be deep"
     "where the input parameters are being modified by the algorithm, but can "
     "slow down the code.", "");
 PARAM_FLAG("check_input_matrices", "If specified, the input matrix is checked for"
-    " NaN values; an exception is thrown if any are found.", "");
+    " NaN and inf values; an exception is thrown if any are found.", "");
 
 // Nothing else needs to be defined---the binding will use mlpackMain() as-is.
 

From bfff19e88dea9eb903b4b5508b8d8b00f96782a4 Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Wed, 13 Jan 2021 00:34:48 +0530
Subject: [PATCH 066/253] fixed indentations, random indices in tests, changed
 comments

---
 src/mlpack/bindings/python/py_option.hpp      |  2 +-
 .../python/tests/test_python_binding.py       |  8 +++++--
 src/mlpack/core/util/io.cpp                   | 24 +++++++++----------
 src/mlpack/core/util/io.hpp                   |  2 +-
 4 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/bindings/python/py_option.hpp b/src/mlpack/bindings/python/py_option.hpp
index 0a62afc709..b3d8519f84 100644
--- a/src/mlpack/bindings/python/py_option.hpp
+++ b/src/mlpack/bindings/python/py_option.hpp
@@ -65,7 +65,7 @@ class PyOption
     data.input = input;
     data.loaded = false;
     // Only "verbose", "copy_all_inputs" and "check_input_matrices"
-    //  will be persistent.
+    // will be persistent.
     if (identifier == "verbose" || identifier == "copy_all_inputs" ||
         identifier == "check_input_matrices")
       data.persistent = true;
diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index 82ddf3dc88..f6beffa483 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1342,7 +1342,9 @@ class TestPythonBinding(unittest.TestCase):
     NaN values.
     """
     x = np.random.rand(100, 5)
-    x[0][0] = np.nan
+    a = np.random.randint(low=0, high=100)
+    b = np.random.randint(low=0, high=5)
+    x[a][b] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1358,7 +1360,9 @@ class TestPythonBinding(unittest.TestCase):
     inf values.
     """
     x = np.random.rand(100, 5)
-    x[0][0] = np.inf
+    a = np.random.randint(low=0, high=100)
+    b = np.random.randint(low=0, high=5)
+    x[a][b] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 25d800a89d..9de3825595 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -293,48 +293,48 @@ void IO::CheckInputMatrices()
       if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (IO::GetParam<arma::Mat<size_t>>(paramName).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::colvec")
     {
       if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (IO::GetParam<arma::Col<double>>(paramName).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (IO::GetParam<arma::Col<double>>(paramName).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Col<size_t>")
     {
       if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (IO::GetParam<arma::Col<size_t>>(paramName).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (IO::GetParam<arma::Col<size_t>>(paramName).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::rowvec")
     {
       if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (IO::GetParam<arma::Row<double>>(paramName).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (IO::GetParam<arma::Row<double>>(paramName).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Row<size_t>")
     {
       if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (IO::GetParam<arma::Row<size_t>>(paramName).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (IO::GetParam<arma::Row<size_t>>(paramName).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
     {
       if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_nan())
         Log::Fatal << errMsg1 << std::endl;
 
-	  if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_inf())
-	  	Log::Fatal << errMsg2 << std::endl;
+      if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
     }
   }
 }
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index a435fc0121..dbe75da481 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -286,7 +286,7 @@ class IO
   static void ClearSettings();
 
   /**
-   * Checks all input matrices for NaN and inf values, if found throws an exception.
+   * Checks all input matrices for NaN and inf values, exits if found any.
    */
   static void CheckInputMatrices();
 

From 7056aebcdf8dac50aeba1004154761190d7640df Mon Sep 17 00:00:00 2001
From: NippunSharma <inbox.nippun@gmail.com>
Date: Wed, 13 Jan 2021 00:38:25 +0530
Subject: [PATCH 067/253] fixed indent

---
 src/mlpack/core/util/io.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 9de3825595..fcd6a002e2 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -286,7 +286,7 @@ void IO::CheckInputMatrices()
         Log::Fatal << errMsg1 << std::endl;
 
       if (IO::GetParam<arma::Mat<double>>(paramName).has_inf())
-      	Log::Fatal << errMsg2 << std::endl;
+        Log::Fatal << errMsg2 << std::endl;
     }
     else if (paramType == "arma::Mat<size_t>")
     {

From 4de66bbf0ad0cdb4a7a82ad7e7e6f8eef728d7e6 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 12 Jan 2021 20:22:00 -0500
Subject: [PATCH 068/253] Um, right, C++ needs semicolons...

---
 src/mlpack/methods/rann/ra_model_impl.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/rann/ra_model_impl.hpp b/src/mlpack/methods/rann/ra_model_impl.hpp
index 443964b91a..30bed21c01 100644
--- a/src/mlpack/methods/rann/ra_model_impl.hpp
+++ b/src/mlpack/methods/rann/ra_model_impl.hpp
@@ -83,7 +83,7 @@ void RABiSearchVisitor<SortPolicy>::SearchLeaf(RAType* ra) const
     Timer::Start("tree_building");
     Log::Info << "Building query tree...."<< std::endl;
     std::vector<size_t> oldFromNewQueries;
-    typedef typename RAType::Tree TreeType
+    typedef typename RAType::Tree TreeType;
     TreeType queryTree(std::move(querySet), oldFromNewQueries, leafSize);
     Log::Info << "Tree Built." << std::endl;
     Timer::Stop("tree_building");

From f385522a5218fb644fced6ca164e137b098ab77e Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Tue, 12 Jan 2021 20:25:42 -0500
Subject: [PATCH 069/253] Update src/mlpack/bindings/R/CMakeLists.txt

Co-authored-by: Yashwant Singh Parihar <Yashwantsingh.sngh@gmail.com>
---
 src/mlpack/bindings/R/CMakeLists.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/bindings/R/CMakeLists.txt b/src/mlpack/bindings/R/CMakeLists.txt
index 13f171140d..f5f6907159 100644
--- a/src/mlpack/bindings/R/CMakeLists.txt
+++ b/src/mlpack/bindings/R/CMakeLists.txt
@@ -229,7 +229,7 @@ if (BUILD_R_BINDINGS)
   # Installation script for the packagae.
   install(CODE
       "execute_process(
-         COMMAND R CMD INSTALL mlpack_${PACKAGE_VERSION}.tar.gz
+         COMMAND ${R_EXECUTABLE} CMD INSTALL mlpack_${PACKAGE_VERSION}.tar.gz
          WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})"
   )
 

From 5e0a3472cd4e9ae012026a37f31caa50d02e1f93 Mon Sep 17 00:00:00 2001
From: Nippun Sharma <nippun@pop-os.localdomain>
Date: Wed, 13 Jan 2021 12:05:12 +0530
Subject: [PATCH 070/253] added templated utility function

---
 src/mlpack/core/util/io.cpp      | 58 ++++----------------------------
 src/mlpack/core/util/io.hpp      |  8 +++++
 src/mlpack/core/util/io_impl.hpp | 13 +++++++
 3 files changed, 28 insertions(+), 51 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index fcd6a002e2..2f1b4792ad 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -277,65 +277,21 @@ void IO::CheckInputMatrices()
   {
     std::string paramName = itr->first;
     std::string paramType = itr->second.cppType;
-    std::string errMsg1 = "The input " + paramName + " has NaN values.";
-    std::string errMsg2 = "The input " + paramName + " has inf values.";
 
     if (paramType == "arma::mat")
-    {
-      if (IO::GetParam<arma::Mat<double>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Mat<double>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Mat<double>>(paramName);
     else if (paramType == "arma::Mat<size_t>")
-    {
-      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Mat<size_t>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Mat<size_t>>(paramName);
     else if (paramType == "arma::colvec")
-    {
-      if (IO::GetParam<arma::Col<double>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Col<double>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Col<double>>(paramName);
     else if (paramType == "arma::Col<size_t>")
-    {
-      if (IO::GetParam<arma::Col<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Col<size_t>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Col<size_t>>(paramName);
     else if (paramType == "arma::rowvec")
-    {
-      if (IO::GetParam<arma::Row<double>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Row<double>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Row<double>>(paramName);
     else if (paramType == "arma::Row<size_t>")
-    {
-      if (IO::GetParam<arma::Row<size_t>>(paramName).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (IO::GetParam<arma::Row<size_t>>(paramName).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Row<size_t>>(paramName);
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
-    {
-      if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-
-      if (std::get<1>(IO::GetParam<TupleType>(paramName)).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<TupleType>(paramName);
   }
 }
 
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index dbe75da481..0633fd8c5d 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -285,6 +285,14 @@ class IO
    */
   static void ClearSettings();
 
+  /**
+   * Utility function for CheckInputMatrices().
+   *
+   * @param matrix Matrix to check for NaN or Inf values.
+   */
+  template<typename T>
+  static void CheckInputMatrix(T& matrix);
+
   /**
    * Checks all input matrices for NaN and inf values, exits if found any.
    */
diff --git a/src/mlpack/core/util/io_impl.hpp b/src/mlpack/core/util/io_impl.hpp
index feb892325c..e40d5824dc 100644
--- a/src/mlpack/core/util/io_impl.hpp
+++ b/src/mlpack/core/util/io_impl.hpp
@@ -145,6 +145,19 @@ T& IO::GetRawParam(const std::string& identifier)
   }
 }
 
+template<typename T>
+void CheckInputMatrix(const std::string paramName)
+{
+  std::string errMsg1 = "The input " + paramName + " has NaN values.";
+  std::string errMsg2 = "The input " + paramName + " has inf values.";
+
+  if (IO::GetParam<T>(paramName).has_nan())
+    Log::Fatal << errMsg1 << std::endl;
+
+  if (IO::GetParam<T>(paramName).has_inf())
+    Log::Fatal << errMsg2 << std::endl;
+}
+
 } // namespace mlpack
 
 #endif

From dc398bfb6418e045bfa84040c812b57a881e6712 Mon Sep 17 00:00:00 2001
From: Nippun Sharma <nippun@pop-os.localdomain>
Date: Wed, 13 Jan 2021 12:11:51 +0530
Subject: [PATCH 071/253] fixing errors

---
 src/mlpack/core/util/io.hpp      |  4 ++--
 src/mlpack/core/util/io_impl.hpp | 10 +++++-----
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index 0633fd8c5d..26571659d4 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -288,10 +288,10 @@ class IO
   /**
    * Utility function for CheckInputMatrices().
    *
-   * @param matrix Matrix to check for NaN or Inf values.
+   * @param identifier Name of the parameter in question.
    */
   template<typename T>
-  static void CheckInputMatrix(T& matrix);
+  static void CheckInputMatrix(const std::string& identifier);
 
   /**
    * Checks all input matrices for NaN and inf values, exits if found any.
diff --git a/src/mlpack/core/util/io_impl.hpp b/src/mlpack/core/util/io_impl.hpp
index e40d5824dc..59a68418c3 100644
--- a/src/mlpack/core/util/io_impl.hpp
+++ b/src/mlpack/core/util/io_impl.hpp
@@ -146,15 +146,15 @@ T& IO::GetRawParam(const std::string& identifier)
 }
 
 template<typename T>
-void CheckInputMatrix(const std::string paramName)
+void CheckInputMatrix(const std::string& identifier)
 {
-  std::string errMsg1 = "The input " + paramName + " has NaN values.";
-  std::string errMsg2 = "The input " + paramName + " has inf values.";
+  std::string errMsg1 = "The input " + identifier + " has NaN values.";
+  std::string errMsg2 = "The input " + identifier + " has inf values.";
 
-  if (IO::GetParam<T>(paramName).has_nan())
+  if (IO::GetParam<T>(identifier).has_nan())
     Log::Fatal << errMsg1 << std::endl;
 
-  if (IO::GetParam<T>(paramName).has_inf())
+  if (IO::GetParam<T>(identifier).has_inf())
     Log::Fatal << errMsg2 << std::endl;
 }
 

From 6ad120aa6e04cad6fc0cbf958042e998dbcb307e Mon Sep 17 00:00:00 2001
From: Nippun Sharma <nippun@pop-os.localdomain>
Date: Wed, 13 Jan 2021 17:38:39 +0530
Subject: [PATCH 072/253] added CheckInputMatrix() to reduce code block in
 CheckInputMatrices()

---
 src/mlpack/core/util/io.cpp      | 17 +++++++++++++++++
 src/mlpack/core/util/io.hpp      | 16 ++++++++--------
 src/mlpack/core/util/io_impl.hpp |  7 +++----
 3 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 2f1b4792ad..8998f331bb 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -268,6 +268,23 @@ void IO::ClearSettings()
   GetSingleton().functionMap = persistentFunctions;
 }
 
+// For handling std::tuple<data::DatasetInfo, arma::mat>
+// seperately.
+template<>
+void IO::CheckInputMatrix<std::tuple<data::DatasetInfo, arma::mat>>(
+  const std::string& identifier)
+{
+  typedef typename std::tuple<data::DatasetInfo, arma::mat> TupleType;
+
+  std::string errMsg1 = "The input " + identifier + " has NaN values.";
+  std::string errMsg2 = "The input " + identifier + " has inf values.";
+
+  if (std::get<1>(IO::GetParam<TupleType>(identifier)).has_nan())
+    Log::Fatal << errMsg1 << std::endl;
+  if (std::get<1>(IO::GetParam<TupleType>(identifier)).has_inf())
+    Log::Fatal << errMsg2 << std::endl;
+}
+
 void IO::CheckInputMatrices()
 {
   typedef typename std::tuple<data::DatasetInfo, arma::mat> TupleType;
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index 26571659d4..5189695abe 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -219,6 +219,14 @@ class IO
   template<typename T>
   static T& GetRawParam(const std::string& identifier);
 
+  /**
+   * Utility function for CheckInputMatrices().
+   *
+   * @param identifier Name of the parameter in question.
+   */
+  template<typename T>
+  static void CheckInputMatrix(const std::string& identifier);
+
   /**
    * Given two (matrix) parameters, ensure that the first is an in-place copy of
    * the second.  This will generally do nothing (as the bindings already do
@@ -285,14 +293,6 @@ class IO
    */
   static void ClearSettings();
 
-  /**
-   * Utility function for CheckInputMatrices().
-   *
-   * @param identifier Name of the parameter in question.
-   */
-  template<typename T>
-  static void CheckInputMatrix(const std::string& identifier);
-
   /**
    * Checks all input matrices for NaN and inf values, exits if found any.
    */
diff --git a/src/mlpack/core/util/io_impl.hpp b/src/mlpack/core/util/io_impl.hpp
index 59a68418c3..f54aaa4eab 100644
--- a/src/mlpack/core/util/io_impl.hpp
+++ b/src/mlpack/core/util/io_impl.hpp
@@ -146,15 +146,14 @@ T& IO::GetRawParam(const std::string& identifier)
 }
 
 template<typename T>
-void CheckInputMatrix(const std::string& identifier)
+void IO::CheckInputMatrix(const std::string& identifier)
 {
   std::string errMsg1 = "The input " + identifier + " has NaN values.";
   std::string errMsg2 = "The input " + identifier + " has inf values.";
 
-  if (IO::GetParam<T>(identifier).has_nan())
+  if (GetParam<T>(identifier).has_nan())
     Log::Fatal << errMsg1 << std::endl;
-
-  if (IO::GetParam<T>(identifier).has_inf())
+  if (GetParam<T>(identifier).has_inf())
     Log::Fatal << errMsg2 << std::endl;
 }
 

From 04dee7ee870c3cae86fe4baa0ac058de736e75b3 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Wed, 13 Jan 2021 18:23:07 +0530
Subject: [PATCH 073/253] fix errors

---
 src/mlpack/core/util/io.cpp | 27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 8998f331bb..d36b287a4e 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -268,23 +268,6 @@ void IO::ClearSettings()
   GetSingleton().functionMap = persistentFunctions;
 }
 
-// For handling std::tuple<data::DatasetInfo, arma::mat>
-// seperately.
-template<>
-void IO::CheckInputMatrix<std::tuple<data::DatasetInfo, arma::mat>>(
-  const std::string& identifier)
-{
-  typedef typename std::tuple<data::DatasetInfo, arma::mat> TupleType;
-
-  std::string errMsg1 = "The input " + identifier + " has NaN values.";
-  std::string errMsg2 = "The input " + identifier + " has inf values.";
-
-  if (std::get<1>(IO::GetParam<TupleType>(identifier)).has_nan())
-    Log::Fatal << errMsg1 << std::endl;
-  if (std::get<1>(IO::GetParam<TupleType>(identifier)).has_inf())
-    Log::Fatal << errMsg2 << std::endl;
-}
-
 void IO::CheckInputMatrices()
 {
   typedef typename std::tuple<data::DatasetInfo, arma::mat> TupleType;
@@ -308,7 +291,15 @@ void IO::CheckInputMatrices()
     else if (paramType == "arma::Row<size_t>")
       IO::CheckInputMatrix<arma::Row<size_t>>(paramName);
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
-      IO::CheckInputMatrix<TupleType>(paramName);
+    {
+      std::string errMsg1 = "The input " + paramName + " has NaN values.";
+      std::string errMsg2 = "The input " + paramName + " has inf values.";
+
+      if (std::get<1>(GetParam<TupleType>(paramName)).has_nan())
+        Log::Fatal << errMsg1 << std::endl;
+      if (std::get<1>(GetParam<TupleType>(paramName)).has_inf())
+        Log::Fatal << errMsg2 << std::endl;
+    }
   }
 }
 

From 448b1010dae820e1602f0125c5e8cf1ab33bfbea Mon Sep 17 00:00:00 2001
From: Marcus Edel <marcus.edel@fu-berlin.de>
Date: Wed, 13 Jan 2021 21:58:34 +0100
Subject: [PATCH 074/253] Minor style improvement.

---
 src/mlpack/methods/pca/pca_impl.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/pca/pca_impl.hpp b/src/mlpack/methods/pca/pca_impl.hpp
index a122cd7159..f469933c14 100644
--- a/src/mlpack/methods/pca/pca_impl.hpp
+++ b/src/mlpack/methods/pca/pca_impl.hpp
@@ -78,8 +78,8 @@ void PCA<DecompositionPolicy>::Apply(const arma::mat& data,
 /**
  * Apply Principal Component Analysis to the provided data set.
  *
- * @param data - Data matrix
- * @param transformedData - Data with PCA applied
+ * @param data - Data matrix.
+ * @param transformedData Data with PCA applied.
  */
 template<typename DecompositionPolicy>
 void PCA<DecompositionPolicy>::Apply(const arma::mat& data,

From c8227266bf5c0fc83e6098bee8e76874d0b282d5 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Thu, 14 Jan 2021 14:24:34 -0500
Subject: [PATCH 075/253] add move assignment operator

---
 .../methods/adaboost/adaboost_model.cpp       | 39 ++++++++++++++-----
 .../methods/adaboost/adaboost_model.hpp       |  3 ++
 2 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/methods/adaboost/adaboost_model.cpp b/src/mlpack/methods/adaboost/adaboost_model.cpp
index a48659b4bd..d71b857d74 100644
--- a/src/mlpack/methods/adaboost/adaboost_model.cpp
+++ b/src/mlpack/methods/adaboost/adaboost_model.cpp
@@ -72,19 +72,40 @@ AdaBoostModel::AdaBoostModel(AdaBoostModel&& other) :
 //! Copy assignment operator.
 AdaBoostModel& AdaBoostModel::operator=(const AdaBoostModel& other)
 {
-  mappings = other.mappings;
-  weakLearnerType = other.weakLearnerType;
+  if (this != &other)
+  {
+    mappings = other.mappings;
+    weakLearnerType = other.weakLearnerType;
 
-  delete dsBoost;
-  dsBoost = (other.dsBoost == NULL) ? NULL :
-      new AdaBoost<ID3DecisionStump>(*other.dsBoost);
+    delete dsBoost;
+    dsBoost = (other.dsBoost == NULL) ? NULL :
+        new AdaBoost<ID3DecisionStump>(*other.dsBoost);
 
-  delete pBoost;
-  pBoost = (other.pBoost == NULL) ? NULL :
-      new AdaBoost<Perceptron<>>(*other.pBoost);
+    delete pBoost;
+    pBoost = (other.pBoost == NULL) ? NULL :
+        new AdaBoost<Perceptron<>>(*other.pBoost);
 
-  dimensionality = other.dimensionality;
+    dimensionality = other.dimensionality;
+  }
+  return *this;
+}
 
+//! Move assignment operator.
+AdaBoostModel& AdaBoostModel::operator=(AdaBoostModel&& other)
+{
+  if (this != &other)
+  {
+    mappings = std::move(other.mappings);
+    weakLearnerType = other.weakLearnerType;
+
+    dsBoost = other.dsBoost;
+    other.dsBoost = nullptr;
+
+    pBoost = other.pBoost;
+    other.pBoost = nullptr;
+
+    dimensionality = other.dimensionality;
+  }
   return *this;
 }
 
diff --git a/src/mlpack/methods/adaboost/adaboost_model.hpp b/src/mlpack/methods/adaboost/adaboost_model.hpp
index e8dcac3a82..36743c4e18 100644
--- a/src/mlpack/methods/adaboost/adaboost_model.hpp
+++ b/src/mlpack/methods/adaboost/adaboost_model.hpp
@@ -61,6 +61,9 @@ class AdaBoostModel
   //! Copy assignment operator.
   AdaBoostModel& operator=(const AdaBoostModel& other);
 
+  //! Move assignment operator.
+  AdaBoostModel& operator=(AdaBoostModel&& other);
+
   //! Clean up memory.
   ~AdaBoostModel();
 

From b442b8c33c3794c0840ab9a810ef16d63c1893fb Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 00:17:30 -0500
Subject: [PATCH 076/253] add move assignment for hrectbound

---
 src/mlpack/core/tree/hrectbound.hpp      |  4 +++
 src/mlpack/core/tree/hrectbound_impl.hpp | 31 ++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/src/mlpack/core/tree/hrectbound.hpp b/src/mlpack/core/tree/hrectbound.hpp
index 1d15fe6582..31186f621d 100644
--- a/src/mlpack/core/tree/hrectbound.hpp
+++ b/src/mlpack/core/tree/hrectbound.hpp
@@ -73,12 +73,16 @@ class HRectBound
 
   //! Copy constructor; necessary to prevent memory leaks.
   HRectBound(const HRectBound& other);
+
   //! Same as copy constructor; necessary to prevent memory leaks.
   HRectBound& operator=(const HRectBound& other);
 
   //! Move constructor: take possession of another bound's information.
   HRectBound(HRectBound&& other);
 
+  //! Move assignment operator
+  HRectBound& operator=(HRectBound&& other);
+
   //! Destructor: clean up memory.
   ~HRectBound();
 
diff --git a/src/mlpack/core/tree/hrectbound_impl.hpp b/src/mlpack/core/tree/hrectbound_impl.hpp
index 2b73eb020a..26132e50a5 100644
--- a/src/mlpack/core/tree/hrectbound_impl.hpp
+++ b/src/mlpack/core/tree/hrectbound_impl.hpp
@@ -103,6 +103,37 @@ inline HRectBound<MetricType, ElemType>::HRectBound(
   other.minWidth = 0.0;
 }
 
+/**
+ * Move assignment operator
+ */
+template<typename MetricType, typename ElemType>
+inline HRectBound<
+    MetricType,
+    ElemType>& HRectBound<MetricType,
+    ElemType>::operator=(HRectBound<MetricType, ElemType>&& other)
+{
+  if (this != &other)
+  {
+    if (dim != other.Dim())
+    {
+      // Reallocation is necessary.
+      if (bounds)
+        delete[] bounds;
+
+      dim = other.Dim();
+      bounds = new math::RangeType<ElemType>[dim];
+    }
+
+    // Now move each of the bound values.
+    // cannot move the bound pointer because there are no accessor method to the bound pointer
+    for (size_t i = 0; i < dim; ++i)
+      bounds[i] = std::move(other[i]);
+
+    minWidth = std::move(other.MinWidth());
+  }
+  return *this;
+}
+
 /**
  * Destructor: clean up memory.
  */

From 8eab8c47df197d9e02c17f60ec4626651c8db72f Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 00:22:27 -0500
Subject: [PATCH 077/253] fix hrectbound move assignment

---
 src/mlpack/core/tree/hrectbound_impl.hpp | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/core/tree/hrectbound_impl.hpp b/src/mlpack/core/tree/hrectbound_impl.hpp
index 26132e50a5..45d4b81a76 100644
--- a/src/mlpack/core/tree/hrectbound_impl.hpp
+++ b/src/mlpack/core/tree/hrectbound_impl.hpp
@@ -114,22 +114,12 @@ inline HRectBound<
 {
   if (this != &other)
   {
-    if (dim != other.Dim())
-    {
-      // Reallocation is necessary.
-      if (bounds)
-        delete[] bounds;
-
-      dim = other.Dim();
-      bounds = new math::RangeType<ElemType>[dim];
-    }
-
-    // Now move each of the bound values.
-    // cannot move the bound pointer because there are no accessor method to the bound pointer
-    for (size_t i = 0; i < dim; ++i)
-      bounds[i] = std::move(other[i]);
-
-    minWidth = std::move(other.MinWidth());
+    bounds = other.bounds;
+    minWidth = other.minWidth;
+    dim = other.dim;
+    other.dim = 0;
+    other.bounds = nullptr;
+    other.minWidth = 0.0;
   }
   return *this;
 }

From 30e98ec05a814ecc2bc1c7d26759f880b41693d1 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 00:27:02 -0500
Subject: [PATCH 078/253] ball bound move assignment operator

---
 src/mlpack/core/tree/ballbound.hpp      |  3 +++
 src/mlpack/core/tree/ballbound_impl.hpp | 16 ++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/src/mlpack/core/tree/ballbound.hpp b/src/mlpack/core/tree/ballbound.hpp
index 0d6633f7ca..e1a8674f03 100644
--- a/src/mlpack/core/tree/ballbound.hpp
+++ b/src/mlpack/core/tree/ballbound.hpp
@@ -81,6 +81,9 @@ class BallBound
   //! Move constructor: take possession of another bound.
   BallBound(BallBound&& other);
 
+  //! Move assignment operator.
+  BallBound& operator=(BallBound&& other);
+
   //! Destructor to release allocated memory.
   ~BallBound();
 
diff --git a/src/mlpack/core/tree/ballbound_impl.hpp b/src/mlpack/core/tree/ballbound_impl.hpp
index 59ef8bffc3..d1e5af2c06 100644
--- a/src/mlpack/core/tree/ballbound_impl.hpp
+++ b/src/mlpack/core/tree/ballbound_impl.hpp
@@ -92,6 +92,22 @@ BallBound<MetricType, VecType>::BallBound(BallBound&& other) :
   other.ownsMetric = false;
 }
 
+//! Move assignment operator.
+template<typename MetricType, typename VecType>
+BallBound<MetricType, VecType>& BallBound<MetricType, VecType>::operator=(
+    BallBound&& other)
+{
+  radius = other.radius,
+  center = std::move(other.center),
+  metric = other.metric,
+  ownsMetric = other.ownsMetric
+
+  other.radius = 0.0;
+  other.center = VecType();
+  other.metric = nullptr;
+  other.ownsMetric = false;
+}
+
 //! Destructor to release allocated memory.
 template<typename MetricType, typename VecType>
 BallBound<MetricType, VecType>::~BallBound()

From 4abbb39aec00dd178b1119e9cc84c9702f7192bb Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 00:31:14 -0500
Subject: [PATCH 079/253] add move assignment operator and fix static code
 check

---
 src/mlpack/core/tree/hollow_ball_bound.hpp    |  3 ++
 .../core/tree/hollow_ball_bound_impl.hpp      | 41 +++++++++++++++----
 2 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/core/tree/hollow_ball_bound.hpp b/src/mlpack/core/tree/hollow_ball_bound.hpp
index d8b65dcf87..d699eab693 100644
--- a/src/mlpack/core/tree/hollow_ball_bound.hpp
+++ b/src/mlpack/core/tree/hollow_ball_bound.hpp
@@ -86,6 +86,9 @@ class HollowBallBound
   //! Move constructor: take possession of another bound.
   HollowBallBound(HollowBallBound&& other);
 
+  //! Move assignment operator.
+  HollowBallBound& operator=(HollowBallBound&& other);
+
   //! Destructor to release allocated memory.
   ~HollowBallBound();
 
diff --git a/src/mlpack/core/tree/hollow_ball_bound_impl.hpp b/src/mlpack/core/tree/hollow_ball_bound_impl.hpp
index b8446ec350..8ccd06225c 100644
--- a/src/mlpack/core/tree/hollow_ball_bound_impl.hpp
+++ b/src/mlpack/core/tree/hollow_ball_bound_impl.hpp
@@ -80,15 +80,17 @@ template<typename TMetricType, typename ElemType>
 HollowBallBound<TMetricType, ElemType>& HollowBallBound<TMetricType, ElemType>::
 operator=(const HollowBallBound& other)
 {
-  if (ownsMetric)
-    delete metric;
-
-  radii = other.radii;
-  center = other.center;
-  hollowCenter = other.hollowCenter;
-  metric = other.metric;
-  ownsMetric = false;
+  if (this != &other)
+  {
+    if (ownsMetric)
+      delete metric;
 
+    radii = other.radii;
+    center = other.center;
+    hollowCenter = other.hollowCenter;
+    metric = other.metric;
+    ownsMetric = false;
+  }
   return *this;
 }
 
@@ -111,6 +113,29 @@ HollowBallBound<TMetricType, ElemType>::HollowBallBound(
   other.ownsMetric = false;
 }
 
+//! Move assignment operator.
+template<typename TMetricType, typename ElemType>
+HollowBallBound<TMetricType, ElemType>& HollowBallBound<TMetricType, ElemType>::
+operator=(HollowBallBound&& other)
+{
+  if (this != &other)
+  {
+    radii = other.radii;
+    center = std::move(other.center);
+    hollowCenter = std::move(other.hollowCenter);
+    metric = other.metric;
+    ownsMetric = other.ownsMetric;
+
+    other.radii.Hi() = 0.0;
+    other.radii.Lo() = 0.0;
+    other.center = arma::Col<ElemType>();
+    other.hollowCenter = arma::Col<ElemType>();
+    other.metric = nullptr;
+    other.ownsMetric = false;
+  }
+  return *this;
+}
+
 //! Destructor to release allocated memory.
 template<typename TMetricType, typename ElemType>
 HollowBallBound<TMetricType, ElemType>::~HollowBallBound()

From f02eb1464137f02733fc42bdd9d904e933c6d9f5 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 08:58:19 -0500
Subject: [PATCH 080/253] fix error

---
 src/mlpack/core/tree/ballbound_impl.hpp | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/core/tree/ballbound_impl.hpp b/src/mlpack/core/tree/ballbound_impl.hpp
index d1e5af2c06..5722fb854a 100644
--- a/src/mlpack/core/tree/ballbound_impl.hpp
+++ b/src/mlpack/core/tree/ballbound_impl.hpp
@@ -97,10 +97,10 @@ template<typename MetricType, typename VecType>
 BallBound<MetricType, VecType>& BallBound<MetricType, VecType>::operator=(
     BallBound&& other)
 {
-  radius = other.radius,
-  center = std::move(other.center),
-  metric = other.metric,
-  ownsMetric = other.ownsMetric
+  radius = other.radius;
+  center = std::move(other.center);
+  metric = other.metric;
+  ownsMetric = other.ownsMetric;
 
   other.radius = 0.0;
   other.center = VecType();

From cd42db9f0aea1c2e9c33dbed4bcbc310fe6fdefd Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 15 Jan 2021 21:54:14 -0500
Subject: [PATCH 081/253] continue fixing static code check

---
 .../rectangle_tree/discrete_hilbert_value.hpp |  8 ++
 .../discrete_hilbert_value_impl.hpp           | 21 +++++
 .../simple_residue_termination.hpp            | 10 ++-
 .../svd_complete_incremental_learning.hpp     |  4 +-
 .../svd_incomplete_incremental_learning.hpp   |  2 +-
 src/mlpack/methods/fastmks/fastmks.hpp        |  5 ++
 src/mlpack/methods/fastmks/fastmks_impl.hpp   | 29 ++++++
 src/mlpack/methods/fastmks/fastmks_model.cpp  | 90 ++++++++++++-------
 src/mlpack/methods/fastmks/fastmks_model.hpp  |  3 +
 src/mlpack/methods/hmm/hmm_model.hpp          | 14 +++
 .../methods/range_search/range_search.hpp     | 14 ++-
 .../range_search/range_search_impl.hpp        | 77 ++++++++++++----
 12 files changed, 219 insertions(+), 58 deletions(-)

diff --git a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
index 405188a4f6..32bb94ece9 100644
--- a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
+++ b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
@@ -182,6 +182,14 @@ class DiscreteHilbertValue
    */
   DiscreteHilbertValue& operator=(const DiscreteHilbertValue& val);
 
+   /**
+   * Move the local Hilbert object.
+   *
+   * @param val The DiscreteHilbertValue object from which the dataset
+   *    will be copied.
+   */
+  DiscreteHilbertValue& operator=(DiscreteHilbertValue&& val);
+
   /**
    * Nullify the localHilbertValues pointer in order to prevent an invalid free.
    */
diff --git a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
index c4baa38a90..48ad8557f7 100644
--- a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
+++ b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
@@ -450,6 +450,27 @@ operator=(const DiscreteHilbertValue& val)
   return *this;
 }
 
+template<typename TreeElemType>
+DiscreteHilbertValue<TreeElemType>& DiscreteHilbertValue<TreeElemType>::
+operator=(DiscreteHilbertValue&& other)
+{
+  if (this != &other)
+  {
+    localHilbertValues = other.localHilbertValues;
+    ownsLocalHilbertValues = other.ownsLocalHilbertValues;
+    numValues = other.numValues;
+    valueToInsert = other.valueToInsert;
+    ownsValueToInsert = other.ownsValueToInsert;
+
+    other.localHilbertValues = nullptr;
+    other.ownsLocalHilbertValues = false;
+    other.numValues = 0;
+    other.valueToInsert = nullptr;
+    other.ownsValueToInsert = false;
+  }
+  return *this;
+}
+
 template<typename TreeElemType>
 void DiscreteHilbertValue<TreeElemType>::NullifyData()
 {
diff --git a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
index 970b24289f..81893f4fa3 100644
--- a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
@@ -41,7 +41,15 @@ class SimpleResidueTermination
    */
   SimpleResidueTermination(const double minResidue = 1e-5,
                            const size_t maxIterations = 10000)
-      : minResidue(minResidue), maxIterations(maxIterations) { }
+      : minResidue(minResidue), 
+        maxIterations(maxIterations), 
+        residue(0.0), 
+        iteration(0), 
+        nm(0), 
+        normOld(0) 
+  { 
+    // Nothing to do here.
+  }
 
   /**
    * Initializes the termination policy before stating the factorization.
diff --git a/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp b/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
index 4ab1c0d610..37b7ab8c0a 100644
--- a/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
+++ b/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
@@ -56,7 +56,7 @@ class SVDCompleteIncrementalLearning
   SVDCompleteIncrementalLearning(double u = 0.0001,
                                  double kw = 0,
                                  double kh = 0)
-            : u(u), kw(kw), kh(kh)
+            : u(u), kw(kw), kh(kh), currentUserIndex(0), currentItemIndex(0)
   {
     // Nothing to do.
   }
@@ -172,7 +172,7 @@ class SVDCompleteIncrementalLearning<arma::sp_mat>
   SVDCompleteIncrementalLearning(double u = 0.01,
                                  double kw = 0,
                                  double kh = 0)
-            : u(u), kw(kw), kh(kh), it(NULL)
+            : u(u), kw(kw), kh(kh), it(NULL), m(0), n(0), isStart(false)
     {}
 
   ~SVDCompleteIncrementalLearning()
diff --git a/src/mlpack/methods/amf/update_rules/svd_incomplete_incremental_learning.hpp b/src/mlpack/methods/amf/update_rules/svd_incomplete_incremental_learning.hpp
index 0082824129..9880ea2945 100644
--- a/src/mlpack/methods/amf/update_rules/svd_incomplete_incremental_learning.hpp
+++ b/src/mlpack/methods/amf/update_rules/svd_incomplete_incremental_learning.hpp
@@ -53,7 +53,7 @@ class SVDIncompleteIncrementalLearning
   SVDIncompleteIncrementalLearning(double u = 0.001,
                                    double kw = 0,
                                    double kh = 0)
-          : u(u), kw(kw), kh(kh)
+          : u(u), kw(kw), kh(kh), currentUserIndex(0)
   {
     // Nothing to do.
   }
diff --git a/src/mlpack/methods/fastmks/fastmks.hpp b/src/mlpack/methods/fastmks/fastmks.hpp
index 93d234d541..ea2057b0b9 100644
--- a/src/mlpack/methods/fastmks/fastmks.hpp
+++ b/src/mlpack/methods/fastmks/fastmks.hpp
@@ -163,6 +163,11 @@ class FastMKS
    */
   FastMKS& operator=(const FastMKS& other);
 
+  /**
+   * Move assignment operator.
+   */
+  FastMKS& operator=(FastMKS&& other);
+
   //! Destructor for the FastMKS object.
   ~FastMKS();
 
diff --git a/src/mlpack/methods/fastmks/fastmks_impl.hpp b/src/mlpack/methods/fastmks/fastmks_impl.hpp
index 660617fdb0..3b2d12eaae 100644
--- a/src/mlpack/methods/fastmks/fastmks_impl.hpp
+++ b/src/mlpack/methods/fastmks/fastmks_impl.hpp
@@ -250,6 +250,35 @@ FastMKS<KernelType, MatType, TreeType>::operator=(const FastMKS& other)
   naive = other.naive;
 }
 
+template<typename KernelType,
+         typename MatType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+FastMKS<KernelType, MatType, TreeType>&
+FastMKS<KernelType, MatType, TreeType>::operator=(FastMKS&& other)
+{
+  if (this != &other)
+  {
+    referenceSet = other.referenceSet;
+    referenceTree = other.referenceTree;
+    treeOwner = other.treeOwner;
+    setOwner = other.setOwner;
+    singleMode = other.singleMode;
+    naive = other.naive;
+    metric = std::move(other.metric);
+
+    // Clear information from the other.
+    other.referenceSet = nullptr;
+    other.referenceTree = nullptr;
+    other.treeOwner = false;
+    other.setOwner = false;
+    other.singleMode = false;
+    other.naive = false;
+  }
+  return *this;
+}
+
 template<typename KernelType,
          typename MatType,
          template<typename TreeMetricType,
diff --git a/src/mlpack/methods/fastmks/fastmks_model.cpp b/src/mlpack/methods/fastmks/fastmks_model.cpp
index 2fcda8e831..ae557d2358 100644
--- a/src/mlpack/methods/fastmks/fastmks_model.cpp
+++ b/src/mlpack/methods/fastmks/fastmks_model.cpp
@@ -71,40 +71,68 @@ FastMKSModel::FastMKSModel(FastMKSModel&& other) :
 
 FastMKSModel& FastMKSModel::operator=(const FastMKSModel& other)
 {
-  // Clear memory.
-  delete linear;
-  delete polynomial;
-  delete cosine;
-  delete gaussian;
-  delete epan;
-  delete triangular;
-  delete hyptan;
+  if (this != &other)
+  {
+    // Clear memory.
+    delete linear;
+    delete polynomial;
+    delete cosine;
+    delete gaussian;
+    delete epan;
+    delete triangular;
+    delete hyptan;
 
-  // Set pointers to null.
-  linear = NULL;
-  polynomial = NULL;
-  cosine = NULL;
-  gaussian = NULL;
-  epan = NULL;
-  triangular = NULL;
-  hyptan = NULL;
+    // Set pointers to null.
+    linear = NULL;
+    polynomial = NULL;
+    cosine = NULL;
+    gaussian = NULL;
+    epan = NULL;
+    triangular = NULL;
+    hyptan = NULL;
 
-  kernelType = other.kernelType;
-  if (other.linear)
-    linear = new FastMKS<LinearKernel>(*other.linear);
-  if (other.polynomial)
-    polynomial = new FastMKS<PolynomialKernel>(*other.polynomial);
-  if (other.cosine)
-    cosine = new FastMKS<CosineDistance>(*other.cosine);
-  if (other.gaussian)
-    gaussian = new FastMKS<GaussianKernel>(*other.gaussian);
-  if (other.epan)
-    epan = new FastMKS<EpanechnikovKernel>(*other.epan);
-  if (other.triangular)
-    triangular = new FastMKS<TriangularKernel>(*other.triangular);
-  if (other.hyptan)
-    hyptan = new FastMKS<HyperbolicTangentKernel>(*other.hyptan);
+    kernelType = other.kernelType;
+    if (other.linear)
+      linear = new FastMKS<LinearKernel>(*other.linear);
+    if (other.polynomial)
+      polynomial = new FastMKS<PolynomialKernel>(*other.polynomial);
+    if (other.cosine)
+      cosine = new FastMKS<CosineDistance>(*other.cosine);
+    if (other.gaussian)
+      gaussian = new FastMKS<GaussianKernel>(*other.gaussian);
+    if (other.epan)
+      epan = new FastMKS<EpanechnikovKernel>(*other.epan);
+    if (other.triangular)
+      triangular = new FastMKS<TriangularKernel>(*other.triangular);
+    if (other.hyptan)
+      hyptan = new FastMKS<HyperbolicTangentKernel>(*other.hyptan);
+  }
+  return *this;
+}
 
+FastMKSModel& FastMKSModel::operator=(FastMKSModel&& other)
+{
+  if (this != &other)
+  {
+    kernelType = other.kernelType;
+    linear = other.linear;
+    polynomial = other.polynomial;
+    cosine = other.cosine;
+    gaussian = other.gaussian;
+    epan = other.epan;
+    triangular = other.triangular;
+    hyptan = other.hyptan;
+
+    // Clear other object.
+    other.kernelType = KernelTypes::LINEAR_KERNEL;
+    other.linear = nullptr;
+    other.polynomial = nullptr;
+    other.cosine = nullptr;
+    other.gaussian = nullptr;
+    other.epan = nullptr;
+    other.triangular = nullptr;
+    other.hyptan = nullptr;
+  }
   return *this;
 }
 
diff --git a/src/mlpack/methods/fastmks/fastmks_model.hpp b/src/mlpack/methods/fastmks/fastmks_model.hpp
index e84eee0c28..0b7568c641 100644
--- a/src/mlpack/methods/fastmks/fastmks_model.hpp
+++ b/src/mlpack/methods/fastmks/fastmks_model.hpp
@@ -60,6 +60,9 @@ class FastMKSModel
   //! Copy assignment operator.
   FastMKSModel& operator=(const FastMKSModel& other);
 
+  //! Move assignment operator.
+  FastMKSModel& operator=(FastMKSModel&& other);
+
   /**
    * Clean memory.
    */
diff --git a/src/mlpack/methods/hmm/hmm_model.hpp b/src/mlpack/methods/hmm/hmm_model.hpp
index 41a7fd406b..0a2bce384b 100644
--- a/src/mlpack/methods/hmm/hmm_model.hpp
+++ b/src/mlpack/methods/hmm/hmm_model.hpp
@@ -129,6 +129,20 @@ class HMMModel
     return *this;
   }
 
+  //! Move assignment operator.
+  HMMModel& operator=(HMMModel&& other)
+  {
+    if (this != &other)
+    {
+      type = other.type;
+      discreteHMM = other.discreteHMM;
+      gaussianHMM = other.gaussianHMM;
+      gmmHMM = other.gmmHMM;
+      diagGMMHMM = other.diagGMMHMM;
+    }
+    return *this;
+  }
+
   //! Clean memory.
   ~HMMModel()
   {
diff --git a/src/mlpack/methods/range_search/range_search.hpp b/src/mlpack/methods/range_search/range_search.hpp
index 06575005ac..98de888a69 100644
--- a/src/mlpack/methods/range_search/range_search.hpp
+++ b/src/mlpack/methods/range_search/range_search.hpp
@@ -122,12 +122,18 @@ class RangeSearch
   RangeSearch(RangeSearch&& other);
 
   /**
-   * Copy the given RangeSearch model.
-   * Use std::move to pass in the model if the old copy is no longer needed.
-   *
+   * Deep copy the given RangeSearch model.
+   * 
    * @param other RangeSearch model to copy.
    */
-  RangeSearch& operator=(RangeSearch other);
+  RangeSearch& operator=(const RangeSearch& other);
+
+  /**
+   * Move the given RangeSearch model.
+   *
+   * @param other RangeSearch model to move.
+   */
+  RangeSearch& operator=(RangeSearch&& other);
 
   /**
    * Destroy the RangeSearch object.  If trees were created, they will be
diff --git a/src/mlpack/methods/range_search/range_search_impl.hpp b/src/mlpack/methods/range_search/range_search_impl.hpp
index 298aae995e..2652d47c89 100644
--- a/src/mlpack/methods/range_search/range_search_impl.hpp
+++ b/src/mlpack/methods/range_search/range_search_impl.hpp
@@ -169,25 +169,61 @@ template<typename MetricType,
                   typename TreeStatType,
                   typename TreeMatType> class TreeType>
 RangeSearch<MetricType, MatType, TreeType>&
-RangeSearch<MetricType, MatType, TreeType>::operator=(RangeSearch other)
+RangeSearch<MetricType, MatType, TreeType>::operator=(const RangeSearch& other)
 {
-  // Clean memory first.
-  if (treeOwner)
-    delete referenceTree;
-  if (naive)
-    delete referenceSet;
+  if (this != &other)
+  {
+    oldFromNewReferences = other.oldFromNewReferences;
+    referenceTree = other.referenceTree ? new Tree(*other.referenceTree) : nullptr;
+    referenceSet = other.referenceTree ? &referenceTree->Dataset() :
+        new MatType(*other.referenceSet);
+    treeOwner = other.referenceTree;
+    naive = other.naive;
+    singleMode = other.singleMode;
+    metric = other.metric;
+    baseCases = other.baseCases;
+    scores = other.scores;
+  }
+  return *this;
+}
 
-  // Move the other model.
-  oldFromNewReferences = std::move(other.oldFromNewReferences);
-  referenceTree = other.referenceTree;
-  referenceSet = other.referenceSet;
-  treeOwner = other.treeOwner;
-  naive = other.naive;
-  singleMode = other.singleMode;
-  metric = std::move(other.metric);
-  baseCases = other.baseCases;
-  scores = other.scores;
+template<typename MetricType,
+         typename MatType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType>
+RangeSearch<MetricType, MatType, TreeType>&
+RangeSearch<MetricType, MatType, TreeType>::operator=(RangeSearch&& other)
+{
+  if (this != &other)
+  {
+    // Clean memory first.
+    if (treeOwner)
+      delete referenceTree;
+    if (naive)
+      delete referenceSet;
 
+    // Move the other model.
+    oldFromNewReferences = std::move(other.oldFromNewReferences);
+    referenceTree = other.referenceTree;
+    referenceSet = other.referenceSet;
+    treeOwner = other.treeOwner;
+    naive = other.naive;
+    singleMode = other.singleMode;
+    metric = std::move(other.metric);
+    baseCases = other.baseCases;
+    scores = other.scores;
+
+    // Clear other object.
+    other.referenceTree = nullptr;
+    other.referenceSet = nullptr;
+    other.treeOwner = false;
+    other.naive = false;
+    other.singleMode = false;
+    other.baseCases = 0;
+    other.scores = 0;
+
+  }
   return *this;
 }
 
@@ -254,12 +290,15 @@ void RangeSearch<MetricType, MatType, TreeType>::Train(
     throw std::invalid_argument("cannot train on given reference tree when "
         "naive search (without trees) is desired");
 
+  // Can only train when passed argument `referenceTree` is not nullptr
   if (treeOwner && referenceTree)
+  {
     delete this->referenceTree;
 
-  this->referenceTree = referenceTree;
-  this->referenceSet = &referenceTree->Dataset();
-  treeOwner = false;
+    this->referenceTree = referenceTree;
+    this->referenceSet = &referenceTree->Dataset();
+    treeOwner = false;
+  }
 }
 
 template<typename MetricType,

From cc3f6ebefec119eef007ead71502dbfbc6d98ce5 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Sun, 17 Jan 2021 00:48:22 -0500
Subject: [PATCH 082/253] fix static code check 17/1

---
 .../hoeffding_trees/hoeffding_tree.hpp        |  21 ++++
 .../hoeffding_trees/hoeffding_tree_impl.hpp   | 111 ++++++++++++++++++
 .../hoeffding_trees/hoeffding_tree_model.cpp  |  78 ++++++------
 src/mlpack/methods/kde/kde.hpp                |   9 +-
 src/mlpack/methods/kde/kde_impl.hpp           | 104 ++++++++++++----
 5 files changed, 264 insertions(+), 59 deletions(-)

diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree.hpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree.hpp
index 488048f4e6..b58d97a423 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree.hpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree.hpp
@@ -155,6 +155,27 @@ class HoeffdingTree
    */
   HoeffdingTree(const HoeffdingTree& other);
 
+  /**
+   * Move another tree.
+   *
+   * @param other Tree to move.
+   */
+  HoeffdingTree(HoeffdingTree&& other);
+
+  /**
+   * Copy assignment operator.
+   * 
+   * @param other Tree to copy.
+   */
+  HoeffdingTree& operator=(const HoeffdingTree& other);
+
+  /**
+   * Move assignment operator.
+   * 
+   * @param other Tree to move.
+   */
+  HoeffdingTree& operator=(HoeffdingTree&& other);
+
   /**
    * Clean up memory.
    */
diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
index e6172f8324..f7e8bdd830 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
@@ -224,6 +224,117 @@ HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
   }
 }
 
+// Move constructor.
+template<typename FitnessFunction,
+         template<typename> class NumericSplitType,
+         template<typename> class CategoricalSplitType>
+HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
+    HoeffdingTree(HoeffdingTree&& other) :
+    numericSplits(std::move(other.numericSplits)),
+    categoricalSplits(std::move(other.categoricalSplits)),
+    dimensionMappings(other.dimensionMappings),
+    ownsMappings(true),
+    numSamples(other.numSamples),
+    numClasses(other.numClasses),
+    maxSamples(other.maxSamples),
+    checkInterval(other.checkInterval),
+    minSamples(other.minSamples),
+    datasetInfo(other.datasetInfo),
+    ownsInfo(true),
+    successProbability(other.successProbability),
+    splitDimension(other.splitDimension),
+    majorityClass(other.majorityClass),
+    majorityProbability(other.majorityProbability),
+    categoricalSplit(std::move(other.categoricalSplit)),
+    numericSplit(std::move(other.numericSplit))
+{
+  // Remove pointers.
+  other.dimensionMappings = nullptr;
+  other.datasetInfo = nullptr;
+}
+
+// Copy assignment operator.
+template<typename FitnessFunction,
+         template<typename> class NumericSplitType,
+         template<typename> class CategoricalSplitType>
+HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>&
+    HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
+    operator=(const HoeffdingTree& other) :
+{
+  if (this != &other)
+  {
+    numericSplits = other.numericSplits;
+    categoricalSplits = other.categoricalSplits;
+    dimensionMappings = new std::unordered_map<size_t,
+        std::pair<size_t, size_t>>(*other.dimensionMappings);
+    ownsMappings = true;
+    numSamples = other.numSamples;
+    numClasses = other.numClasses;
+    maxSamples = other.maxSamples;
+    checkInterval = other.checkInterval;
+    minSamples = other.minSamples;
+    datasetInfo = new data::DatasetInfo(*other.datasetInfo);
+    ownsInfo = true;
+    successProbability = other.successProbability;
+    splitDimension = other.splitDimension;
+    majorityClass = other.majorityClass;
+    majorityProbability = other.majorityProbability;
+    categoricalSplit = other.categoricalSplit;
+    numericSplit = other.numericSplit;
+
+    // Copy each of the children.
+    for (size_t i = 0; i < other.children.size(); ++i)
+    {
+      children.push_back(new HoeffdingTree(*other.children[i]));
+
+      // Delete copied datasetInfo and dimension mappings.
+      delete children[i]->datasetInfo;
+      children[i]->datasetInfo = this->datasetInfo;
+      children[i]->ownsInfo = false;
+
+      delete children[i]->dimensionMappings;
+      children[i]->dimensionMappings = this->dimensionMappings;
+      children[i]->ownsMappings = false;
+    }
+  }
+  return *this;
+}
+
+// Move assignment operator.
+template<typename FitnessFunction,
+         template<typename> class NumericSplitType,
+         template<typename> class CategoricalSplitType>
+HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>&
+    HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
+    operator=(HoeffdingTree&& other) :
+{
+  if (this != &other)
+  {
+    numericSplits = std::move(other.numericSplits);
+    categoricalSplits = std::move(other.categoricalSplits);
+    dimensionMappings = other.dimensionMappings;
+    ownsMappings = true;
+    numSamples = other.numSamples;
+    numClasses = other.numClasses;
+    maxSamples = other.maxSamples;
+    checkInterval = other.checkInterval;
+    minSamples = other.minSamples;
+    datasetInfo = other.datasetInfo;
+    ownsInfo = true;
+    successProbability = other.successProbability;
+    splitDimension = other.splitDimension;
+    majorityClass = other.majorityClass;
+    majorityProbability = other.majorityProbability;
+    categoricalSplit = std::move(other.categoricalSplit);
+    numericSplit = std::move(other.numericSplit);
+    // Remove pointers.
+    other.dimensionMappings = nullptr;
+    other.datasetInfo = nullptr;
+  }
+  return *this;
+}
+
+
 template<typename FitnessFunction,
          template<typename> class NumericSplitType,
          template<typename> class CategoricalSplitType>
diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_model.cpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_model.cpp
index d35970dd5b..2dfe857edf 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_model.cpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_model.cpp
@@ -62,53 +62,57 @@ HoeffdingTreeModel::HoeffdingTreeModel(HoeffdingTreeModel&& other) :
 HoeffdingTreeModel& HoeffdingTreeModel::operator=(
     const HoeffdingTreeModel& other)
 {
-  // Clear this model.
-  delete giniHoeffdingTree;
-  delete giniBinaryTree;
-  delete infoHoeffdingTree;
-  delete infoBinaryTree;
+  if (this != &other)
+  {
+    // Clear this model.
+    delete giniHoeffdingTree;
+    delete giniBinaryTree;
+    delete infoHoeffdingTree;
+    delete infoBinaryTree;
 
-  giniHoeffdingTree = NULL;
-  giniBinaryTree = NULL;
-  infoHoeffdingTree = NULL;
-  infoBinaryTree = NULL;
-
-  // Create the right tree.
-  type = other.type;
-  if (other.giniHoeffdingTree && (type == GINI_HOEFFDING))
-    giniHoeffdingTree = new GiniHoeffdingTreeType(*other.giniHoeffdingTree);
-  else if (other.giniBinaryTree && (type == GINI_BINARY))
-    giniBinaryTree = new GiniBinaryTreeType(*other.giniBinaryTree);
-  else if (other.infoHoeffdingTree && (type == INFO_HOEFFDING))
-    infoHoeffdingTree = new InfoHoeffdingTreeType(*other.infoHoeffdingTree);
-  else if (other.infoBinaryTree && (type == INFO_BINARY))
-    infoBinaryTree = new InfoBinaryTreeType(*other.infoBinaryTree);
+    giniHoeffdingTree = NULL;
+    giniBinaryTree = NULL;
+    infoHoeffdingTree = NULL;
+    infoBinaryTree = NULL;
 
+    // Create the right tree.
+    type = other.type;
+    if (other.giniHoeffdingTree && (type == GINI_HOEFFDING))
+      giniHoeffdingTree = new GiniHoeffdingTreeType(*other.giniHoeffdingTree);
+    else if (other.giniBinaryTree && (type == GINI_BINARY))
+      giniBinaryTree = new GiniBinaryTreeType(*other.giniBinaryTree);
+    else if (other.infoHoeffdingTree && (type == INFO_HOEFFDING))
+      infoHoeffdingTree = new InfoHoeffdingTreeType(*other.infoHoeffdingTree);
+    else if (other.infoBinaryTree && (type == INFO_BINARY))
+      infoBinaryTree = new InfoBinaryTreeType(*other.infoBinaryTree);
+  }
   return *this;
 }
 
 // Move operator.
 HoeffdingTreeModel& HoeffdingTreeModel::operator=(HoeffdingTreeModel&& other)
 {
-  // Clear this model.
-  delete giniHoeffdingTree;
-  delete giniBinaryTree;
-  delete infoHoeffdingTree;
-  delete infoBinaryTree;
+  if (this != &other)
+  {
+    // Clear this model.
+    delete giniHoeffdingTree;
+    delete giniBinaryTree;
+    delete infoHoeffdingTree;
+    delete infoBinaryTree;
 
-  type = other.type;
-  giniHoeffdingTree = other.giniHoeffdingTree;
-  giniBinaryTree = other.giniBinaryTree;
-  infoHoeffdingTree = other.infoHoeffdingTree;
-  infoBinaryTree = other.infoBinaryTree;
-
-  // Clear the other model.
-  other.type = GINI_HOEFFDING;
-  other.giniHoeffdingTree = NULL;
-  other.giniBinaryTree = NULL;
-  other.infoHoeffdingTree = NULL;
-  other.infoBinaryTree = NULL;
+    type = other.type;
+    giniHoeffdingTree = other.giniHoeffdingTree;
+    giniBinaryTree = other.giniBinaryTree;
+    infoHoeffdingTree = other.infoHoeffdingTree;
+    infoBinaryTree = other.infoBinaryTree;
 
+    // Clear the other model.
+    other.type = GINI_HOEFFDING;
+    other.giniHoeffdingTree = NULL;
+    other.giniBinaryTree = NULL;
+    other.infoHoeffdingTree = NULL;
+    other.infoBinaryTree = NULL;
+  }
   return *this;
 }
 
diff --git a/src/mlpack/methods/kde/kde.hpp b/src/mlpack/methods/kde/kde.hpp
index 448d32dd84..8885c2e894 100644
--- a/src/mlpack/methods/kde/kde.hpp
+++ b/src/mlpack/methods/kde/kde.hpp
@@ -140,11 +140,16 @@ class KDE
   /**
    * Copy a KDE model.
    *
-   * Use std::move if the object to copy is no longer needed.
+   * @param other KDE model to copy.
+   */
+  KDE& operator=(const KDE& other);
+
+  /**
+   * Move a KDE model.
    *
    * @param other KDE model to copy.
    */
-  KDE& operator=(KDE other);
+  KDE& operator=(KDE&& other);
 
   /**
    * Destroy the KDE object. If this object created any trees, they will be
diff --git a/src/mlpack/methods/kde/kde_impl.hpp b/src/mlpack/methods/kde/kde_impl.hpp
index b48190e686..054c02119d 100644
--- a/src/mlpack/methods/kde/kde_impl.hpp
+++ b/src/mlpack/methods/kde/kde_impl.hpp
@@ -190,31 +190,95 @@ KDE<KernelType,
     TreeType,
     DualTreeTraversalType,
     SingleTreeTraversalType>::
-operator=(KDE other)
+operator=(const KDE& other)
 {
-  // Clean memory.
-  if (ownsReferenceTree)
+  if (this != &other)
   {
-    delete referenceTree;
-    delete oldFromNewReferences;
+    // Clean memory.
+    if (ownsReferenceTree)
+    {
+      delete referenceTree;
+      delete oldFromNewReferences;
+    }
+    kernel = KernelType(other.kernel);
+    metric = MetricType(other.metric);
+    relError = other.relError;
+    absError = other.absError;
+    ownsReferenceTree = other.ownsReferenceTree;
+    trained = other.trained;
+    mode = other.mode;
+    monteCarlo = other.monteCarlo;
+    mcProb = other.mcProb;
+    initialSampleSize = other.initialSampleSize;
+    mcEntryCoef = other.mcEntryCoef;
+    mcBreakCoef = other.mcBreakCoef;
+    if (trained)
+    {
+      if (ownsReferenceTree)
+      {
+        oldFromNewReferences =
+            new std::vector<size_t>(*other.oldFromNewReferences);
+        referenceTree = new Tree(*other.referenceTree);
+      }
+      else
+      {
+        oldFromNewReferences = other.oldFromNewReferences;
+        referenceTree = other.referenceTree;
+      }
+    }
   }
+  return *this;
+}
 
-  // Move the other object.
-  this->kernel = std::move(other.kernel);
-  this->metric = std::move(other.metric);
-  this->referenceTree = std::move(other.referenceTree);
-  this->oldFromNewReferences = std::move(other.oldFromNewReferences);
-  this->relError = other.relError;
-  this->absError = other.absError;
-  this->ownsReferenceTree = other.ownsReferenceTree;
-  this->trained = other.trained;
-  this->mode = other.mode;
-  this->monteCarlo = other.monteCarlo;
-  this->mcProb = other.mcProb;
-  this->initialSampleSize = other.initialSampleSize;
-  this->mcEntryCoef = other.mcEntryCoef;
-  this->mcBreakCoef = other.mcBreakCoef;
+template<typename KernelType,
+         typename MetricType,
+         typename MatType,
+         template<typename TreeMetricType,
+                  typename TreeStatType,
+                  typename TreeMatType> class TreeType,
+         template<typename> class DualTreeTraversalType,
+         template<typename> class SingleTreeTraversalType>
+KDE<KernelType,
+    MetricType,
+    MatType,
+    TreeType,
+    DualTreeTraversalType,
+    SingleTreeTraversalType>&
+KDE<KernelType,
+    MetricType,
+    MatType,
+    TreeType,
+    DualTreeTraversalType,
+    SingleTreeTraversalType>::
+operator=(KDE&& other)
+{
+  if (this != &other)
+  {
+    // Clean memory.
+    if (ownsReferenceTree)
+    {
+      delete referenceTree;
+      delete oldFromNewReferences;
+    }
 
+    // Move the other object.
+    this->kernel = std::move(other.kernel);
+    this->metric = std::move(other.metric);
+    // TODO: This should be: this->referenceTree = other.referenceTree;
+    this->referenceTree = std::move(other.referenceTree);
+    // TODO: This should be: this->oldFromNewReferences = other.oldFromNewReferences;
+    this->oldFromNewReferences = std::move(other.oldFromNewReferences);
+    this->relError = other.relError;
+    this->absError = other.absError;
+    this->ownsReferenceTree = other.ownsReferenceTree;
+    this->trained = other.trained;
+    this->mode = other.mode;
+    this->monteCarlo = other.monteCarlo;
+    this->mcProb = other.mcProb;
+    this->initialSampleSize = other.initialSampleSize;
+    this->mcEntryCoef = other.mcEntryCoef;
+    this->mcBreakCoef = other.mcBreakCoef;
+  }
   return *this;
 }
 

From 568ce1f15681645600b6e102a033c9d047f3fb4d Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Sun, 17 Jan 2021 14:54:02 -0500
Subject: [PATCH 083/253] finish fixing static code check

---
 .../complete_incremental_termination.hpp      |  3 +-
 .../incomplete_incremental_termination.hpp    |  3 +-
 .../ann/layer/recurrent_attention_impl.hpp    |  3 +-
 .../ann/layer/reinforce_normal_impl.hpp       |  2 +-
 .../hoeffding_trees/hoeffding_tree_impl.hpp   |  4 +--
 .../kmeans/dual_tree_kmeans_rules_impl.hpp    |  3 +-
 .../methods/preprocess/scaling_model.hpp      |  3 ++
 .../methods/preprocess/scaling_model_impl.hpp | 32 ++++++++++++++++++-
 .../q_networks/categorical_dqn.hpp            |  2 +-
 9 files changed, 46 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp b/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
index e3a030836d..bdd02d7fec 100644
--- a/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
@@ -36,7 +36,8 @@ class CompleteIncrementalTermination
    */
   CompleteIncrementalTermination(
       TerminationPolicy tPolicy = TerminationPolicy()) :
-      tPolicy(tPolicy) { }
+      tPolicy(tPolicy), incrementalIndex(0), iteration(0)
+  { /** Nothing to do here. */ }
 
   /**
    * Initializes the termination policy before stating the factorization.
diff --git a/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp b/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
index 62b112b061..d01fdfd4c5 100644
--- a/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
@@ -35,7 +35,8 @@ class IncompleteIncrementalTermination
    */
   IncompleteIncrementalTermination(
       TerminationPolicy tPolicy = TerminationPolicy()) :
-      tPolicy(tPolicy) { }
+      tPolicy(tPolicy), incrementalIndex(0), iteration(0)
+  { /** Nothing to do here. */ }
 
   /**
    * Initializes the termination policy before stating the factorization.
diff --git a/src/mlpack/methods/ann/layer/recurrent_attention_impl.hpp b/src/mlpack/methods/ann/layer/recurrent_attention_impl.hpp
index 4cdb912756..dcc60055d5 100644
--- a/src/mlpack/methods/ann/layer/recurrent_attention_impl.hpp
+++ b/src/mlpack/methods/ann/layer/recurrent_attention_impl.hpp
@@ -31,7 +31,8 @@ RecurrentAttention<InputDataType, OutputDataType>::RecurrentAttention() :
     rho(0),
     forwardStep(0),
     backwardStep(0),
-    deterministic(false)
+    deterministic(false),
+    outSize(0)
 {
   // Nothing to do.
 }
diff --git a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
index 67eebf107d..b3c2fd700b 100644
--- a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
+++ b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
@@ -21,7 +21,7 @@ namespace ann /** Artificial Neural Network. */ {
 
 template<typename InputDataType, typename OutputDataType>
 ReinforceNormal<InputDataType, OutputDataType>::ReinforceNormal(
-    const double stdev) : stdev(stdev)
+    const double stdev) : stdev(stdev), reward(0.0), deterministic(false)
 {
   // Nothing to do here.
 }
diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
index f7e8bdd830..3535f9558b 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
@@ -259,7 +259,7 @@ template<typename FitnessFunction,
          template<typename> class CategoricalSplitType>
 HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>&
     HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
-    operator=(const HoeffdingTree& other) :
+    operator=(const HoeffdingTree& other)
 {
   if (this != &other)
   {
@@ -306,7 +306,7 @@ template<typename FitnessFunction,
          template<typename> class CategoricalSplitType>
 HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>&
     HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
-    operator=(HoeffdingTree&& other) :
+    operator=(HoeffdingTree&& other)
 {
   if (this != &other)
   {
diff --git a/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp b/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
index 6f180c2e99..5e08f88a28 100644
--- a/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
+++ b/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
@@ -40,7 +40,8 @@ DualTreeKMeansRules<MetricType, TreeType>::DualTreeKMeansRules(
     baseCases(0),
     scores(0),
     lastQueryIndex(dataset.n_cols),
-    lastReferenceIndex(centroids.n_cols)
+    lastReferenceIndex(centroids.n_cols),
+    lastBaseCase(0.0)
 {
   // We must set the traversal info last query and reference node pointers to
   // something that is both invalid (i.e. not a tree node) and not NULL.  We'll
diff --git a/src/mlpack/methods/preprocess/scaling_model.hpp b/src/mlpack/methods/preprocess/scaling_model.hpp
index 87693cc796..a5d7082658 100644
--- a/src/mlpack/methods/preprocess/scaling_model.hpp
+++ b/src/mlpack/methods/preprocess/scaling_model.hpp
@@ -65,6 +65,9 @@ class ScalingModel
   //! Copy assignment operator.
   ScalingModel& operator=(const ScalingModel& other);
 
+  //! Move assignment operator.
+  ScalingModel& operator=(ScalingModel&& other);
+
   //! Clean up memory.
   ~ScalingModel();
 
diff --git a/src/mlpack/methods/preprocess/scaling_model_impl.hpp b/src/mlpack/methods/preprocess/scaling_model_impl.hpp
index dd918de9d9..6da36e6f49 100644
--- a/src/mlpack/methods/preprocess/scaling_model_impl.hpp
+++ b/src/mlpack/methods/preprocess/scaling_model_impl.hpp
@@ -84,7 +84,7 @@ ScalingModel::ScalingModel(ScalingModel&& other) :
 }
 
 //! Copy assignment operator.
-ScalingModel& ScalingModel::operator= (const ScalingModel& other)
+ScalingModel& ScalingModel::operator=(const ScalingModel& other)
 {
   if (this == &other)
   {
@@ -123,6 +123,36 @@ ScalingModel& ScalingModel::operator= (const ScalingModel& other)
   return *this;
 }
 
+//! Move assignment operator.
+ScalingModel& ScalingModel::operator=(ScalingModel&& other)
+{
+  if (this != &other)
+  {
+    scalerType = other.scalerType;
+    minmaxscale = other.minmaxscale;
+    maxabsscale = other.maxabsscale;
+    meanscale = other.meanscale;
+    standardscale = other.standardscale;
+    pcascale = other.pcascale;
+    zcascale = other.zcascale;
+    minValue = other.minValue;
+    maxValue = other.maxValue;
+    epsilon = other.epsilon;
+
+    other.scalerType = 0;
+    other.minmaxscale = nullptr;
+    other.maxabsscale = nullptr;
+    other.meanscale = nullptr;
+    other.standardscale = nullptr;
+    other.pcascale = nullptr;
+    other.zcascale = nullptr;
+    other.minValue = 0;
+    other.maxValue = 1;
+    other.epsilon = 0.00005;
+  }
+  return *this;
+}
+
 ScalingModel::~ScalingModel()
 {
   delete minmaxscale;
diff --git a/src/mlpack/methods/reinforcement_learning/q_networks/categorical_dqn.hpp b/src/mlpack/methods/reinforcement_learning/q_networks/categorical_dqn.hpp
index b52110d744..82ce15e77e 100644
--- a/src/mlpack/methods/reinforcement_learning/q_networks/categorical_dqn.hpp
+++ b/src/mlpack/methods/reinforcement_learning/q_networks/categorical_dqn.hpp
@@ -53,7 +53,7 @@ class CategoricalDQN
   /**
    * Default constructor.
    */
-  CategoricalDQN() : network(), isNoisy(false)
+  CategoricalDQN() : network(), isNoisy(false), atomSize(0), vMin(0.0), vMax(0.0)
   { /* Nothing to do here. */ }
 
   /**

From f7b5537aa790c6ba4ebc540976000032bdefb5fb Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Mon, 18 Jan 2021 09:57:30 +0530
Subject: [PATCH 084/253] Added Hinge Loss Skeleton

---
 .../methods/ann/loss_functions/CMakeLists.txt |  26 ++---
 .../methods/ann/loss_functions/hinge_loss.hpp | 102 ++++++++++++++++++
 .../ann/loss_functions/hinge_loss_impl.hpp    |  65 +++++++++++
 3 files changed, 181 insertions(+), 12 deletions(-)
 create mode 100644 src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
 create mode 100644 src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp

diff --git a/src/mlpack/methods/ann/loss_functions/CMakeLists.txt b/src/mlpack/methods/ann/loss_functions/CMakeLists.txt
index 70b570e0ff..12d9d1718a 100644
--- a/src/mlpack/methods/ann/loss_functions/CMakeLists.txt
+++ b/src/mlpack/methods/ann/loss_functions/CMakeLists.txt
@@ -9,24 +9,32 @@ set(SOURCES
   dice_loss_impl.hpp
   earth_mover_distance.hpp
   earth_mover_distance_impl.hpp
+  empty_loss.hpp
+  empty_loss_impl.hpp
   huber_loss.hpp
   huber_loss_impl.hpp
+  hinge_embedding_loss.hpp
+  hinge_embedding_loss_impl.hpp
+  hinge_loss.hpp
+  hinge_loss_impl.hpp
   kl_divergence.hpp
   kl_divergence_impl.hpp
-  margin_ranking_loss.hpp
-  margin_ranking_loss_impl.hpp
-  mean_bias_error.hpp
-  mean_bias_error_impl.hpp
   l1_loss.hpp
   l1_loss_impl.hpp
+  log_cosh_loss.hpp
+  log_cosh_loss_impl.hpp
+  margin_ranking_loss.hpp
+  margin_ranking_loss_impl.hpp
+  mean_absolute_percentage_error.hpp
+  mean_absolute_percentage_error_impl.hpp
+  mean_bias_error.hpp
+  mean_bias_error_impl.hpp
   mean_squared_error.hpp
   mean_squared_error_impl.hpp
   mean_squared_logarithmic_error.hpp
   mean_squared_logarithmic_error_impl.hpp
   negative_log_likelihood.hpp
   negative_log_likelihood_impl.hpp
-  log_cosh_loss.hpp
-  log_cosh_loss_impl.hpp
   poisson_nll_loss.hpp
   poisson_nll_loss_impl.hpp
   reconstruction_loss.hpp
@@ -35,12 +43,6 @@ set(SOURCES
   sigmoid_cross_entropy_error_impl.hpp
   soft_margin_loss.hpp
   soft_margin_loss_impl.hpp
-  hinge_embedding_loss.hpp
-  hinge_embedding_loss_impl.hpp
-  empty_loss.hpp
-  empty_loss_impl.hpp
-  mean_absolute_percentage_error.hpp
-  mean_absolute_percentage_error_impl.hpp
   triplet_margin_loss.hpp
   triplet_margin_loss_impl.hpp
 )
diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
new file mode 100644
index 0000000000..e43ec9d862
--- /dev/null
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
@@ -0,0 +1,102 @@
+/**
+ * @file methods/ann/loss_functions/hinge_loss.hpp
+ * @author Anush Kini
+ *
+ * Definition of the Hinge Loss Function.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+
+#ifndef MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_LOSS_HPP
+#define MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_LOSS_HPP
+
+#include<mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+/**
+ * Computes the hinge loss between y_true and y_pred. Expects y_true to be
+ * either -1 or 1. If y_true is either 0 or 1, a temporary conversion is made to
+ * calculate the loss.
+ *
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ */
+template <
+        typename InputDataType = arma::mat,
+        typename OutputDataType = arma::mat
+>
+class HingeLoss
+{
+ public:
+  /**
+   * Create HingeLoss object.
+   * @param reduction Specifies the reduction to apply to the output. If false,
+   *                  'mean' reduction is used, where sum of the output will be
+   *                  divided by the number of elements in the output. If
+   *                  true, 'sum' reduction is used and the output will be
+   *                  summed. It is set to true by default.
+   */
+  HingeLoss(const bool reduction = true);
+
+  /**
+   * Computes the Hinge loss function.
+   *
+   * @param prediction Prediction used for evaluating the specified loss
+   *     function.
+   * @param target Target data to compare with.
+   */
+  template<typename PredictionType, typename TargetType>
+  typename PredictionType::elem_type Forward(const PredictionType& prediction,
+                                              const TargetType& target);
+
+  /**
+   * Ordinary feed backward pass of a neural network.
+   *
+   * @param prediction Prediction used for evaluating the specified loss
+   *     function.
+   * @param target The target vector.
+   * @param loss The calculated error.
+   */
+  template<typename PredictionType, typename TargetType>
+  void Backward(const PredictionType& prediction,
+                const TargetType& target,
+                LossType& loss);
+
+  //! Get the output parameter.
+  OutputDataType& OutputParameter() const { return outputParameter; }
+  //! Modify the output parameter.
+  OutputDataType& OutputParameter() { return outputParameter; }
+
+  //! Get the type of reduction used.
+  bool Reduction() const { return reduction; }
+  //! Modify the type of reduction used.
+  bool& Reduction() { return reduction; }
+
+  /**
+   * Serialize the layer.
+   */
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */);
+
+ private:
+  //! Locally-stored output parameter object.
+  OutputDataType outputParameter;
+
+  //! The boolean value that tells if reduction is sum or mean.
+  bool reduction;
+}; // class HingeLoss
+
+} // namespace ann
+} // namespace mlpack
+
+// include implementation
+#include "hinge_loss_impl.hpp"
+
+#endif
diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
new file mode 100644
index 0000000000..8cb74192c7
--- /dev/null
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
@@ -0,0 +1,65 @@
+/**
+ * @file methods/ann/loss_functions/hinge_loss_impl.hpp
+ * @author Anush Kini
+ *
+ * Implementation of the Hinge loss function.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+
+#ifndef MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_LOSS_IMPL_HPP
+#define MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_LOSS_IMPL_HPP
+
+// In case it hasn't yet been included.
+#include "hinge_loss.hpp"
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+template<typename InputDataType, typename OutputDataType>
+HingeLoss<InputDataType, OutputDataType>::HingeLoss(const bool reduction):
+  reduction(reduction)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename PredictionType, typename TargetType>
+typename PredictionType::elem_type
+HingeLoss<InputDataType, OutputDataType>::Forward(
+    const PredictionType& prediction,
+    const TargetType& target)
+{
+  TargetType temp = target - (target == 0);
+  TargetType temp_zeros.zeros(target.size());
+
+  PredictionType loss = arma::mean(arma::max(1 - prediction % temp, temp_zeros), 1);
+  typename PredictionType::elem_type lossSum = arma::accu(loss);
+
+  if (reduction)
+    return lossSum;
+
+  return lossSum / loss.n_elem;
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename PredictionType, typename TargetType, typename LossType>
+void HingeEmbeddingLoss<InputDataType, OutputDataType>::Backward(
+    const PredictionType& prediction,
+    const TargetType& target,
+    LossType& loss)
+{
+  TargetType temp = target - (target == 0);
+  loss = (prediction < 1 / temp) % -temp;
+}
+
+
+
+
+} // namespace ann
+} // namespace mlpack
+
+#endif

From a21a52dec17fdfa516cf4803fcd3a1c1ef8ce60d Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Mon, 18 Jan 2021 10:00:32 +0530
Subject: [PATCH 085/253] Style fixes

---
 src/mlpack/methods/ann/layer/multiply_constant.hpp | 8 ++++----
 src/mlpack/methods/ann/layer/multiply_merge.hpp    | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/multiply_constant.hpp b/src/mlpack/methods/ann/layer/multiply_constant.hpp
index a9a32a19ac..32fad5b5b3 100644
--- a/src/mlpack/methods/ann/layer/multiply_constant.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_constant.hpp
@@ -39,16 +39,16 @@ class MultiplyConstant
    */
   MultiplyConstant(const double scalar = 1.0);
 
-  //! Copy Constructor
+  //! Copy Constructor.
   MultiplyConstant(const MultiplyConstant& layer);
 
-  //! Move Constructor
+  //! Move Constructor.
   MultiplyConstant(MultiplyConstant&& layer);
 
-  //! Copy assignment operator
+  //! Copy assignment operator.
   MultiplyConstant& operator=(const MultiplyConstant& layer);
 
-  //! Move assignment operator
+  //! Move assignment operator.
   MultiplyConstant& operator=(MultiplyConstant&& layer);
 
   /**
diff --git a/src/mlpack/methods/ann/layer/multiply_merge.hpp b/src/mlpack/methods/ann/layer/multiply_merge.hpp
index 94e4169d52..1ac73a0bbd 100644
--- a/src/mlpack/methods/ann/layer/multiply_merge.hpp
+++ b/src/mlpack/methods/ann/layer/multiply_merge.hpp
@@ -50,16 +50,16 @@ class MultiplyMerge
    */
   MultiplyMerge(const bool model = false, const bool run = true);
 
-  //! Copy Constructor
+  //! Copy Constructor.
   MultiplyMerge(const MultiplyMerge& layer);
 
-  //! Move Constructor
+  //! Move Constructor.
   MultiplyMerge(MultiplyMerge&& layer);
 
-  //! Copy assignment operator
+  //! Copy assignment operator.
   MultiplyMerge& operator=(const MultiplyMerge& layer);
 
-  //! Move assignment operator
+  //! Move assignment operator.
   MultiplyMerge& operator=(MultiplyMerge&& layer);
 
   //! Destructor to release allocated memory.

From e4fb279689f66ffd1ade7ff9d565cee59839ca98 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Mon, 18 Jan 2021 19:14:24 +0530
Subject: [PATCH 086/253] Added an implementation of hinge loss

---
 .../ann/loss_functions/hinge_loss_impl.hpp     | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
index 8cb74192c7..0d6729b5b5 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
@@ -36,7 +36,8 @@ HingeLoss<InputDataType, OutputDataType>::Forward(
   TargetType temp = target - (target == 0);
   TargetType temp_zeros.zeros(target.size());
 
-  PredictionType loss = arma::mean(arma::max(1 - prediction % temp, temp_zeros), 1);
+  PredictionType loss = arma::max(1 - prediction % temp, temp_zeros);
+
   typename PredictionType::elem_type lossSum = arma::accu(loss);
 
   if (reduction)
@@ -53,11 +54,20 @@ void HingeEmbeddingLoss<InputDataType, OutputDataType>::Backward(
     LossType& loss)
 {
   TargetType temp = target - (target == 0);
-  loss = (prediction < 1 / temp) % -temp;
+  loss = (prediction < (1 / temp)) % -temp;
+
+  if (!reduction)
+    loss /= target.n_elem;
 }
 
-
-
+template<typename InputDataType, typename OutputDataType>
+template<typename Archive>
+void HingeEmbeddingLoss<InputDataType, OutputDataType>::serialize(
+    Archive& ar,
+    const uint32_t /* version */)
+{
+  ar(CEREAL_NVP(reduction));
+}
 
 } // namespace ann
 } // namespace mlpack

From 151ca758abed17013287ea5a360acaecf94b66db Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Mon, 18 Jan 2021 16:59:24 -0500
Subject: [PATCH 087/253] fix static error 1/18

---
 src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp     | 2 +-
 src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp | 2 +-
 src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp  | 3 +--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
index b3c2fd700b..2c985dff6d 100644
--- a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
+++ b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
@@ -34,7 +34,7 @@ void ReinforceNormal<InputDataType, OutputDataType>::Forward(
   if (!deterministic)
   {
     // Multiply by standard deviations and re-center the means to the mean.
-    output = arma::randn<arma::Mat<eT> >(input.n_rows, input.n_cols) *
+    output = arma::randn<arma::Mat<eT>>(input.n_rows, input.n_cols) *
         stdev + input;
 
     moduleInputParameter.push_back(input);
diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
index 3535f9558b..5e31358621 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
@@ -452,7 +452,7 @@ void HoeffdingTree<
     delete dimensionMappings;
 
   const CategoricalSplitType<FitnessFunction> categoricalSplitIn(0, 0);
-  const NumericSplitType<FitnessFunction>& numericSplitIn(0);
+  const NumericSplitType<FitnessFunction> numericSplitIn(0);
 
   dimensionMappings =
       new std::unordered_map<size_t, std::pair<size_t, size_t>>();
diff --git a/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp b/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
index 5e08f88a28..2d1a66fe12 100644
--- a/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
+++ b/src/mlpack/methods/kmeans/dual_tree_kmeans_rules_impl.hpp
@@ -157,8 +157,7 @@ inline double DualTreeKMeansRules<MetricType, TreeType>::Score(
         traversalInfo.LastQueryNode()->MinimumBoundDistance();
     const double lastRefDescDist =
         traversalInfo.LastReferenceNode()->MinimumBoundDistance();
-    adjustedScore = lastScore + lastQueryDescDist;
-    adjustedScore = lastScore + lastRefDescDist;
+    adjustedScore = lastScore + lastQueryDescDist + lastRefDescDist;
   }
 
   // Assemble an adjusted score.  For nearest neighbor search, this adjusted

From 0008893ef70f92b4589aa739f7097627f0cf2f89 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Mon, 18 Jan 2021 22:28:24 -0500
Subject: [PATCH 088/253] fix static error

---
 src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
index 2c985dff6d..be4803b6c6 100644
--- a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
+++ b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
@@ -34,8 +34,12 @@ void ReinforceNormal<InputDataType, OutputDataType>::Forward(
   if (!deterministic)
   {
     // Multiply by standard deviations and re-center the means to the mean.
-    output = arma::randn<arma::Mat<eT>>(input.n_rows, input.n_cols) *
-        stdev + input;
+    arma::Mat<eT> output(input.n_rows, input.n_cols);
+
+    output = output.randn() * stdev + input;
+    
+    // output = arma::randn<arma::Mat<eT>>(input.n_rows, input.n_cols) *
+    //     stdev + input;
 
     moduleInputParameter.push_back(input);
   }

From 2e208af07573ba04ed9215db77704d2d6bab6f25 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Tue, 19 Jan 2021 01:41:09 -0500
Subject: [PATCH 089/253] fix static code 1/19

---
 src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
index be4803b6c6..74de3d93d4 100644
--- a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
+++ b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
@@ -34,9 +34,7 @@ void ReinforceNormal<InputDataType, OutputDataType>::Forward(
   if (!deterministic)
   {
     // Multiply by standard deviations and re-center the means to the mean.
-    arma::Mat<eT> output(input.n_rows, input.n_cols);
-
-    output = output.randn() * stdev + input;
+    output = output.randn(input.n_rows, input.n_cols) * stdev + input;
     
     // output = arma::randn<arma::Mat<eT>>(input.n_rows, input.n_cols) *
     //     stdev + input;

From 772b95ffb73e498cfab97c2c78d8ec06ca8c3884 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Tue, 19 Jan 2021 12:40:38 +0530
Subject: [PATCH 090/253] Added hinge loss implementation

---
 src/mlpack/methods/ann/loss_functions/hinge_loss.hpp      | 2 +-
 src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
index e43ec9d862..a9c2563b9e 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
@@ -64,7 +64,7 @@ class HingeLoss
    * @param target The target vector.
    * @param loss The calculated error.
    */
-  template<typename PredictionType, typename TargetType>
+  template<typename PredictionType, typename TargetType, typename LossType>
   void Backward(const PredictionType& prediction,
                 const TargetType& target,
                 LossType& loss);
diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
index 0d6729b5b5..85fb07cb88 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
@@ -34,7 +34,7 @@ HingeLoss<InputDataType, OutputDataType>::Forward(
     const TargetType& target)
 {
   TargetType temp = target - (target == 0);
-  TargetType temp_zeros.zeros(target.size());
+  TargetType temp_zeros(size(target), arma::fill::zeros);
 
   PredictionType loss = arma::max(1 - prediction % temp, temp_zeros);
 
@@ -48,7 +48,7 @@ HingeLoss<InputDataType, OutputDataType>::Forward(
 
 template<typename InputDataType, typename OutputDataType>
 template<typename PredictionType, typename TargetType, typename LossType>
-void HingeEmbeddingLoss<InputDataType, OutputDataType>::Backward(
+void HingeLoss<InputDataType, OutputDataType>::Backward(
     const PredictionType& prediction,
     const TargetType& target,
     LossType& loss)
@@ -62,7 +62,7 @@ void HingeEmbeddingLoss<InputDataType, OutputDataType>::Backward(
 
 template<typename InputDataType, typename OutputDataType>
 template<typename Archive>
-void HingeEmbeddingLoss<InputDataType, OutputDataType>::serialize(
+void HingeLoss<InputDataType, OutputDataType>::serialize(
     Archive& ar,
     const uint32_t /* version */)
 {

From 472e8a4d01186b8733dbf3168cdc2d6d5879e7a7 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Tue, 19 Jan 2021 09:40:42 -0500
Subject: [PATCH 091/253] finishing up

---
 src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
index 74de3d93d4..c2f92df476 100644
--- a/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
+++ b/src/mlpack/methods/ann/layer/reinforce_normal_impl.hpp
@@ -35,9 +35,6 @@ void ReinforceNormal<InputDataType, OutputDataType>::Forward(
   {
     // Multiply by standard deviations and re-center the means to the mean.
     output = output.randn(input.n_rows, input.n_cols) * stdev + input;
-    
-    // output = arma::randn<arma::Mat<eT>>(input.n_rows, input.n_cols) *
-    //     stdev + input;
 
     moduleInputParameter.push_back(input);
   }

From b17bc76a3a47ca920b4a16ccd6c43d9d353b24c8 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Wed, 20 Jan 2021 17:00:40 -0500
Subject: [PATCH 092/253] Update src/mlpack/core/tree/hrectbound_impl.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/core/tree/hrectbound_impl.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/tree/hrectbound_impl.hpp b/src/mlpack/core/tree/hrectbound_impl.hpp
index 45d4b81a76..a1259a677c 100644
--- a/src/mlpack/core/tree/hrectbound_impl.hpp
+++ b/src/mlpack/core/tree/hrectbound_impl.hpp
@@ -104,7 +104,7 @@ inline HRectBound<MetricType, ElemType>::HRectBound(
 }
 
 /**
- * Move assignment operator
+ * Move assignment operator.
  */
 template<typename MetricType, typename ElemType>
 inline HRectBound<

From 947fc2b83cbdf9b199ed73a70a58cb105e521065 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Wed, 20 Jan 2021 17:00:47 -0500
Subject: [PATCH 093/253] Update
 src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
index 32bb94ece9..c6cc5bb586 100644
--- a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
+++ b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
@@ -182,7 +182,7 @@ class DiscreteHilbertValue
    */
   DiscreteHilbertValue& operator=(const DiscreteHilbertValue& val);
 
-   /**
+  /**
    * Move the local Hilbert object.
    *
    * @param val The DiscreteHilbertValue object from which the dataset

From 7bf86ac51bb68f1e0221bed8264f50a219f2ea9b Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Wed, 20 Jan 2021 17:01:15 -0500
Subject: [PATCH 094/253] Update
 src/mlpack/methods/range_search/range_search_impl.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/methods/range_search/range_search_impl.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/range_search/range_search_impl.hpp b/src/mlpack/methods/range_search/range_search_impl.hpp
index 2652d47c89..03f90b3057 100644
--- a/src/mlpack/methods/range_search/range_search_impl.hpp
+++ b/src/mlpack/methods/range_search/range_search_impl.hpp
@@ -290,7 +290,7 @@ void RangeSearch<MetricType, MatType, TreeType>::Train(
     throw std::invalid_argument("cannot train on given reference tree when "
         "naive search (without trees) is desired");
 
-  // Can only train when passed argument `referenceTree` is not nullptr
+  // Can only train when passed argument `referenceTree` is not nullptr.
   if (treeOwner && referenceTree)
   {
     delete this->referenceTree;

From 880471defbf4a9c4df53757ecf47ffb92bb9ad9f Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Wed, 20 Jan 2021 19:19:03 -0500
Subject: [PATCH 095/253] change val to other

---
 .../core/tree/rectangle_tree/discrete_hilbert_value.hpp   | 8 ++++----
 .../tree/rectangle_tree/discrete_hilbert_value_impl.hpp   | 8 ++++----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
index c6cc5bb586..a21dd1af3d 100644
--- a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
+++ b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value.hpp
@@ -177,18 +177,18 @@ class DiscreteHilbertValue
   /**
    * Copy the local Hilbert value's pointer.
    *
-   * @param val The DiscreteHilbertValue object from which the dataset
+   * @param other The DiscreteHilbertValue object from which the dataset
    *    will be copied.
    */
-  DiscreteHilbertValue& operator=(const DiscreteHilbertValue& val);
+  DiscreteHilbertValue& operator=(const DiscreteHilbertValue& other);
 
   /**
    * Move the local Hilbert object.
    *
-   * @param val The DiscreteHilbertValue object from which the dataset
+   * @param other The DiscreteHilbertValue object from which the dataset
    *    will be copied.
    */
-  DiscreteHilbertValue& operator=(DiscreteHilbertValue&& val);
+  DiscreteHilbertValue& operator=(DiscreteHilbertValue&& other);
 
   /**
    * Nullify the localHilbertValues pointer in order to prevent an invalid free.
diff --git a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
index 48ad8557f7..bd3c9cb87e 100644
--- a/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
+++ b/src/mlpack/core/tree/rectangle_tree/discrete_hilbert_value_impl.hpp
@@ -434,18 +434,18 @@ RemoveNode(TreeType* node, const size_t nodeIndex)
 
 template<typename TreeElemType>
 DiscreteHilbertValue<TreeElemType>& DiscreteHilbertValue<TreeElemType>::
-operator=(const DiscreteHilbertValue& val)
+operator=(const DiscreteHilbertValue& other)
 {
-  if (this == &val)
+  if (this == &other)
     return *this;
 
   if (ownsLocalHilbertValues)
     delete localHilbertValues;
 
   localHilbertValues = const_cast<arma::Mat<HilbertElemType>* >
-      (val.LocalHilbertValues());
+      (other.LocalHilbertValues());
   ownsLocalHilbertValues = false;
-  numValues = val.NumValues();
+  numValues = other.NumValues();
 
   return *this;
 }

From 2fbb7cdcb1087b4e9363a8e526c0209c92d2e935 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Thu, 21 Jan 2021 11:24:12 +0530
Subject: [PATCH 096/253] Added Test for Hinge Loss Function

---
 src/mlpack/tests/loss_functions_test.cpp | 73 ++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/src/mlpack/tests/loss_functions_test.cpp b/src/mlpack/tests/loss_functions_test.cpp
index 5a208984dd..b5ab0c155a 100644
--- a/src/mlpack/tests/loss_functions_test.cpp
+++ b/src/mlpack/tests/loss_functions_test.cpp
@@ -34,6 +34,7 @@
 #include <mlpack/methods/ann/loss_functions/soft_margin_loss.hpp>
 #include <mlpack/methods/ann/loss_functions/mean_absolute_percentage_error.hpp>
 #include <mlpack/methods/ann/loss_functions/triplet_margin_loss.hpp>
+#include <mlpack/methods/ann/loss_functions/hinge_loss.hpp>
 #include <mlpack/methods/ann/init_rules/nguyen_widrow_init.hpp>
 #include <mlpack/methods/ann/ffn.hpp>
 
@@ -955,3 +956,75 @@ TEST_CASE("TripletMarginLossTest")
   REQUIRE(arma::accu(output) == -12);
   REQUIRE(output.n_elem == 1);
 }
+
+/**
+ * Simple test for the Hinge loss function.
+ */
+TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
+{
+  arma::mat input, target, target_b, output;
+  double loss, loss_b;
+  HingeLoss<> module1;
+  HingeLoss<> module2(false);
+
+  // Test the Forward function. Loss should be 0 if input = target.
+  input = arma::ones(10, 1);
+  target = arma::ones(10, 1);
+  loss = module1.Forward(input, target);
+  REQUIRE(loss == 0);
+
+  // Test the Backward function for input = target.
+  module1.Backward(input, target, output);
+  for (double el : output)
+  {
+    // For input = target we should get 0.0 everywhere.
+    REQUIRE(el == Approx(0.0).epsilon(1e-5));
+  }
+
+  REQUIRE(output.n_rows == input.n_rows);
+  REQUIRE(output.n_cols == input.n_cols);
+
+  input = {{0.90599973, -0.33040298, 0.07123354},
+      {0.71988434, 0.49657596, 0.39873373},
+      {-0.57646927, 0.3951491 , -0.1003365},
+      {0.12528634, 0.68122971, 0.85448826}};
+
+  target = {{-1, -1, 1},
+      {-1, 1, 1},
+      {1, -1, -1},
+      {1, -1, -1}};
+
+  // Binary labels for target
+  target_b = {{0, 0, 1},
+      {0, 1, 1},
+      {1, 0, 0},
+      {1, 0, 0}};
+
+  // Test for binary labels as target.
+  loss = module1.Forward(input, target);
+  loss_b = module1.Forward(input, target_b);
+
+  // Loss should be same due to internal conversion of binary labels.
+  REQUIRE(loss == loss_b);
+
+  // Test for sum reduction.
+  // Test the Forward function.
+  loss = module1.Forward(input, target);
+  REQUIRE(loss == Approx(14.61065).epsilon(1e-3));
+
+  // Test the Backward function
+  module1.Backward(input, target, output);
+  REQUIRE(arma::accu(output) == Approx(-5).epsilon(1e-3));
+  REQUIRE(output.n_rows == input.n_rows);
+  REQUIRE(output.n_cols == input.n_cols);
+
+  // Test for mean reduction.
+  loss = module2.Forward(input, target);
+  REQUIRE(loss == Approx(1.21755).epsilon(1e-3));
+
+  // Test the Backward function.
+  module2.Backward(input, target, output);
+  REQUIRE(arma::accu(output) == Approx(-0.41667).epsilon(1e-3));
+  REQUIRE(output.n_rows == input.n_rows);
+  REQUIRE(output.n_cols == input.n_cols);
+}

From 67ee79d51a3a7fa79c3b20b9b32919630c8d6830 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Thu, 21 Jan 2021 18:53:09 +0530
Subject: [PATCH 097/253] Minor comment addition

---
 src/mlpack/tests/loss_functions_test.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/tests/loss_functions_test.cpp b/src/mlpack/tests/loss_functions_test.cpp
index b5ab0c155a..82e7c76db8 100644
--- a/src/mlpack/tests/loss_functions_test.cpp
+++ b/src/mlpack/tests/loss_functions_test.cpp
@@ -994,7 +994,7 @@ TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
       {1, -1, -1},
       {1, -1, -1}};
 
-  // Binary labels for target
+  // Binary labels for target.
   target_b = {{0, 0, 1},
       {0, 1, 1},
       {1, 0, 0},
@@ -1019,6 +1019,7 @@ TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
   REQUIRE(output.n_cols == input.n_cols);
 
   // Test for mean reduction.
+  // Test for the Forward function.
   loss = module2.Forward(input, target);
   REQUIRE(loss == Approx(1.21755).epsilon(1e-3));
 

From d81f60ca931a4652fcba9c395eb0bd5e5ad2d859 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 09:48:15 -0500
Subject: [PATCH 098/253] Add k-means++ initialization.

---
 src/mlpack/methods/kmeans/CMakeLists.txt      |   1 +
 src/mlpack/methods/kmeans/kmeans_main.cpp     |  31 ++++--
 .../kmeans_plus_plus_initialization.hpp       | 102 ++++++++++++++++++
 src/mlpack/tests/kmeans_test.cpp              |  66 ++++++++++++
 src/mlpack/tests/main.cpp                     |   4 +-
 5 files changed, 194 insertions(+), 10 deletions(-)
 create mode 100644 src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp

diff --git a/src/mlpack/methods/kmeans/CMakeLists.txt b/src/mlpack/methods/kmeans/CMakeLists.txt
index 1dbbbba626..6782ed2f66 100644
--- a/src/mlpack/methods/kmeans/CMakeLists.txt
+++ b/src/mlpack/methods/kmeans/CMakeLists.txt
@@ -14,6 +14,7 @@ set(SOURCES
   kill_empty_clusters.hpp
   kmeans.hpp
   kmeans_impl.hpp
+  kmeans_plus_plus_initialization.hpp
   max_variance_new_cluster.hpp
   max_variance_new_cluster_impl.hpp
   naive_kmeans.hpp
diff --git a/src/mlpack/methods/kmeans/kmeans_main.cpp b/src/mlpack/methods/kmeans/kmeans_main.cpp
index 4c7a689aec..1f0833e9da 100644
--- a/src/mlpack/methods/kmeans/kmeans_main.cpp
+++ b/src/mlpack/methods/kmeans/kmeans_main.cpp
@@ -17,6 +17,7 @@
 #include "allow_empty_clusters.hpp"
 #include "kill_empty_clusters.hpp"
 #include "refined_start.hpp"
+#include "kmeans_plus_plus_initialization.hpp"
 #include "elkan_kmeans.hpp"
 #include "hamerly_kmeans.hpp"
 #include "pelleg_moore_kmeans.hpp"
@@ -44,14 +45,17 @@ BINDING_LONG_DESC(
     " the point furthest from the centroid of the cluster with maximum variance"
     " is taken to fill that cluster."
     "\n\n"
-    "Optionally, the Bradley and Fayyad approach (\"Refining initial points for"
-    " k-means clustering\", 1998) can be used to select initial points by "
-    "specifying the " + PRINT_PARAM_STRING("refined_start") + " parameter.  "
-    "This approach works by taking random samplings of the dataset; to specify "
-    "the number of samplings, the " + PRINT_PARAM_STRING("samplings") +
-    " parameter is used, and to specify the percentage of the dataset to be "
-    "used in each sample, the " + PRINT_PARAM_STRING("percentage") +
-    " parameter is used (it should be a value between 0.0 and 1.0)."
+    "Optionally, the strategy to choose initial centroids can be specified.  "
+    "The k-means++ algorithm can be used to choose initial centroids with "
+    "the " + PRINT_PARAM_STRING("kmeans_plus_plus") + " parameter.  The "
+    "Bradley and Fayyad approach (\"Refining initial points for k-means "
+    "clustering\", 1998) can be used to select initial points by specifying "
+    "the " + PRINT_PARAM_STRING("refined_start") + " parameter.  This approach "
+    "works by taking random samplings of the dataset; to specify the number of "
+    "samplings, the " + PRINT_PARAM_STRING("samplings") + " parameter is used, "
+    "and to specify the percentage of the dataset to be used in each sample, "
+    "the " + PRINT_PARAM_STRING("percentage") + " parameter is used (it should "
+    "be a value between 0.0 and 1.0)."
     "\n\n"
     "There are several options available for the algorithm used for each Lloyd "
     "iteration, specified with the " + PRINT_PARAM_STRING("algorithm") + " "
@@ -102,6 +106,7 @@ BINDING_EXAMPLE(
 // See also...
 BINDING_SEE_ALSO("K-Means tutorial", "@doxygen/kmtutorial.html");
 BINDING_SEE_ALSO("@dbscan", "#dbscan");
+BINDING_SEE_ALSO("k-means++", "https://en.wikipedia.org/wiki/K-means%2B%2B");
 BINDING_SEE_ALSO("Using the triangle inequality to accelerate k-means (pdf)",
         "http://www.aaai.org/Papers/ICML/2003/ICML03-022.pdf");
 BINDING_SEE_ALSO("Making k-means even faster (pdf)",
@@ -147,6 +152,8 @@ PARAM_INT_IN("samplings", "Number of samplings to perform for refined start "
     "(use when --refined_start is specified).", "S", 100);
 PARAM_DOUBLE_IN("percentage", "Percentage of dataset to use for each refined "
     "start sampling (use when --refined_start is specified).", "p", 0.02);
+PARAM_FLAG("kmeans_plus_plus", "Use the k-means++ initialization strategy to "
+    "choose initial points.", "K");
 
 PARAM_STRING_IN("algorithm", "Algorithm to use for the Lloyd iteration "
     "('naive', 'pelleg-moore', 'elkan', 'hamerly', 'dualtree', or "
@@ -176,6 +183,9 @@ static void mlpackMain()
   else
     math::RandomSeed((size_t) std::time(NULL));
 
+  util::RequireOnlyOnePassed({ "refined_start", "kmeans_plus_plus" }, true,
+      "Only one initialization strategy can be specified!");
+
   // Now, start building the KMeans type that we'll be using.  Start with the
   // initial partition policy.  The call to FindEmptyClusterPolicy<> results in
   // a call to RunKMeans<> and the algorithm is completed.
@@ -191,6 +201,11 @@ static void mlpackMain()
 
     FindEmptyClusterPolicy<RefinedStart>(RefinedStart(samplings, percentage));
   }
+  else if (IO::HasParam("kmeans_plus_plus"))
+  {
+    FindEmptyClusterPolicy<KMeansPlusPlusInitialization>(
+        KMeansPlusPlusInitialization());
+  }
   else
   {
     FindEmptyClusterPolicy<SampleInitialization>(SampleInitialization());
diff --git a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
new file mode 100644
index 0000000000..23164ec231
--- /dev/null
+++ b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
@@ -0,0 +1,102 @@
+/**
+ * @file kmeans_plus_plus_initialization.hpp
+ * @author Ryan Curtin
+ *
+ * This file implements the k-means++ initialization strategy.
+ */
+#ifndef KMEANS_PLUS_PLUS_INITIALIZATION_HPP
+#define KMEANS_PLUS_PLUS_INITIALIZATION_HPP
+
+#include <mlpack/prereqs.hpp>
+
+/**
+ * This class implements the k-means++ initialization, as described in the
+ * following paper:
+ *
+ * @code
+ * @inproceedings{arthur2007k,
+ *   title={k-means++: The advantages of careful seeding},
+ *   author={Arthur, David and Vassilvitskii, Sergei},
+ *   booktitle={Proceedings of the Eighteenth Annual ACM-SIAM Symposium on
+ *        Discrete Algorithms (SODA '07)},
+ *   pages={1027--1035},
+ *   year={2007},
+ *   organization={Society for Industrial and Applied Mathematics}
+ * }
+ * @endcode
+ *
+ * In accordance with mlpack's InitialPartitionPolicy template type, we only
+ * need to implement a constructor and a method to compute the initial
+ * centroids.
+ */
+class KMeansPlusPlusInitialization
+{
+ public:
+  //! Empty constructor, required by the InitialPartitionPolicy type definition.
+  KMeansPlusPlusInitialization() { }
+
+  /**
+   * Initialize the centroids matrix by randomly sampling points from the data
+   * matrix.
+   *
+   * @param data Dataset.
+   * @param clusters Number of clusters.
+   * @param centroids Matrix to put initial centroids into.
+   */
+  template<typename MatType>
+  inline static void Cluster(const MatType& data,
+                             const size_t clusters,
+                             arma::mat& centroids)
+  {
+    centroids.set_size(data.n_rows, clusters);
+
+    // We'll sample our first point fully randomly.
+    size_t firstPoint = mlpack::math::RandInt(0, data.n_cols);
+    centroids.col(0) = data.col(firstPoint);
+
+    // Utility variable.
+    arma::vec distribution(data.n_cols);
+
+    // Now, sample other points...
+    for (size_t i = 1; i < clusters; ++i)
+    {
+      // We must compute the CDF for sampling... this depends on the computation
+      // of the minimum distance between each point and its closest
+      // already-chosen centroid.
+      //
+      // This computation is ripe for speedup with trees!  I am not sure exactly
+      // how much we would need to approximate, but I think it could be done
+      // without breaking the O(log k)-competitive guarantee (I think).
+      for (size_t p = 0; p < data.n_cols; ++p)
+      {
+        double minDistance = std::numeric_limits<double>::max();
+        for (size_t j = 0; j < i; ++j)
+        {
+          const double distance =
+              mlpack::metric::SquaredEuclideanDistance::Evaluate(data.col(p),
+              centroids.col(j));
+          minDistance = std::min(distance, minDistance);
+        }
+
+        distribution[p] = minDistance;
+      }
+
+      // Next normalize the distribution (actually technically we could avoid
+      // this.)
+      distribution /= arma::accu(distribution);
+
+      // Turn it into a CDF for convenience...
+      for (size_t j = 1; j < distribution.n_elem; ++j)
+        distribution[j] += distribution[j - 1];
+
+      // Sample a point...
+      const double sampleValue = mlpack::math::Random();
+      double* elem = std::lower_bound(distribution.begin(), distribution.end(),
+          sampleValue);
+      size_t position = (size_t) (elem - distribution.begin()) / sizeof(double);
+      centroids.col(i) = data.col(position);
+    }
+  }
+};
+
+#endif
diff --git a/src/mlpack/tests/kmeans_test.cpp b/src/mlpack/tests/kmeans_test.cpp
index 5d4bae2abf..ef14467b74 100644
--- a/src/mlpack/tests/kmeans_test.cpp
+++ b/src/mlpack/tests/kmeans_test.cpp
@@ -12,6 +12,7 @@
 #include <mlpack/methods/kmeans/kmeans.hpp>
 #include <mlpack/methods/kmeans/allow_empty_clusters.hpp>
 #include <mlpack/methods/kmeans/refined_start.hpp>
+#include <mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp>
 #include <mlpack/methods/kmeans/elkan_kmeans.hpp>
 #include <mlpack/methods/kmeans/hamerly_kmeans.hpp>
 #include <mlpack/methods/kmeans/pelleg_moore_kmeans.hpp>
@@ -486,6 +487,71 @@ TEST_CASE("RefinedStartTest", "[KMeansTest]")
   REQUIRE(distortion < 14000.0);
 }
 
+/**
+ * Test that the k-means++ initialization strategy returns decent initial
+ * cluster estimates.
+ */
+TEST_CASE("KMeansPlusPlusTest", "[KMeansTest]")
+{
+  // Our dataset will be five Gaussians of largely varying numbers of points and
+  // we expect that the refined starting policy should return good guesses at
+  // what these Gaussians are.
+  arma::mat data(3, 3000);
+  data.randn();
+
+  // First Gaussian: 10000 points, centered at (0, 0, 0).
+  // Second Gaussian: 2000 points, centered at (5, 0, -2).
+  // Third Gaussian: 5000 points, centered at (-2, -2, -2).
+  // Fourth Gaussian: 1000 points, centered at (-6, 8, 8).
+  // Fifth Gaussian: 12000 points, centered at (1, 6, 1).
+  arma::mat centroids(" 0  5 -2 -6  1;"
+                      " 0  0 -2  8  6;"
+                      " 0 -2 -2  8  1");
+
+  for (size_t i = 1000; i < 1200; ++i)
+    data.col(i) += centroids.col(1);
+  for (size_t i = 1200; i < 1700; ++i)
+    data.col(i) += centroids.col(2);
+  for (size_t i = 1700; i < 1800; ++i)
+    data.col(i) += centroids.col(3);
+  for (size_t i = 1800; i < 3000; ++i)
+    data.col(i) += centroids.col(4);
+
+  KMeansPlusPlusInitialization k;
+  arma::mat resultingCentroids;
+  k.Cluster(data, 5, resultingCentroids);
+
+  // Calculate resulting assignments.
+  arma::Row<size_t> assignments(data.n_cols);
+  for (size_t i = 0; i < data.n_cols; ++i)
+  {
+    double bestDist = DBL_MAX;
+    for (size_t j = 0; j < 5; ++j)
+    {
+      const double dist = metric::EuclideanDistance::Evaluate(data.col(i),
+          resultingCentroids.col(j));
+      if (dist < bestDist)
+      {
+        bestDist = dist;
+        assignments[i] = j;
+      }
+    }
+  }
+
+  // Calculate sum of distances from centroid means.
+  double distortion = 0;
+  for (size_t i = 0; i < 3000; ++i)
+    distortion += metric::EuclideanDistance::Evaluate(data.col(i),
+        resultingCentroids.col(assignments[i]));
+
+  // Using k-means++, the distance for this dataset is usually around
+  // 10000.  Regular k-means is between 10000 and 30000 (I think the 10000
+  // figure is a corner case which actually does not give good clusters), and
+  // random initial starts give distortion around 22000.  So we'll require that
+  // our distortion is less than 12000.
+  REQUIRE(distortion < 12000.0);
+}
+
 #ifdef ARMA_HAS_SPMAT
 /**
  * Make sure sparse k-means works okay.
diff --git a/src/mlpack/tests/main.cpp b/src/mlpack/tests/main.cpp
index 3267ae850d..44ae40d641 100644
--- a/src/mlpack/tests/main.cpp
+++ b/src/mlpack/tests/main.cpp
@@ -22,8 +22,8 @@ int main(int argc, char** argv)
    * each run.  This is good for ensuring that a test's tolerance is sufficient
    * across many different runs.
    */
-  // size_t seed = std::time(NULL);
-  // mlpack::math::RandomSeed(seed);
+  size_t seed = std::time(NULL);
+  mlpack::math::RandomSeed(seed);
   #ifndef TEST_VERBOSE
     #ifdef DEBUG
     mlpack::Log::Debug.ignoreInput = true;

From 295d24b42e1ea5b3544c321c858040b48c95ce65 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 09:50:32 -0500
Subject: [PATCH 099/253] Update HISTORY.

---
 HISTORY.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index 7529a3ee86..c5b118476e 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -13,6 +13,8 @@
 
   * Add finalizers to Julia binding model types to fix memory handling (#2756).
 
+  * Add k-means++ initialization strategy (#2813).
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.

From 2ea6d50b6da6b222f9e5190a4d8f4b2af4d7d0e5 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:36:56 -0500
Subject: [PATCH 100/253] Apply suggestions from code review

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
index 23164ec231..c4e074e4f7 100644
--- a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
+++ b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
@@ -1,5 +1,5 @@
 /**
- * @file kmeans_plus_plus_initialization.hpp
+ * @file methods/kmeans/kmeans_plus_plus_initialization.hpp
  * @author Ryan Curtin
  *
  * This file implements the k-means++ initialization strategy.
@@ -82,7 +82,7 @@ class KMeansPlusPlusInitialization
       }
 
       // Next normalize the distribution (actually technically we could avoid
-      // this.)
+      // this).
       distribution /= arma::accu(distribution);
 
       // Turn it into a CDF for convenience...

From 1d90bf817d757406a3141deb4da9abae104abc0e Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:38:02 -0500
Subject: [PATCH 101/253] Update header guard macro name.

---
 src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
index c4e074e4f7..ae63ee80c5 100644
--- a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
+++ b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
@@ -4,8 +4,8 @@
  *
  * This file implements the k-means++ initialization strategy.
  */
-#ifndef KMEANS_PLUS_PLUS_INITIALIZATION_HPP
-#define KMEANS_PLUS_PLUS_INITIALIZATION_HPP
+#ifndef MLPACK_METHODS_KMEANS_KMEANS_PLUS_PLUS_INITIALIZATION_HPP
+#define MLPACK_METHODS_KMEANS_KMEANS_PLUS_PLUS_INITIALIZATION_HPP
 
 #include <mlpack/prereqs.hpp>
 

From 79d2621a838256dafd77ab05645df6a178363d7c Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:39:20 -0500
Subject: [PATCH 102/253] Add const.

---
 .../methods/kmeans/kmeans_plus_plus_initialization.hpp     | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
index ae63ee80c5..e43c59fe1a 100644
--- a/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
+++ b/src/mlpack/methods/kmeans/kmeans_plus_plus_initialization.hpp
@@ -91,9 +91,10 @@ class KMeansPlusPlusInitialization
 
       // Sample a point...
       const double sampleValue = mlpack::math::Random();
-      double* elem = std::lower_bound(distribution.begin(), distribution.end(),
-          sampleValue);
-      size_t position = (size_t) (elem - distribution.begin()) / sizeof(double);
+      const double* elem = std::lower_bound(distribution.begin(),
+          distribution.end(), sampleValue);
+      const size_t position = (size_t)
+          (elem - distribution.begin()) / sizeof(double);
       centroids.col(i) = data.col(position);
     }
   }

From 4e39217837bd05934c2dc4a8cacacb0adc538bcd Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:53:01 -0500
Subject: [PATCH 103/253] Modify RequireOnlyOnePassed() to allow none to be
 passed.

---
 src/mlpack/core/util/param_checks.hpp      | 5 ++++-
 src/mlpack/core/util/param_checks_impl.hpp | 5 +++--
 src/mlpack/methods/kmeans/kmeans_main.cpp  | 6 +++---
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/src/mlpack/core/util/param_checks.hpp b/src/mlpack/core/util/param_checks.hpp
index a9180a4816..c1ac39aeea 100644
--- a/src/mlpack/core/util/param_checks.hpp
+++ b/src/mlpack/core/util/param_checks.hpp
@@ -43,11 +43,14 @@ namespace util {
  * @param fatal If true, output goes to Log::Fatal instead of Log::Warn and an
  *     exception is thrown.
  * @param customErrorMessage Error message to append.
+ * @param allowNone If true, then no error message will be thrown if none of the
+ *     parameters in the constraints were passed.
  */
 void RequireOnlyOnePassed(
     const std::vector<std::string>& constraints,
     const bool fatal = true,
-    const std::string& customErrorMessage = "");
+    const std::string& customErrorMessage = "",
+    const bool allowNone = false);
 
 /**
  * Require that at least one of the given parameters in the constraints set was
diff --git a/src/mlpack/core/util/param_checks_impl.hpp b/src/mlpack/core/util/param_checks_impl.hpp
index be88c8a3e9..8562e1341f 100644
--- a/src/mlpack/core/util/param_checks_impl.hpp
+++ b/src/mlpack/core/util/param_checks_impl.hpp
@@ -21,7 +21,8 @@ namespace util {
 inline void RequireOnlyOnePassed(
     const std::vector<std::string>& constraints,
     const bool fatal,
-    const std::string& errorMessage)
+    const std::string& errorMessage,
+    const bool allowNone)
 {
   if (BINDING_IGNORE_CHECK(constraints))
     return;
@@ -57,7 +58,7 @@ inline void RequireOnlyOnePassed(
       stream << "; " << errorMessage;
     stream << "!" << std::endl;
   }
-  else if (set == 0)
+  else if (set == 0 && !allowNone)
   {
     stream << (fatal ? "Must " : "Should ");
 
diff --git a/src/mlpack/methods/kmeans/kmeans_main.cpp b/src/mlpack/methods/kmeans/kmeans_main.cpp
index 1f0833e9da..4707c05b7e 100644
--- a/src/mlpack/methods/kmeans/kmeans_main.cpp
+++ b/src/mlpack/methods/kmeans/kmeans_main.cpp
@@ -183,8 +183,8 @@ static void mlpackMain()
   else
     math::RandomSeed((size_t) std::time(NULL));
 
-  util::RequireOnlyOnePassed({ "refined_start", "kmeans_plus_plus" }, true,
-      "Only one initialization strategy can be specified!");
+  RequireOnlyOnePassed({ "refined_start", "kmeans_plus_plus" }, true,
+      "Only one initialization strategy can be specified!", true);
 
   // Now, start building the KMeans type that we'll be using.  Start with the
   // initial partition policy.  The call to FindEmptyClusterPolicy<> results in
@@ -286,7 +286,7 @@ void RunKMeans(const InitialPartitionPolicy& ipp)
   const int maxIterations = IO::GetParam<int>("max_iterations");
 
   // Make sure we have an output file if we're not doing the work in-place.
-  RequireAtLeastOnePassed({ "in_place", "output", "centroid" }, false,
+  RequireOnlyOnePassed({ "in_place", "output", "centroid" }, false,
       "no results will be saved");
 
   arma::mat dataset = IO::GetParam<arma::mat>("input");  // Load our dataset.

From 5ffb8b4ea41424fcdaf0063f917befd81b681c5d Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:53:50 -0500
Subject: [PATCH 104/253] Update src/mlpack/tests/main.cpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/tests/main.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/tests/main.cpp b/src/mlpack/tests/main.cpp
index 44ae40d641..3267ae850d 100644
--- a/src/mlpack/tests/main.cpp
+++ b/src/mlpack/tests/main.cpp
@@ -22,8 +22,8 @@ int main(int argc, char** argv)
    * each run.  This is good for ensuring that a test's tolerance is sufficient
    * across many different runs.
    */
-  size_t seed = std::time(NULL);
-  mlpack::math::RandomSeed(seed);
+  // size_t seed = std::time(NULL);
+  // mlpack::math::RandomSeed(seed);
   #ifndef TEST_VERBOSE
     #ifdef DEBUG
     mlpack::Log::Debug.ignoreInput = true;

From 2f504f5669c570401b8e4efc260813ab7a1bead3 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 21 Jan 2021 18:55:46 -0500
Subject: [PATCH 105/253] Fix style.

---
 src/mlpack/methods/cf/cf_main.cpp | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/methods/cf/cf_main.cpp b/src/mlpack/methods/cf/cf_main.cpp
index ce083c8c4a..0c8cd49539 100644
--- a/src/mlpack/methods/cf/cf_main.cpp
+++ b/src/mlpack/methods/cf/cf_main.cpp
@@ -371,10 +371,15 @@ static void mlpackMain()
       arma::Mat<size_t> users =
           std::move(IO::GetParam<arma::Mat<size_t>>("query"));
       if (users.n_rows > 1)
+      {
         users = users.t();
+      }
+
       if (users.n_rows > 1)
+      {
         Log::Fatal << "List of query users must be one-dimensional!"
-                   << std::endl;
+            << std::endl;
+      }
 
       Log::Info << "Generating recommendations for " << users.n_elem
           << " users." << endl;

From 0c77578f47cac2d14a67e70af56bb9260f511036 Mon Sep 17 00:00:00 2001
From: jeffin143 <jeffinsam@karunya.edu.in>
Date: Fri, 22 Jan 2021 21:18:33 +0530
Subject: [PATCH 106/253] Add cereal library to history

---
 HISTORY.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index c8a3c94497..b7b0ad75ee 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -16,6 +16,8 @@
   * HMM: add functions to calculate likelihood for data stream with/without
     pre-calculated emission probability (#2142).
 
+  * Replace boost Boost serialization library by Cereal (#2458).
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.

From 22e3fb4bff0512e98716ea3b3c6922b22de56a4c Mon Sep 17 00:00:00 2001
From: jeffin sam <jeffinsam@karunya.edu.in>
Date: Sat, 23 Jan 2021 01:40:33 +0530
Subject: [PATCH 107/253] Update HISTORY.md

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 HISTORY.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/HISTORY.md b/HISTORY.md
index b7b0ad75ee..001e6e2762 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -16,7 +16,7 @@
   * HMM: add functions to calculate likelihood for data stream with/without
     pre-calculated emission probability (#2142).
 
-  * Replace boost Boost serialization library by Cereal (#2458).
+  * Replace Boost serialization library by Cereal (#2458).
 
 ### mlpack 3.4.2
 ###### 2020-10-26

From eba621e9cbc965f4ea209d2d2f500d05c9168842 Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Fri, 22 Jan 2021 22:48:37 +0100
Subject: [PATCH 108/253] Remove libarmadillo-dev from the path, keep the
 manually installed one

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 .ci/linux-steps.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.ci/linux-steps.yaml b/.ci/linux-steps.yaml
index 21baace148..eba826ac92 100644
--- a/.ci/linux-steps.yaml
+++ b/.ci/linux-steps.yaml
@@ -21,7 +21,7 @@ steps:
     unset BOOST_ROOT
     echo "##vso[task.setvariable variable=BOOST_ROOT]"$BOOST_ROOT
 
-    sudo apt-get install -y --allow-unauthenticated libopenblas-dev liblapack-dev g++ libboost1.70-dev libarmadillo-dev xz-utils
+    sudo apt-get install -y --allow-unauthenticated libopenblas-dev liblapack-dev g++ libboost1.70-dev xz-utils
 
     if [ "$(binding)" == "python" ]; then
       export PYBIN=$(which python)

From 0e8e6f1ba14755e072f68f952625f7dca0a32c15 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Sat, 23 Jan 2021 19:53:47 +0530
Subject: [PATCH 109/253] simplification

---
 src/mlpack/core/util/io.cpp      | 29 ++++++++++++++---------------
 src/mlpack/core/util/io.hpp      |  3 ++-
 src/mlpack/core/util/io_impl.hpp |  6 +++---
 3 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index d36b287a4e..8687a6df12 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -279,27 +279,26 @@ void IO::CheckInputMatrices()
     std::string paramType = itr->second.cppType;
 
     if (paramType == "arma::mat")
-      IO::CheckInputMatrix<arma::Mat<double>>(paramName);
+      IO::CheckInputMatrix<arma::Mat<double>>(
+          IO::GetParam<arma::Mat<double>>(paramName), paramName);
     else if (paramType == "arma::Mat<size_t>")
-      IO::CheckInputMatrix<arma::Mat<size_t>>(paramName);
+      IO::CheckInputMatrix<arma::Mat<size_t>>(
+          IO::GetParam<arma::Mat<size_t>>(paramName), paramName);
     else if (paramType == "arma::colvec")
-      IO::CheckInputMatrix<arma::Col<double>>(paramName);
+      IO::CheckInputMatrix<arma::Col<double>>(
+          IO::GetParam<arma::Col<double>>(paramName), paramName);
     else if (paramType == "arma::Col<size_t>")
-      IO::CheckInputMatrix<arma::Col<size_t>>(paramName);
+      IO::CheckInputMatrix<arma::Col<size_t>>(
+          IO::GetParam<arma::Col<size_t>>(paramName), paramName);
     else if (paramType == "arma::rowvec")
-      IO::CheckInputMatrix<arma::Row<double>>(paramName);
+      IO::CheckInputMatrix<arma::Row<double>>(
+          IO::GetParam<arma::Row<double>>(paramName), paramName);
     else if (paramType == "arma::Row<size_t>")
-      IO::CheckInputMatrix<arma::Row<size_t>>(paramName);
+      IO::CheckInputMatrix<arma::Row<size_t>>(
+          IO::GetParam<arma::Row<size_t>>(paramName), paramName);
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
-    {
-      std::string errMsg1 = "The input " + paramName + " has NaN values.";
-      std::string errMsg2 = "The input " + paramName + " has inf values.";
-
-      if (std::get<1>(GetParam<TupleType>(paramName)).has_nan())
-        Log::Fatal << errMsg1 << std::endl;
-      if (std::get<1>(GetParam<TupleType>(paramName)).has_inf())
-        Log::Fatal << errMsg2 << std::endl;
-    }
+      IO::CheckInputMatrix<arma::Mat<double>>(
+        std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);
   }
 }
 
diff --git a/src/mlpack/core/util/io.hpp b/src/mlpack/core/util/io.hpp
index 5189695abe..aa9d71c16f 100644
--- a/src/mlpack/core/util/io.hpp
+++ b/src/mlpack/core/util/io.hpp
@@ -222,10 +222,11 @@ class IO
   /**
    * Utility function for CheckInputMatrices().
    *
+   * @param matrix Matrix to check.
    * @param identifier Name of the parameter in question.
    */
   template<typename T>
-  static void CheckInputMatrix(const std::string& identifier);
+  static void CheckInputMatrix(const T& matrix, const std::string& identifier);
 
   /**
    * Given two (matrix) parameters, ensure that the first is an in-place copy of
diff --git a/src/mlpack/core/util/io_impl.hpp b/src/mlpack/core/util/io_impl.hpp
index f54aaa4eab..e7407efd7f 100644
--- a/src/mlpack/core/util/io_impl.hpp
+++ b/src/mlpack/core/util/io_impl.hpp
@@ -146,14 +146,14 @@ T& IO::GetRawParam(const std::string& identifier)
 }
 
 template<typename T>
-void IO::CheckInputMatrix(const std::string& identifier)
+void IO::CheckInputMatrix(const T& matrix, const std::string& identifier)
 {
   std::string errMsg1 = "The input " + identifier + " has NaN values.";
   std::string errMsg2 = "The input " + identifier + " has inf values.";
 
-  if (GetParam<T>(identifier).has_nan())
+  if (matrix.has_nan())
     Log::Fatal << errMsg1 << std::endl;
-  if (GetParam<T>(identifier).has_inf())
+  if (matrix.has_inf())
     Log::Fatal << errMsg2 << std::endl;
 }
 

From 654e6503d892e9f4934266a5f977297c56a44b10 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Sat, 23 Jan 2021 19:57:18 +0530
Subject: [PATCH 110/253] updated HISTORY.md

---
 HISTORY.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index 001e6e2762..0c81a8265a 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -1,5 +1,8 @@
 ### mlpack ?.?.?
 ###### ????-??-??
+  * Add "check_input_matrices" option to python bindings that checks
+    for NaN and inf values in all the input matrices (#2787).
+
   * Add Adjusted R squared functionality to R2Score::Evaluate (#2624).
 
   * Disabled all the bindings by default in CMake (#2782).

From 33af71dbce383b4809509429d40603aa4e69a1ab Mon Sep 17 00:00:00 2001
From: Nippun Sharma <53967069+NippunSharma@users.noreply.github.com>
Date: Sun, 24 Jan 2021 00:35:21 +0530
Subject: [PATCH 111/253] Update src/mlpack/core/util/io.cpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/util/io.cpp | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 8687a6df12..dba1bbecd8 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -279,26 +279,36 @@ void IO::CheckInputMatrices()
     std::string paramType = itr->second.cppType;
 
     if (paramType == "arma::mat")
-      IO::CheckInputMatrix<arma::Mat<double>>(
-          IO::GetParam<arma::Mat<double>>(paramName), paramName);
+    {
+      IO::CheckInputMatrix(IO::GetParam<arma::mat>(paramName), paramName);
+    }
     else if (paramType == "arma::Mat<size_t>")
-      IO::CheckInputMatrix<arma::Mat<size_t>>(
+    {
+      IO::CheckInputMatrix(
           IO::GetParam<arma::Mat<size_t>>(paramName), paramName);
+    }
     else if (paramType == "arma::colvec")
-      IO::CheckInputMatrix<arma::Col<double>>(
-          IO::GetParam<arma::Col<double>>(paramName), paramName);
+    {
+      IO::CheckInputMatrix(IO::GetParam<arma::colvec>(paramName), paramName);
+    }
     else if (paramType == "arma::Col<size_t>")
-      IO::CheckInputMatrix<arma::Col<size_t>>(
+    {
+      IO::CheckInputMatrix(
           IO::GetParam<arma::Col<size_t>>(paramName), paramName);
+    }
     else if (paramType == "arma::rowvec")
-      IO::CheckInputMatrix<arma::Row<double>>(
-          IO::GetParam<arma::Row<double>>(paramName), paramName);
+    {
+      IO::CheckInputMatrix(IO::GetParam<arma::rowvec>(paramName), paramName);
+    }
     else if (paramType == "arma::Row<size_t>")
-      IO::CheckInputMatrix<arma::Row<size_t>>(
+    {
+      IO::CheckInputMatrix(
           IO::GetParam<arma::Row<size_t>>(paramName), paramName);
+    }
     else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
-      IO::CheckInputMatrix<arma::Mat<double>>(
+    {
+      IO::CheckInputMatrix(
         std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);
+    }
   }
 }
-

From 723ecf82ebf0a6e47d3ab50e9804bc1a2f8f32f9 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Sun, 24 Jan 2021 00:36:50 +0530
Subject: [PATCH 112/253] added more tests

---
 .../python/tests/test_python_binding.py       | 108 ++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index f6beffa483..207e8711d3 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1354,6 +1354,60 @@ class TestPythonBinding(unittest.TestCase):
                                                    matrix_in=x,
                                                    check_input_matrices=True))
 
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                  int_in=12,
+                                                  double_in=4.0,
+                                                  mat_req_in=[[1.0]],
+                                                  col_req_in=[1.0],
+                                                  umatrix_in=x,
+                                                  check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   row_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   urow_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   col_in=x,
+                                                   check_input_matrices=True))
+ 
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   ucol_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   matrix_and_info_in=x,
+                                                   check_input_matrices=True))
+
   def testCheckInputMatricesInf(self):
     """
     Checks that an exception is thrown if the input matrix contains
@@ -1372,5 +1426,59 @@ class TestPythonBinding(unittest.TestCase):
                                                    matrix_in=x,
                                                    check_input_matrices=True))
 
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                  int_in=12,
+                                                  double_in=4.0,
+                                                  mat_req_in=[[1.0]],
+                                                  col_req_in=[1.0],
+                                                  umatrix_in=x,
+                                                  check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   row_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   urow_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   col_in=x,
+                                                   check_input_matrices=True))
+ 
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   ucol_in=x,
+                                                   check_input_matrices=True))
+
+    self.assertRaises(RuntimeError,
+                      lambda : test_python_binding(string_in="hello",
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   matrix_and_info_in=x,
+                                                   check_input_matrices=True))
+
 if __name__ == '__main__':
   unittest.main()

From 8cc834fe4357a0a5289f739c9fcc8c8ee277c02d Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Sat, 23 Jan 2021 20:20:03 +0100
Subject: [PATCH 113/253] Remove lapack, it is not need, openblas should be
 enough

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 .ci/linux-steps.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.ci/linux-steps.yaml b/.ci/linux-steps.yaml
index eba826ac92..f695c14fe1 100644
--- a/.ci/linux-steps.yaml
+++ b/.ci/linux-steps.yaml
@@ -21,7 +21,7 @@ steps:
     unset BOOST_ROOT
     echo "##vso[task.setvariable variable=BOOST_ROOT]"$BOOST_ROOT
 
-    sudo apt-get install -y --allow-unauthenticated libopenblas-dev liblapack-dev g++ libboost1.70-dev xz-utils
+    sudo apt-get install -y --allow-unauthenticated libopenblas-dev g++ libboost1.70-dev xz-utils
 
     if [ "$(binding)" == "python" ]; then
       export PYBIN=$(which python)

From 141b92d07cef34ace3b3e2714125195755cb9183 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Sun, 24 Jan 2021 00:57:00 +0530
Subject: [PATCH 114/253] fixes

---
 .../python/tests/test_python_binding.py       | 28 +++++++++++++------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index 207e8711d3..0fcdb70353 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1363,13 +1363,16 @@ class TestPythonBinding(unittest.TestCase):
                                                   umatrix_in=x,
                                                   check_input_matrices=True))
 
+    x_row = np.random.rand(1, 100)
+    a = np.random.randint(low=0, high=100)
+    x_row[0][a] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   row_in=x,
+                                                   row_in=x_row,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1378,16 +1381,19 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   urow_in=x,
+                                                   urow_in=x_row,
                                                    check_input_matrices=True))
 
+    x_col = np.random.rand(100, 1)
+    a = np.random.randint(low=0, high=100)
+    x_col[a][0] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   col_in=x,
+                                                   col_in=x_col,
                                                    check_input_matrices=True))
  
     self.assertRaises(RuntimeError,
@@ -1396,7 +1402,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   ucol_in=x,
+                                                   ucol_in=x_col,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1435,13 +1441,16 @@ class TestPythonBinding(unittest.TestCase):
                                                   umatrix_in=x,
                                                   check_input_matrices=True))
 
+    x_row = np.random.rand(1, 100)
+    a = np.random.randint(low=0, high=100)
+    x_row[0][a] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   row_in=x,
+                                                   row_in=x_row,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1450,16 +1459,19 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   urow_in=x,
+                                                   urow_in=x_row,
                                                    check_input_matrices=True))
 
+    x_col = np.random.rand(100, 1)
+    a = np.random.randint(low=0, high=100)
+    x_col[a][0] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   col_in=x,
+                                                   col_in=x_col,
                                                    check_input_matrices=True))
  
     self.assertRaises(RuntimeError,
@@ -1468,7 +1480,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   ucol_in=x,
+                                                   ucol_in=x_col,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,

From 0d31176db8dfe643578d66645d759e29abcd2876 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Sun, 24 Jan 2021 21:14:41 +0530
Subject: [PATCH 115/253] added check for unsigned matrix

---
 src/mlpack/core/util/io.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index dba1bbecd8..8c36aa442a 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -287,6 +287,11 @@ void IO::CheckInputMatrices()
       IO::CheckInputMatrix(
           IO::GetParam<arma::Mat<size_t>>(paramName), paramName);
     }
+    else if (paramType == "arma::Mat<unsigned int>")
+    {
+      IO::CheckInputMatrix(
+          IO::GetParam<arma::Mat<unsigned int>>(paramName), paramName);
+    }
     else if (paramType == "arma::colvec")
     {
       IO::CheckInputMatrix(IO::GetParam<arma::colvec>(paramName), paramName);

From 954f3c490e8d0617f09a74dba55233bd0804d289 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Mon, 25 Jan 2021 00:51:57 +0530
Subject: [PATCH 116/253] fixing parameter types while checking

---
 .../python/tests/test_python_binding.py       | 48 +++++++++----------
 src/mlpack/core/util/io.cpp                   | 10 +---
 2 files changed, 26 insertions(+), 32 deletions(-)

diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index 0fcdb70353..c4af5fa18b 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1341,7 +1341,7 @@ class TestPythonBinding(unittest.TestCase):
     Checks that an exception is thrown if the input matrix contains
     NaN values.
     """
-    x = np.random.rand(100, 5)
+    x = np.random.randint(low=0, high=500, size=[100, 5]).astype(float)
     a = np.random.randint(low=0, high=100)
     b = np.random.randint(low=0, high=5)
     x[a][b] = np.nan
@@ -1356,16 +1356,16 @@ class TestPythonBinding(unittest.TestCase):
 
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
-                                                  int_in=12,
-                                                  double_in=4.0,
-                                                  mat_req_in=[[1.0]],
-                                                  col_req_in=[1.0],
-                                                  umatrix_in=x,
-                                                  check_input_matrices=True))
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   umatrix_in=x,
+                                                   check_input_matrices=True))
 
-    x_row = np.random.rand(1, 100)
+    x_row = np.random.randint(0, high=500, size=100).astype(float)
     a = np.random.randint(low=0, high=100)
-    x_row[0][a] = np.nan
+    x_row[a] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1384,9 +1384,9 @@ class TestPythonBinding(unittest.TestCase):
                                                    urow_in=x_row,
                                                    check_input_matrices=True))
 
-    x_col = np.random.rand(100, 1)
+    x_col = np.random.randint(0, high=500, size=100).astype(float)
     a = np.random.randint(low=0, high=100)
-    x_col[a][0] = np.nan
+    x_col[a] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1395,7 +1395,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    col_req_in=[1.0],
                                                    col_in=x_col,
                                                    check_input_matrices=True))
- 
+
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1419,7 +1419,7 @@ class TestPythonBinding(unittest.TestCase):
     Checks that an exception is thrown if the input matrix contains
     inf values.
     """
-    x = np.random.rand(100, 5)
+    x = np.random.randint(low=0, high=500, size=[100, 5]).astype(float)
     a = np.random.randint(low=0, high=100)
     b = np.random.randint(low=0, high=5)
     x[a][b] = np.inf
@@ -1434,16 +1434,16 @@ class TestPythonBinding(unittest.TestCase):
 
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
-                                                  int_in=12,
-                                                  double_in=4.0,
-                                                  mat_req_in=[[1.0]],
-                                                  col_req_in=[1.0],
-                                                  umatrix_in=x,
-                                                  check_input_matrices=True))
+                                                   int_in=12,
+                                                   double_in=4.0,
+                                                   mat_req_in=[[1.0]],
+                                                   col_req_in=[1.0],
+                                                   umatrix_in=x,
+                                                   check_input_matrices=True))
 
-    x_row = np.random.rand(1, 100)
+    x_row = np.random.randint(0, high=500, size=100).astype(float)
     a = np.random.randint(low=0, high=100)
-    x_row[0][a] = np.inf
+    x_row[a] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1462,9 +1462,9 @@ class TestPythonBinding(unittest.TestCase):
                                                    urow_in=x_row,
                                                    check_input_matrices=True))
 
-    x_col = np.random.rand(100, 1)
+    x_col = np.random.randint(0, high=500, size=100).astype(float)
     a = np.random.randint(low=0, high=100)
-    x_col[a][0] = np.inf
+    x_col[a] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
@@ -1473,7 +1473,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    col_req_in=[1.0],
                                                    col_in=x_col,
                                                    check_input_matrices=True))
- 
+
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 8c36aa442a..e13903d6cf 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -277,7 +277,6 @@ void IO::CheckInputMatrices()
   {
     std::string paramName = itr->first;
     std::string paramType = itr->second.cppType;
-
     if (paramType == "arma::mat")
     {
       IO::CheckInputMatrix(IO::GetParam<arma::mat>(paramName), paramName);
@@ -287,14 +286,9 @@ void IO::CheckInputMatrices()
       IO::CheckInputMatrix(
           IO::GetParam<arma::Mat<size_t>>(paramName), paramName);
     }
-    else if (paramType == "arma::Mat<unsigned int>")
+    else if (paramType == "arma::vec")
     {
-      IO::CheckInputMatrix(
-          IO::GetParam<arma::Mat<unsigned int>>(paramName), paramName);
-    }
-    else if (paramType == "arma::colvec")
-    {
-      IO::CheckInputMatrix(IO::GetParam<arma::colvec>(paramName), paramName);
+      IO::CheckInputMatrix(IO::GetParam<arma::vec>(paramName), paramName);
     }
     else if (paramType == "arma::Col<size_t>")
     {

From 3890be60f15be006771a8192d1151ec4642adf11 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sun, 24 Jan 2021 17:21:07 -0500
Subject: [PATCH 117/253] Update tolerance.

---
 src/mlpack/tests/kmeans_test.cpp | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/tests/kmeans_test.cpp b/src/mlpack/tests/kmeans_test.cpp
index ef14467b74..c20014c046 100644
--- a/src/mlpack/tests/kmeans_test.cpp
+++ b/src/mlpack/tests/kmeans_test.cpp
@@ -548,8 +548,9 @@ TEST_CASE("KMeansPlusPlusTest", "[KMeansTest]")
   // 10000.  Regular k-means is between 10000 and 30000 (I think the 10000
   // figure is a corner case which actually does not give good clusters), and
   // random initial starts give distortion around 22000.  So we'll require that
-  // our distortion is less than 12000.
-  REQUIRE(distortion < 12000.0);
+  // our distortion is less than 14500.  (It seems like there is a lot of noise
+  // in the result.)
+  REQUIRE(distortion < 14500.0);
 }
 
 #ifdef ARMA_HAS_SPMAT

From f5b32bc890c38f38f1e763907c3c9401f5b18fec Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Mon, 25 Jan 2021 19:59:51 +0530
Subject: [PATCH 118/253] removing size_t tests

---
 .../python/tests/test_python_binding.py       | 80 +++----------------
 src/mlpack/core/util/io.cpp                   |  2 +-
 2 files changed, 11 insertions(+), 71 deletions(-)

diff --git a/src/mlpack/bindings/python/tests/test_python_binding.py b/src/mlpack/bindings/python/tests/test_python_binding.py
index c4af5fa18b..dd67aed974 100644
--- a/src/mlpack/bindings/python/tests/test_python_binding.py
+++ b/src/mlpack/bindings/python/tests/test_python_binding.py
@@ -1341,7 +1341,7 @@ class TestPythonBinding(unittest.TestCase):
     Checks that an exception is thrown if the input matrix contains
     NaN values.
     """
-    x = np.random.randint(low=0, high=500, size=[100, 5]).astype(float)
+    x = np.random.rand(100, 5)
     a = np.random.randint(low=0, high=100)
     b = np.random.randint(low=0, high=5)
     x[a][b] = np.nan
@@ -1354,25 +1354,16 @@ class TestPythonBinding(unittest.TestCase):
                                                    matrix_in=x,
                                                    check_input_matrices=True))
 
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   umatrix_in=x,
-                                                   check_input_matrices=True))
-
-    x_row = np.random.randint(0, high=500, size=100).astype(float)
+    x_vec = np.random.rand(100)
     a = np.random.randint(low=0, high=100)
-    x_row[a] = np.nan
+    x_vec[a] = np.nan
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   row_in=x_row,
+                                                   row_in=x_vec,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1381,28 +1372,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   urow_in=x_row,
-                                                   check_input_matrices=True))
-
-    x_col = np.random.randint(0, high=500, size=100).astype(float)
-    a = np.random.randint(low=0, high=100)
-    x_col[a] = np.nan
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   col_in=x_col,
-                                                   check_input_matrices=True))
-
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   ucol_in=x_col,
+                                                   col_in=x_vec,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1419,7 +1389,7 @@ class TestPythonBinding(unittest.TestCase):
     Checks that an exception is thrown if the input matrix contains
     inf values.
     """
-    x = np.random.randint(low=0, high=500, size=[100, 5]).astype(float)
+    x = np.random.rand(100, 5)
     a = np.random.randint(low=0, high=100)
     b = np.random.randint(low=0, high=5)
     x[a][b] = np.inf
@@ -1432,25 +1402,16 @@ class TestPythonBinding(unittest.TestCase):
                                                    matrix_in=x,
                                                    check_input_matrices=True))
 
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   umatrix_in=x,
-                                                   check_input_matrices=True))
-
-    x_row = np.random.randint(0, high=500, size=100).astype(float)
+    x_vec = np.random.rand(100)
     a = np.random.randint(low=0, high=100)
-    x_row[a] = np.inf
+    x_vec[a] = np.inf
     self.assertRaises(RuntimeError,
                       lambda : test_python_binding(string_in="hello",
                                                    int_in=12,
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   row_in=x_row,
+                                                   row_in=x_vec,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
@@ -1459,28 +1420,7 @@ class TestPythonBinding(unittest.TestCase):
                                                    double_in=4.0,
                                                    mat_req_in=[[1.0]],
                                                    col_req_in=[1.0],
-                                                   urow_in=x_row,
-                                                   check_input_matrices=True))
-
-    x_col = np.random.randint(0, high=500, size=100).astype(float)
-    a = np.random.randint(low=0, high=100)
-    x_col[a] = np.inf
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   col_in=x_col,
-                                                   check_input_matrices=True))
-
-    self.assertRaises(RuntimeError,
-                      lambda : test_python_binding(string_in="hello",
-                                                   int_in=12,
-                                                   double_in=4.0,
-                                                   mat_req_in=[[1.0]],
-                                                   col_req_in=[1.0],
-                                                   ucol_in=x_col,
+                                                   col_in=x_vec,
                                                    check_input_matrices=True))
 
     self.assertRaises(RuntimeError,
diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index e13903d6cf..c3c3182ac3 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -304,7 +304,7 @@ void IO::CheckInputMatrices()
       IO::CheckInputMatrix(
           IO::GetParam<arma::Row<size_t>>(paramName), paramName);
     }
-    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
+    else if (paramType == "TUPLE_TYPE")
     {
       IO::CheckInputMatrix(
         std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);

From 7ec4058f35e6af50db55123a0c16899763b574f4 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Tue, 26 Jan 2021 19:08:07 +0530
Subject: [PATCH 119/253] removed size_t conditions from CheckInputMatrices()

---
 src/mlpack/core/util/io.cpp | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index c3c3182ac3..2c9efefb3a 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -281,29 +281,14 @@ void IO::CheckInputMatrices()
     {
       IO::CheckInputMatrix(IO::GetParam<arma::mat>(paramName), paramName);
     }
-    else if (paramType == "arma::Mat<size_t>")
-    {
-      IO::CheckInputMatrix(
-          IO::GetParam<arma::Mat<size_t>>(paramName), paramName);
-    }
     else if (paramType == "arma::vec")
     {
       IO::CheckInputMatrix(IO::GetParam<arma::vec>(paramName), paramName);
     }
-    else if (paramType == "arma::Col<size_t>")
-    {
-      IO::CheckInputMatrix(
-          IO::GetParam<arma::Col<size_t>>(paramName), paramName);
-    }
     else if (paramType == "arma::rowvec")
     {
       IO::CheckInputMatrix(IO::GetParam<arma::rowvec>(paramName), paramName);
     }
-    else if (paramType == "arma::Row<size_t>")
-    {
-      IO::CheckInputMatrix(
-          IO::GetParam<arma::Row<size_t>>(paramName), paramName);
-    }
     else if (paramType == "TUPLE_TYPE")
     {
       IO::CheckInputMatrix(

From 16ff91b60b201bde0c18aff0a4aa35e839eba613 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Tue, 26 Jan 2021 21:58:03 +0530
Subject: [PATCH 120/253] made definition of TUPLE_TYPE inline

---
 src/mlpack/core/util/param.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index 208ca64b2f..c820df4b65 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1013,9 +1013,9 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  * collisions are still possible, and they produce bizarre error messages.  See
  * https://github.com/mlpack/mlpack/issues/100 for more information.
  */
-#define TUPLE_TYPE std::tuple<mlpack::data::DatasetInfo, arma::mat>
 #define PARAM_MATRIX_AND_INFO_IN(ID, DESC, ALIAS) \
-    PARAM_IN(TUPLE_TYPE, ID, DESC, ALIAS, TUPLE_TYPE(), false)
+    PARAM_IN(std::tuple<mlpack::data::DatasetInfo, arma::mat>, ID, DESC, \
+        ALIAS, std::tuple<mlpack::data::DatasetInfo, arma::mat>(), false)
 
 /**
  * Define an input model.  From the command line, the user can specify the file

From 458b302c39ffbf11e293ea115f8eeca8eec9bdc5 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Wed, 27 Jan 2021 00:31:58 +0530
Subject: [PATCH 121/253] removed TUPLE_TYPE

---
 src/mlpack/core/util/io.cpp    | 2 +-
 src/mlpack/core/util/param.hpp | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 2c9efefb3a..9dd571e369 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -289,7 +289,7 @@ void IO::CheckInputMatrices()
     {
       IO::CheckInputMatrix(IO::GetParam<arma::rowvec>(paramName), paramName);
     }
-    else if (paramType == "TUPLE_TYPE")
+    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
     {
       IO::CheckInputMatrix(
         std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);
diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index c820df4b65..73f462e464 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1014,8 +1014,8 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  * https://github.com/mlpack/mlpack/issues/100 for more information.
  */
 #define PARAM_MATRIX_AND_INFO_IN(ID, DESC, ALIAS) \
-    PARAM_IN(std::tuple<mlpack::data::DatasetInfo, arma::mat>, ID, DESC, \
-        ALIAS, std::tuple<mlpack::data::DatasetInfo, arma::mat>(), false)
+    PARAM_IN(std::tuple<mlpack::data::DatasetInfo, arma::mat>, ID, DESC, ALIAS, \
+        std::tuple<mlpack::data::DatasetInfo, arma::mat>(), false)
 
 /**
  * Define an input model.  From the command line, the user can specify the file

From ab3110e08965b437e62d44fcb8162074907a3dea Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Wed, 27 Jan 2021 00:33:23 +0530
Subject: [PATCH 122/253] minor change

---
 src/mlpack/core/util/io.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index 9dd571e369..b7ca51987e 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -289,7 +289,7 @@ void IO::CheckInputMatrices()
     {
       IO::CheckInputMatrix(IO::GetParam<arma::rowvec>(paramName), paramName);
     }
-    else if (paramType == "std::tuple<data::DatasetInfo, arma::mat>")
+    else if (paramType == "std::tuple<mlpack::data::DatasetInfo, arma::mat>")
     {
       IO::CheckInputMatrix(
         std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);

From 28f369cb14c0b81d64f78d0f382df1034356926a Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Tue, 26 Jan 2021 23:32:29 -0500
Subject: [PATCH 123/253] Update src/mlpack/core/tree/hrectbound.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/core/tree/hrectbound.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/tree/hrectbound.hpp b/src/mlpack/core/tree/hrectbound.hpp
index 31186f621d..6b8ef6c69a 100644
--- a/src/mlpack/core/tree/hrectbound.hpp
+++ b/src/mlpack/core/tree/hrectbound.hpp
@@ -80,7 +80,7 @@ class HRectBound
   //! Move constructor: take possession of another bound's information.
   HRectBound(HRectBound&& other);
 
-  //! Move assignment operator
+  //! Move assignment operator.
   HRectBound& operator=(HRectBound&& other);
 
   //! Destructor: clean up memory.

From e2adf5ec7c08a7495de2d855736db49164801c37 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Tue, 26 Jan 2021 23:32:37 -0500
Subject: [PATCH 124/253] Update
 src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 .../termination_policies/incomplete_incremental_termination.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp b/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
index d01fdfd4c5..5646b0d205 100644
--- a/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/incomplete_incremental_termination.hpp
@@ -36,7 +36,7 @@ class IncompleteIncrementalTermination
   IncompleteIncrementalTermination(
       TerminationPolicy tPolicy = TerminationPolicy()) :
       tPolicy(tPolicy), incrementalIndex(0), iteration(0)
-  { /** Nothing to do here. */ }
+  { /* Nothing to do here. */ }
 
   /**
    * Initializes the termination policy before stating the factorization.

From dd8f73d246ea4e4745fef1f2510ec436cc8bbb94 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Tue, 26 Jan 2021 23:32:46 -0500
Subject: [PATCH 125/253] Update
 src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 .../termination_policies/complete_incremental_termination.hpp  | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp b/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
index bdd02d7fec..78eb24108e 100644
--- a/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/complete_incremental_termination.hpp
@@ -37,7 +37,7 @@ class CompleteIncrementalTermination
   CompleteIncrementalTermination(
       TerminationPolicy tPolicy = TerminationPolicy()) :
       tPolicy(tPolicy), incrementalIndex(0), iteration(0)
-  { /** Nothing to do here. */ }
+  { /* Nothing to do here. */ }
 
   /**
    * Initializes the termination policy before stating the factorization.
@@ -120,4 +120,3 @@ class CompleteIncrementalTermination
 } // namespace mlpack
 
 #endif // MLPACK_METHODS_AMF_COMPLETE_INCREMENTAL_TERMINATION_HPP
-

From 0914fe94394eaefba557a304b37c8a25283ee66f Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Wed, 27 Jan 2021 16:01:41 +0530
Subject: [PATCH 126/253] added PARAM_IN_WITH_NAME

---
 src/mlpack/core/util/param.hpp | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index 73f462e464..e2b58d1dcd 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1013,9 +1013,11 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  * collisions are still possible, and they produce bizarre error messages.  See
  * https://github.com/mlpack/mlpack/issues/100 for more information.
  */
+#define TUPLE_TYPE std::tuple<mlpack::data::DatasetInfo, arma::mat>
 #define PARAM_MATRIX_AND_INFO_IN(ID, DESC, ALIAS) \
-    PARAM_IN(std::tuple<mlpack::data::DatasetInfo, arma::mat>, ID, DESC, ALIAS, \
-        std::tuple<mlpack::data::DatasetInfo, arma::mat>(), false)
+    PARAM_IN_WITH_NAME(TUPLE_TYPE, ID, DESC, ALIAS, \
+        "std::tuple<mlpack::data::DatasetInfo, arma::mat>", TUPLE_TYPE(), \
+        false)
 
 /**
  * Define an input model.  From the command line, the user can specify the file
@@ -1228,6 +1230,11 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
       JOIN(io_option_dummy_object_in_, __COUNTER__) \
       (DEF, ID, DESC, ALIAS, #T, REQ, true, false, testName);
 
+  #define PARAM_IN_WITH_NAME(T, ID, DESC, ALIAS, NAME, DEF, REQ) \
+      static mlpack::util::Option<T> \
+      JOIN(io_option_dummy_object_in_, __COUNTER__) \
+      (DEF, ID, DESC, ALIAS, NAME, REQ, true, false, testName);
+
   #define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
       static mlpack::util::Option<T> \
       JOIN(io_option_dummy_object_out_, __COUNTER__) \
@@ -1285,6 +1292,11 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
       JOIN(JOIN(io_option_dummy_object_in_, __LINE__), opt) \
       (DEF, ID, DESC, ALIAS, #T, REQ, true, false, testName);
 
+  #define PARAM_IN_WITH_NAME(T, ID, DESC, ALIAS, NAME, DEF, REQ) \
+      static mlpack::util::Option<T> \
+      JOIN(JOIN(io_option_dummy_object_in_, __LINE__), opt) \
+      (DEF, ID, DESC, ALIAS, NAME, REQ, true, false, testName);
+
   #define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
       static mlpack::util::Option<T> \
       JOIN(JOIN(io_option_dummy_object_out_, __LINE__), opt) \

From 46281ee3ef45a6bd25b6cf170a0a3becba256ef1 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Wed, 27 Jan 2021 19:20:44 -0500
Subject: [PATCH 127/253] Update HISTORY and ANN tutorial.

---
 HISTORY.md                |  5 ++++-
 doc/tutorials/ann/ann.txt | 13 +++++++------
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/HISTORY.md b/HISTORY.md
index ffc90ca02a..6d1cd06bc4 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -12,7 +12,7 @@
   * Add Triplet Margin Loss function (#2762).
 
   * Add finalizers to Julia binding model types to fix memory handling (#2756).
-  
+
   * HMM: add functions to calculate likelihood for data stream with/without
     pre-calculated emission probability (#2142).
 
@@ -23,6 +23,9 @@
 
   * Add k-means++ initialization strategy (#2813).
 
+  * `NegativeLogLikelihood<>` now expects classes in the range `0` to
+    `numClasses - 1` (#2534).
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.
diff --git a/doc/tutorials/ann/ann.txt b/doc/tutorials/ann/ann.txt
index 7cdb9d1f57..43678fb84e 100644
--- a/doc/tutorials/ann/ann.txt
+++ b/doc/tutorials/ann/ann.txt
@@ -210,8 +210,9 @@ int main()
   data::Load("thyroid_test.csv", testData, true);
 
   // Split the labels from the training set and testing set respectively.
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
-  arma::mat testLabels = testData.row(testData.n_rows - 1);
+  // Decrement the labels by 1, so they are in the range 0 to (numClasses - 1).
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
+  arma::mat testLabels = testData.row(testData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
 
@@ -246,9 +247,8 @@ int main()
   // Find index of max prediction for each data point and store in "prediction"
   for (size_t i = 0; i < predictionTemp.n_cols; ++i)
   {
-    // we add 1 to the max index, so that it matches the actual test labels.
     prediction(i) = arma::as_scalar(arma::find(
-        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) + 1;
+        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1));
   }
 
   /*
@@ -311,7 +311,7 @@ void RNNModel()
   for (size_t i = 0; i < labelsTemp.n_cols; ++i)
   {
     const int value = arma::as_scalar(arma::find(
-        arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1)) + 1;
+        arma::max(labelsTemp.col(i)) == labelsTemp.col(i), 1));
     labels.col(i).fill(value);
   }
 
@@ -589,8 +589,9 @@ arma::mat trainData = dataset.submat(0, 0, dataset.n_rows - 4,
     dataset.n_cols - 1);
 
 // Split the data from the training set.
+// Subtract 1 so the labels are the range from 0 to (numClasses - 1).
 arma::mat trainLabels = dataset.submat(dataset.n_rows - 3, 0,
-    dataset.n_rows - 1, dataset.n_cols - 1);
+    dataset.n_rows - 1, dataset.n_cols - 1) - 1;
 
 // Initialize the network.
 FFN<> model;

From 5b76b2f5e752bb3f298de89568eaa9d20a0e56de Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Thu, 28 Jan 2021 13:02:19 +0530
Subject: [PATCH 128/253] changed PARAM_IN_WITH_NAME to PARAM_COMPLETE and
 editted other macros

---
 src/mlpack/core/util/param.hpp | 136 +++++++++------------------------
 1 file changed, 37 insertions(+), 99 deletions(-)

diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index e2b58d1dcd..8652db4fbe 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1015,9 +1015,9 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  */
 #define TUPLE_TYPE std::tuple<mlpack::data::DatasetInfo, arma::mat>
 #define PARAM_MATRIX_AND_INFO_IN(ID, DESC, ALIAS) \
-    PARAM_IN_WITH_NAME(TUPLE_TYPE, ID, DESC, ALIAS, \
-        "std::tuple<mlpack::data::DatasetInfo, arma::mat>", TUPLE_TYPE(), \
-        false)
+    PARAM_COMPLETE(TUPLE_TYPE, ID, DESC, ALIAS, \
+        "std::tuple<mlpack::data::DatasetInfo, arma::mat>", false, true, true, \
+        TUPLE_TYPE())
 
 /**
  * Define an input model.  From the command line, the user can specify the file
@@ -1208,6 +1208,36 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
 #define PARAM_VECTOR_IN_REQ(T, ID, DESC, ALIAS) \
     PARAM_IN(std::vector<T>, ID, DESC, ALIAS, std::vector<T>(), true);
 
+#define PARAM_IN(T, ID, DESC, ALIAS, DEF, REQ) \
+    PARAM_COMPLETE(T, ID, DESC, ALIAS, #T, REQ, true, false, DEF);
+
+#define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
+    PARAM_COMPLETE(T, ID, DESC, ALIAS, #T, REQ, false, false, DEF);
+
+#define PARAM_MATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::mat, ID, DESC, ALIAS, "arma::mat", REQ, IN, \
+        TRANS, arma::mat());
+
+#define PARAM_UMATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::Mat<size_t>, ID, DESC, ALIAS, "arma::Mat<size_t>", \
+        REQ, IN, TRANS, arma::Mat<size_t>());
+
+#define PARAM_COL(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::vec, ID, DESC, ALIAS, "arma::vec", REQ, IN, TRANS, \
+        arma::vec());
+
+#define PARAM_UCOL(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::Col<size_t>, ID, DESC, ALIAS, "arma::Col<size_t>", \
+        REQ, IN, TRANS, arma::Col<size_t>());
+
+#define PARAM_ROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::rowvec, ID, DESC, ALIAS, "arma::rowvec", REQ, IN, \
+    TRANS, arma::rowvec());
+
+#define PARAM_UROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
+    PARAM_COMPLETE(arma::Row<size_t>, ID, DESC, ALIAS, "arma::Row<size_t>", \
+    REQ, IN, TRANS, arma::Row<size_t>());
+
 /**
  * Define an input parameter.  Don't use this function; use the other ones above
  * that call it.  Note that we are using the __LINE__ macro for naming these
@@ -1225,56 +1255,10 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  * @param REQ Whether or not parameter is required (boolean value).
  */
 #ifdef __COUNTER__
-  #define PARAM_IN(T, ID, DESC, ALIAS, DEF, REQ) \
+  #define PARAM_COMPLETE(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
       static mlpack::util::Option<T> \
       JOIN(io_option_dummy_object_in_, __COUNTER__) \
-      (DEF, ID, DESC, ALIAS, #T, REQ, true, false, testName);
-
-  #define PARAM_IN_WITH_NAME(T, ID, DESC, ALIAS, NAME, DEF, REQ) \
-      static mlpack::util::Option<T> \
-      JOIN(io_option_dummy_object_in_, __COUNTER__) \
-      (DEF, ID, DESC, ALIAS, NAME, REQ, true, false, testName);
-
-  #define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
-      static mlpack::util::Option<T> \
-      JOIN(io_option_dummy_object_out_, __COUNTER__) \
-      (DEF, ID, DESC, ALIAS, #T, REQ, false, false, testName);
-
-  #define PARAM_MATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::mat> \
-      JOIN(io_option_dummy_matrix_, __COUNTER__) \
-      (arma::mat(), ID, DESC, ALIAS, "arma::mat", \
-      REQ, IN, !TRANS, testName);
-
-  #define PARAM_UMATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Mat<size_t>> \
-      JOIN(io_option_dummy_umatrix_, __COUNTER__) \
-      (arma::Mat<size_t>(), ID, DESC, ALIAS, "arma::Mat<size_t>", \
-      REQ, IN, !TRANS, testName);
-
-  #define PARAM_COL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::vec> \
-      JOIN(io_option_dummy_col_, __COUNTER__) \
-      (arma::vec(), ID, DESC, ALIAS, "arma::vec", \
-      REQ, IN, !TRANS, testName);
-
-  #define PARAM_UCOL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Col<size_t>> \
-      JOIN(io_option_dummy_ucol_, __COUNTER__) \
-      (arma::Col<size_t>(), ID, DESC, ALIAS, "arma::Col<size_t>", \
-      REQ, IN, !TRANS, testName);
-
-  #define PARAM_ROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::rowvec> \
-      JOIN(io_option_dummy_row_, __COUNTER__) \
-      (arma::rowvec(), ID, DESC, ALIAS, "arma::rowvec", \
-      REQ, IN, !TRANS, testName);
-
-  #define PARAM_UROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Row<size_t>> \
-      JOIN(io_option_dummy_urow_, __COUNTER__) \
-      (arma::Row<size_t>(), ID, DESC, ALIAS, "arma::Row<size_t>", \
-      REQ, IN, !TRANS, testName);
+      (DEF, ID, DESC, ALIAS, NAME, REQ, IN, !TRANS, testName);
 
   // There are no uses of required models, so that is not an option to this
   // macro (it would be easy to add).
@@ -1287,56 +1271,10 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
   // don't think we can absolutely guarantee success, but it should be "good
   // enough".  We use the __LINE__ macro and the type of the parameter to try
   // and get a good guess at something unique.
-  #define PARAM_IN(T, ID, DESC, ALIAS, DEF, REQ) \
+  #define PARAM_COMPLETE(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
       static mlpack::util::Option<T> \
       JOIN(JOIN(io_option_dummy_object_in_, __LINE__), opt) \
-      (DEF, ID, DESC, ALIAS, #T, REQ, true, false, testName);
-
-  #define PARAM_IN_WITH_NAME(T, ID, DESC, ALIAS, NAME, DEF, REQ) \
-      static mlpack::util::Option<T> \
-      JOIN(JOIN(io_option_dummy_object_in_, __LINE__), opt) \
-      (DEF, ID, DESC, ALIAS, NAME, REQ, true, false, testName);
-
-  #define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
-      static mlpack::util::Option<T> \
-      JOIN(JOIN(io_option_dummy_object_out_, __LINE__), opt) \
-      (DEF, ID, DESC, ALIAS, #T, REQ, false, false, testName);
-
-  #define PARAM_MATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::mat> \
-      JOIN(JOIN(io_option_dummy_object_matrix_, __LINE__), opt) \
-      (arma::mat(), ID, DESC, ALIAS, "arma::mat", REQ, IN, !TRANS, \
-      testName);
-
-  #define PARAM_UMATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Mat<size_t>> \
-      JOIN(JOIN(io_option_dummy_object_umatrix_, __LINE__), opt) \
-      (arma::Mat<size_t>(), ID, DESC, ALIAS, "arma::Mat<size_t>", REQ, IN, \
-      !TRANS, testName);
-
-  #define PARAM_COL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::vec> \
-      JOIN(io_option_dummy_object_col_, __LINE__) \
-      (arma::vec(), ID, DESC, ALIAS, "arma::vec", REQ, IN, !TRANS, \
-      testName);
-
-  #define PARAM_UCOL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Col<size_t>> \
-      JOIN(io_option_dummy_object_ucol_, __LINE__) \
-      (arma::Col<size_t>(), ID, DESC, ALIAS, "arma::Col<size_t>", REQ, IN, \
-      !TRANS, testName);
-
-  #define PARAM_ROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::rowvec> \
-      JOIN(io_option_dummy_object_row_, __LINE__) \
-      (arma::rowvec(), ID, DESC, ALIAS, "arma::rowvec", REQ, IN, !TRANS, \
-      testName);
-
-  #define PARAM_UROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-      static mlpack::util::Option<arma::Row<size_t>> \
-      JOIN(io_option_dummy_object_urow_, __LINE__) \
-      (arma::Row<size_t>(), ID, DESC, ALIAS, "arma::Row<size_t>", REQ, IN, \
-      !TRANS, testName);
+      (DEF, ID, DESC, ALIAS, NAME, REQ, IN, !TRANS, testName);
 
   #define PARAM_MODEL(TYPE, ID, DESC, ALIAS, REQ, IN) \
       static mlpack::util::Option<TYPE*> \

From 3664422c3996b59a140854e1a1d4bc02497f7ce6 Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Thu, 28 Jan 2021 13:23:23 +0530
Subject: [PATCH 129/253] added comments

---
 src/mlpack/core/util/param.hpp | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index 8652db4fbe..9499e1a870 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1208,6 +1208,9 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
 #define PARAM_VECTOR_IN_REQ(T, ID, DESC, ALIAS) \
     PARAM_IN(std::vector<T>, ID, DESC, ALIAS, std::vector<T>(), true);
 
+/**
+ * Defining useful macros using PARAM_COMPLETE() macro defined later.
+ */
 #define PARAM_IN(T, ID, DESC, ALIAS, DEF, REQ) \
     PARAM_COMPLETE(T, ID, DESC, ALIAS, #T, REQ, true, false, DEF);
 
@@ -1239,11 +1242,11 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
     REQ, IN, TRANS, arma::Row<size_t>());
 
 /**
- * Define an input parameter.  Don't use this function; use the other ones above
- * that call it.  Note that we are using the __LINE__ macro for naming these
- * actual parameters when __COUNTER__ does not exist, which is a bit of an ugly
- * hack... but this is the preprocessor, after all.  We don't have much choice
- * other than ugliness.
+ * Define the PARAM_COMPLETE(), PARAM_MODEL() macro. Don't use this function; 
+ * use the other ones above that call it.  Note that we are using the __LINE__
+ * macro for naming these actual parameters when __COUNTER__ does not exist, 
+ * which is a bit of an ugly hack... but this is the preprocessor, after all.
+ * We don't have much choice other than ugliness.
  *
  * @param T Type of the parameter.
  * @param ID Name of the parameter.

From b48ba3e77d9aea9ef0ede600f058355d448d0aa8 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 28 Jan 2021 14:03:33 -0500
Subject: [PATCH 130/253] Normalize labels of thyroid data.

---
 src/mlpack/tests/feedforward_network_test.cpp | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_test.cpp b/src/mlpack/tests/feedforward_network_test.cpp
index f12573e4ee..552145704e 100644
--- a/src/mlpack/tests/feedforward_network_test.cpp
+++ b/src/mlpack/tests/feedforward_network_test.cpp
@@ -109,7 +109,8 @@ TEST_CASE("CheckCopyMovingVanillaNetworkTest", "[FeedForwardNetworkTest]")
   arma::mat trainData;
   data::Load("thyroid_train.csv", trainData, true);
 
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
+  // Normalize labels to [0, 2].
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
 
   /*
@@ -162,7 +163,8 @@ TEST_CASE("CheckCopyMovingReparametrizationNetworkTest", "[FeedForwardNetworkTes
   arma::mat trainData;
   data::Load("thyroid_train.csv", trainData, true);
 
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
+  // Normalize labels to [0, 2].
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
 
   /*
@@ -196,7 +198,8 @@ TEST_CASE("CheckCopyMovingLinear3DNetworkTest", "[FeedForwardNetworkTest]")
   arma::mat trainData;
   data::Load("thyroid_train.csv", trainData, true);
 
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
+  // Normalize labels to [0, 2].
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
 
   /*
@@ -334,7 +337,8 @@ TEST_CASE("CheckCopyMovingDropoutNetworkTest", "[FeedForwardNetworkTest]")
   arma::mat trainData;
   data::Load("thyroid_train.csv", trainData, true);
 
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
+  // Normalize labels to [0, 2].
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
 
   /*
@@ -962,13 +966,14 @@ TEST_CASE("FFNCheckInputShapeTest", "[FeedForwardNetworkTest]")
   arma::mat trainData;
   data::Load("thyroid_train.csv", trainData, true);
 
-  arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
+  // Normalize labels to [0, 2].
+  arma::mat trainLabels = trainData.row(trainData.n_rows - 1) - 1;
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
   data::Load("thyroid_test.csv", testData, true);
 
-  arma::mat testLabels = testData.row(testData.n_rows - 1);
+  arma::mat testLabels = testData.row(testData.n_rows - 1) - 1;
   testData.shed_row(testData.n_rows - 1);
 
   FFN<NegativeLogLikelihood<>, RandomInitialization, CustomLayer<> > model;

From 5dd135b551e799612744668d36ae2071fe6b5893 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Thu, 28 Jan 2021 20:22:59 -0500
Subject: [PATCH 131/253] Fix (hopefully) last test.

---
 src/mlpack/tests/feedforward_network_test.cpp | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_test.cpp b/src/mlpack/tests/feedforward_network_test.cpp
index 552145704e..d4789aac1c 100644
--- a/src/mlpack/tests/feedforward_network_test.cpp
+++ b/src/mlpack/tests/feedforward_network_test.cpp
@@ -248,10 +248,10 @@ TEST_CASE("CheckCopyMovingLinear3DNetworkTest", "[FeedForwardNetworkTest]")
  */
 TEST_CASE("CheckCopyMovingNoisyLinearTest", "[FeedForwardNetworkTest]")
 {
-  // Create training input by 5x5 matrix.
-  arma::mat input = arma::randu(10,1);
-  // Create training output by 1 matrix.
-  arma::mat output = arma::mat("1");
+  // Create training input by 10x1 matrix (only 1 point).
+  arma::mat input = arma::randu(10, 1);
+  // Create training output by 1-point matrix.
+  arma::mat output = arma::mat("0");
 
   // Check copying constructor.
   FFN<NegativeLogLikelihood<>> *model1 = new FFN<NegativeLogLikelihood<>>();

From d7bc9e364890ab53b442c7143ac950b7edbf2e53 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <60036798+rxng8@users.noreply.github.com>
Date: Fri, 29 Jan 2021 00:04:59 -0500
Subject: [PATCH 132/253] Update src/mlpack/core/tree/hrectbound_impl.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/tree/hrectbound_impl.hpp | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/core/tree/hrectbound_impl.hpp b/src/mlpack/core/tree/hrectbound_impl.hpp
index a1259a677c..491e25fed6 100644
--- a/src/mlpack/core/tree/hrectbound_impl.hpp
+++ b/src/mlpack/core/tree/hrectbound_impl.hpp
@@ -107,10 +107,9 @@ inline HRectBound<MetricType, ElemType>::HRectBound(
  * Move assignment operator.
  */
 template<typename MetricType, typename ElemType>
-inline HRectBound<
-    MetricType,
-    ElemType>& HRectBound<MetricType,
-    ElemType>::operator=(HRectBound<MetricType, ElemType>&& other)
+inline HRectBound<MetricType, ElemType>&
+HRectBound<MetricType, ElemType>::operator=(
+    HRectBound<MetricType, ElemType>&& other)
 {
   if (this != &other)
   {

From 53571929d57ef8a1a4bf4b3f52cc034465661419 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 29 Jan 2021 01:05:49 -0500
Subject: [PATCH 133/253] next static code fix

---
 src/mlpack/core/tree/ballbound_impl.hpp       | 32 ++++++++++++-------
 .../simple_residue_termination.hpp            | 14 ++++----
 src/mlpack/methods/hmm/hmm_model.hpp          |  6 ++++
 3 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/src/mlpack/core/tree/ballbound_impl.hpp b/src/mlpack/core/tree/ballbound_impl.hpp
index 5722fb854a..59cc86a5ea 100644
--- a/src/mlpack/core/tree/ballbound_impl.hpp
+++ b/src/mlpack/core/tree/ballbound_impl.hpp
@@ -71,10 +71,14 @@ template<typename MetricType, typename VecType>
 BallBound<MetricType, VecType>& BallBound<MetricType, VecType>::operator=(
     const BallBound& other)
 {
-  radius = other.radius;
-  center = other.center;
-  metric = other.metric;
-  ownsMetric = false;
+  if (this != &other)
+  {
+    radius = other.radius;
+    center = other.center;
+    metric = other.metric;
+    ownsMetric = false;
+  }
+  return *this;
 }
 
 //! Move constructor.
@@ -97,15 +101,19 @@ template<typename MetricType, typename VecType>
 BallBound<MetricType, VecType>& BallBound<MetricType, VecType>::operator=(
     BallBound&& other)
 {
-  radius = other.radius;
-  center = std::move(other.center);
-  metric = other.metric;
-  ownsMetric = other.ownsMetric;
+  if (this != &other)
+  {
+    radius = other.radius;
+    center = std::move(other.center);
+    metric = other.metric;
+    ownsMetric = other.ownsMetric;
 
-  other.radius = 0.0;
-  other.center = VecType();
-  other.metric = nullptr;
-  other.ownsMetric = false;
+    other.radius = 0.0;
+    other.center = VecType();
+    other.metric = nullptr;
+    other.ownsMetric = false;
+  }
+  return *this;
 }
 
 //! Destructor to release allocated memory.
diff --git a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
index 81893f4fa3..86631e32ce 100644
--- a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
@@ -40,13 +40,13 @@ class SimpleResidueTermination
    * @param maxIterations Maximum number of iterations.
    */
   SimpleResidueTermination(const double minResidue = 1e-5,
-                           const size_t maxIterations = 10000)
-      : minResidue(minResidue), 
-        maxIterations(maxIterations), 
-        residue(0.0), 
-        iteration(0), 
-        nm(0), 
-        normOld(0) 
+                           const size_t maxIterations = 10000) : 
+    minResidue(minResidue),
+    maxIterations(maxIterations),
+    residue(0.0),
+    iteration(0),
+    nm(0),
+    normOld(0)
   { 
     // Nothing to do here.
   }
diff --git a/src/mlpack/methods/hmm/hmm_model.hpp b/src/mlpack/methods/hmm/hmm_model.hpp
index 0a2bce384b..7665397bdc 100644
--- a/src/mlpack/methods/hmm/hmm_model.hpp
+++ b/src/mlpack/methods/hmm/hmm_model.hpp
@@ -139,6 +139,12 @@ class HMMModel
       gaussianHMM = other.gaussianHMM;
       gmmHMM = other.gmmHMM;
       diagGMMHMM = other.diagGMMHMM;
+
+      other.type = HMMType::DiscreteHMM;
+      other.discreteHMM = new HMM<distribution::DiscreteDistribution>();
+      other.gaussianHMM = nullptr;
+      other.gmmHMM = nullptr;
+      other.diagGMMHMM = nullptr;
     }
     return *this;
   }

From 8b6d068913b2be86589bc8d0625accd6287d1483 Mon Sep 17 00:00:00 2001
From: Alex Nguyen <alexvn.edu@gmail.com>
Date: Fri, 29 Jan 2021 01:59:45 -0500
Subject: [PATCH 134/253] next static code fix

---
 .../hoeffding_trees/hoeffding_tree_impl.hpp   | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
index 5e31358621..f79b0eb027 100644
--- a/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
+++ b/src/mlpack/methods/hoeffding_trees/hoeffding_tree_impl.hpp
@@ -251,6 +251,16 @@ HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>::
   // Remove pointers.
   other.dimensionMappings = nullptr;
   other.datasetInfo = nullptr;
+
+  // Reset primary type variables.
+  other.numSamples = 0;
+  other.numClasses = 0;
+  other.checkInterval = 0;
+  other.minSamples = 0;
+  other.successProbability = 0.0;
+  other.splitDimension = 0;
+  other.majorityClass = 0;
+  other.majorityProbability = 0.0;
 }
 
 // Copy assignment operator.
@@ -327,9 +337,20 @@ HoeffdingTree<FitnessFunction, NumericSplitType, CategoricalSplitType>&
     majorityProbability = other.majorityProbability;
     categoricalSplit = std::move(other.categoricalSplit);
     numericSplit = std::move(other.numericSplit);
+
     // Remove pointers.
     other.dimensionMappings = nullptr;
     other.datasetInfo = nullptr;
+
+    // Reset primary type variables.
+    other.numSamples = 0;
+    other.numClasses = 0;
+    other.checkInterval = 0;
+    other.minSamples = 0;
+    other.successProbability = 0.0;
+    other.splitDimension = 0;
+    other.majorityClass = 0;
+    other.majorityProbability = 0.0;
   }
   return *this;
 }

From 23c39033dee1f3b543d5b982f6708554fa6fd1df Mon Sep 17 00:00:00 2001
From: Nippun Sharma <53967069+NippunSharma@users.noreply.github.com>
Date: Fri, 29 Jan 2021 18:04:40 +0530
Subject: [PATCH 135/253] Update src/mlpack/core/util/io.cpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/util/io.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/util/io.cpp b/src/mlpack/core/util/io.cpp
index b7ca51987e..904a155cc0 100644
--- a/src/mlpack/core/util/io.cpp
+++ b/src/mlpack/core/util/io.cpp
@@ -292,7 +292,7 @@ void IO::CheckInputMatrices()
     else if (paramType == "std::tuple<mlpack::data::DatasetInfo, arma::mat>")
     {
       IO::CheckInputMatrix(
-        std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);
+          std::get<1>(IO::GetParam<TupleType>(paramName)), paramName);
     }
   }
 }

From 9a3815fc1475f4bebf2d31416d800b5b13ab84dc Mon Sep 17 00:00:00 2001
From: NippunSharma <www.inbox.nippun@gmail.com>
Date: Fri, 29 Jan 2021 18:08:37 +0530
Subject: [PATCH 136/253] changed name to PARAM

---
 src/mlpack/core/util/param.hpp | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/src/mlpack/core/util/param.hpp b/src/mlpack/core/util/param.hpp
index 9499e1a870..fc809c5b6e 100644
--- a/src/mlpack/core/util/param.hpp
+++ b/src/mlpack/core/util/param.hpp
@@ -1015,7 +1015,7 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  */
 #define TUPLE_TYPE std::tuple<mlpack::data::DatasetInfo, arma::mat>
 #define PARAM_MATRIX_AND_INFO_IN(ID, DESC, ALIAS) \
-    PARAM_COMPLETE(TUPLE_TYPE, ID, DESC, ALIAS, \
+    PARAM(TUPLE_TYPE, ID, DESC, ALIAS, \
         "std::tuple<mlpack::data::DatasetInfo, arma::mat>", false, true, true, \
         TUPLE_TYPE())
 
@@ -1209,40 +1209,40 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
     PARAM_IN(std::vector<T>, ID, DESC, ALIAS, std::vector<T>(), true);
 
 /**
- * Defining useful macros using PARAM_COMPLETE() macro defined later.
+ * Defining useful macros using PARAM macro defined later.
  */
 #define PARAM_IN(T, ID, DESC, ALIAS, DEF, REQ) \
-    PARAM_COMPLETE(T, ID, DESC, ALIAS, #T, REQ, true, false, DEF);
+    PARAM(T, ID, DESC, ALIAS, #T, REQ, true, false, DEF);
 
 #define PARAM_OUT(T, ID, DESC, ALIAS, DEF, REQ) \
-    PARAM_COMPLETE(T, ID, DESC, ALIAS, #T, REQ, false, false, DEF);
+    PARAM(T, ID, DESC, ALIAS, #T, REQ, false, false, DEF);
 
 #define PARAM_MATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::mat, ID, DESC, ALIAS, "arma::mat", REQ, IN, \
+    PARAM(arma::mat, ID, DESC, ALIAS, "arma::mat", REQ, IN, \
         TRANS, arma::mat());
 
 #define PARAM_UMATRIX(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::Mat<size_t>, ID, DESC, ALIAS, "arma::Mat<size_t>", \
+    PARAM(arma::Mat<size_t>, ID, DESC, ALIAS, "arma::Mat<size_t>", \
         REQ, IN, TRANS, arma::Mat<size_t>());
 
 #define PARAM_COL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::vec, ID, DESC, ALIAS, "arma::vec", REQ, IN, TRANS, \
+    PARAM(arma::vec, ID, DESC, ALIAS, "arma::vec", REQ, IN, TRANS, \
         arma::vec());
 
 #define PARAM_UCOL(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::Col<size_t>, ID, DESC, ALIAS, "arma::Col<size_t>", \
+    PARAM(arma::Col<size_t>, ID, DESC, ALIAS, "arma::Col<size_t>", \
         REQ, IN, TRANS, arma::Col<size_t>());
 
 #define PARAM_ROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::rowvec, ID, DESC, ALIAS, "arma::rowvec", REQ, IN, \
+    PARAM(arma::rowvec, ID, DESC, ALIAS, "arma::rowvec", REQ, IN, \
     TRANS, arma::rowvec());
 
 #define PARAM_UROW(ID, DESC, ALIAS, REQ, TRANS, IN) \
-    PARAM_COMPLETE(arma::Row<size_t>, ID, DESC, ALIAS, "arma::Row<size_t>", \
+    PARAM(arma::Row<size_t>, ID, DESC, ALIAS, "arma::Row<size_t>", \
     REQ, IN, TRANS, arma::Row<size_t>());
 
 /**
- * Define the PARAM_COMPLETE(), PARAM_MODEL() macro. Don't use this function; 
+ * Define the PARAM(), PARAM_MODEL() macro. Don't use this function; 
  * use the other ones above that call it.  Note that we are using the __LINE__
  * macro for naming these actual parameters when __COUNTER__ does not exist, 
  * which is a bit of an ugly hack... but this is the preprocessor, after all.
@@ -1258,7 +1258,7 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
  * @param REQ Whether or not parameter is required (boolean value).
  */
 #ifdef __COUNTER__
-  #define PARAM_COMPLETE(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
+  #define PARAM(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
       static mlpack::util::Option<T> \
       JOIN(io_option_dummy_object_in_, __COUNTER__) \
       (DEF, ID, DESC, ALIAS, NAME, REQ, IN, !TRANS, testName);
@@ -1274,7 +1274,7 @@ using DatasetInfo = DatasetMapper<IncrementPolicy, std::string>;
   // don't think we can absolutely guarantee success, but it should be "good
   // enough".  We use the __LINE__ macro and the type of the parameter to try
   // and get a good guess at something unique.
-  #define PARAM_COMPLETE(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
+  #define PARAM(T, ID, DESC, ALIAS, NAME, REQ, IN, TRANS, DEF) \
       static mlpack::util::Option<T> \
       JOIN(JOIN(io_option_dummy_object_in_, __LINE__), opt) \
       (DEF, ID, DESC, ALIAS, NAME, REQ, IN, !TRANS, testName);

From e339c551e0baf1d3f65fa538572d84e6f7b939a9 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Tue, 2 Feb 2021 19:40:34 +0530
Subject: [PATCH 137/253] Review Cfixes

---
 .../methods/ann/loss_functions/hinge_loss.hpp |  5 +++-
 .../ann/loss_functions/hinge_loss_impl.hpp    |  2 +-
 src/mlpack/tests/loss_functions_test.cpp      | 30 +++++++++++--------
 3 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
index a9c2563b9e..37e6ed20f4 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
@@ -22,6 +22,8 @@ namespace ann /** Artificial Neural Network. */ {
  * Computes the hinge loss between y_true and y_pred. Expects y_true to be
  * either -1 or 1. If y_true is either 0 or 1, a temporary conversion is made to
  * calculate the loss.
+ * The hinge loss \f$l(y_true, y_pred)\f$ is defined as
+ * \f$l(y_true, y_pred) = max(0, 1 - y_true*y_pred)\f$.
  *
  * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
  *         arma::sp_mat or arma::cube).
@@ -37,6 +39,7 @@ class HingeLoss
  public:
   /**
    * Create HingeLoss object.
+   *
    * @param reduction Specifies the reduction to apply to the output. If false,
    *                  'mean' reduction is used, where sum of the output will be
    *                  divided by the number of elements in the output. If
@@ -54,7 +57,7 @@ class HingeLoss
    */
   template<typename PredictionType, typename TargetType>
   typename PredictionType::elem_type Forward(const PredictionType& prediction,
-                                              const TargetType& target);
+                                             const TargetType& target);
 
   /**
    * Ordinary feed backward pass of a neural network.
diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
index 85fb07cb88..6de5a553fa 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss_impl.hpp
@@ -36,7 +36,7 @@ HingeLoss<InputDataType, OutputDataType>::Forward(
   TargetType temp = target - (target == 0);
   TargetType temp_zeros(size(target), arma::fill::zeros);
 
-  PredictionType loss = arma::max(1 - prediction % temp, temp_zeros);
+  PredictionType loss = arma::max(temp_zeros, 1 - prediction % temp);
 
   typename PredictionType::elem_type lossSum = arma::accu(loss);
 
diff --git a/src/mlpack/tests/loss_functions_test.cpp b/src/mlpack/tests/loss_functions_test.cpp
index 82e7c76db8..1fa4283c1a 100644
--- a/src/mlpack/tests/loss_functions_test.cpp
+++ b/src/mlpack/tests/loss_functions_test.cpp
@@ -984,21 +984,23 @@ TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
   REQUIRE(output.n_rows == input.n_rows);
   REQUIRE(output.n_cols == input.n_cols);
 
-  input = {{0.90599973, -0.33040298, 0.07123354},
-      {0.71988434, 0.49657596, 0.39873373},
-      {-0.57646927, 0.3951491 , -0.1003365},
-      {0.12528634, 0.68122971, 0.85448826}};
+  // Randomly generated input.
+  input = { { 0.90599973, -0.33040298, 0.07123354},
+            { 0.71988434, 0.49657596, 0.39873373},
+            { -0.57646927, 0.3951491 , -0.1003365},
+            { 0.12528634, 0.68122971, 0.85448826} };
 
-  target = {{-1, -1, 1},
-      {-1, 1, 1},
-      {1, -1, -1},
-      {1, -1, -1}};
+  // Randomly generated target.
+  target = { { -1, -1, 1},
+             { -1, 1, 1},
+             { 1, -1, -1},
+             { 1, -1, -1} };
 
-  // Binary labels for target.
-  target_b = {{0, 0, 1},
-      {0, 1, 1},
-      {1, 0, 0},
-      {1, 0, 0}};
+  // Binary target can be obtained by replacing -1 with 0 in target.
+  target_b = { { 0, 0, 1},
+               { 0, 1, 1},
+               { 1, 0, 0},
+               { 1, 0, 0} };
 
   // Test for binary labels as target.
   loss = module1.Forward(input, target);
@@ -1009,6 +1011,7 @@ TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
 
   // Test for sum reduction.
   // Test the Forward function.
+  // Loss calculated by referring to implementation of tf.keras.losses.hinge.
   loss = module1.Forward(input, target);
   REQUIRE(loss == Approx(14.61065).epsilon(1e-3));
 
@@ -1020,6 +1023,7 @@ TEST_CASE("HingeLossTest", "[LossFunctionsTest]")
 
   // Test for mean reduction.
   // Test for the Forward function.
+  // Loss calculated by referring to implementation of tf.keras.losses.hinge.
   loss = module2.Forward(input, target);
   REQUIRE(loss == Approx(1.21755).epsilon(1e-3));
 

From 422ce97209bb6939716de8266aa8fbc9fc21c4dd Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Tue, 2 Feb 2021 19:48:38 +0530
Subject: [PATCH 138/253] Adding Doxygen to y_true and y_pred

---
 src/mlpack/methods/ann/loss_functions/hinge_loss.hpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
index 37e6ed20f4..60a2002782 100644
--- a/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
+++ b/src/mlpack/methods/ann/loss_functions/hinge_loss.hpp
@@ -19,9 +19,9 @@ namespace mlpack {
 namespace ann /** Artificial Neural Network. */ {
 
 /**
- * Computes the hinge loss between y_true and y_pred. Expects y_true to be
- * either -1 or 1. If y_true is either 0 or 1, a temporary conversion is made to
- * calculate the loss.
+ * Computes the hinge loss between \f$y_true\f$ and \f$y_pred\f$. Expects
+ * \f$y_true\f$ to be either -1 or 1. If \f$y_true\f$ is either 0 or 1, a
+ * temporary conversion is made to calculate the loss.
  * The hinge loss \f$l(y_true, y_pred)\f$ is defined as
  * \f$l(y_true, y_pred) = max(0, 1 - y_true*y_pred)\f$.
  *

From 0c3ec81d4b024d214ef086e96768b3496fe62447 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Wed, 3 Feb 2021 00:14:26 +0530
Subject: [PATCH 139/253] Changed the restrictors from is_Row to is_arma_type

---
 src/mlpack/core/data/split_data.hpp | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 8a50ceeaf3..055045282f 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -170,7 +170,8 @@ void StratifiedSplit(const arma::Mat<T>& input,
  * @endcode
  *
  * @tparam T Type of the elements of the input matrix.
- * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
+ * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::row,
+ *       arma::Cube or arma::SpMat.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
  * @param trainData Matrix to store training data into.
@@ -182,7 +183,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  *       sample is visited in linear order. (Default true.)
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_Row<LabelsType>::value ||
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value ||
                           arma::is_Mat_only<LabelsType>::value> >
 void Split(const arma::Mat<T>& input,
            const LabelsType& inputLabel,
@@ -300,7 +301,8 @@ void Split(const arma::Mat<T>& input,
  * @endcode
  *
  * @tparam T Type of the elements of the input matrix.
- * @tparam LabelsType Type of input labels. It must be arma::Mat or arma::row.
+ * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::row,
+ *       arma::Cube or arma::SpMat.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
  * @param testRatio Percentage of dataset to use for test set (between 0 and 1).
@@ -313,7 +315,7 @@ void Split(const arma::Mat<T>& input,
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_Row<LabelsType>::value ||
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value ||
                           arma::is_Mat_only<LabelsType>::value> >
 std::tuple<arma::Mat<T>, arma::Mat<T>, LabelsType, LabelsType>
 Split(const arma::Mat<T>& input,

From 591ac9670571c5040aa32b2dcd69127fb93bd345 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Wed, 3 Feb 2021 00:21:49 +0530
Subject: [PATCH 140/253] Improved documentation of overload of split for field

---
 src/mlpack/core/data/split_data.hpp | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 055045282f..1225e6cd8d 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -382,6 +382,8 @@ Split(const arma::Mat<T>& input,
  * Given an input dataset and labels, split into a training set and test set.
  * Example usage below.  This overload places the split dataset into the four
  * output parameters given (trainData, testData, trainLabel, and testLabel).
+ *
+ * The input dataset must be of type arma::field and have a single row.
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -460,6 +462,8 @@ void Split(FieldType& input,
  * Given an input dataset, split into a training set and test set.
  * Example usage below. This overload places the split dataset into the two
  * output parameters given (trainData, testData).
+ *
+ * The input dataset must be of type arma::field and have a single row.
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -521,6 +525,8 @@ void Split(const FieldType& input,
  * with four elements: an FieldType containing the training data, an
  * FieldType containing the test data, an arma::field<arma::vec> containing the
  * training labels, and an arma::field<arma::vec> containing the test labels.
+ *
+ * The input dataset must be of type arma::field and have a single row.
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -568,6 +574,8 @@ Split(FieldType& input,
  * Example usage below.  This overload returns the split dataset as a std::tuple
  * with two elements: an FieldType containing the training data and an
  * FieldType containing the test data.
+ *
+ * The input dataset must be of type arma::field and have a single row.
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *

From 2d98d2ac9a1d95c89f76bd601c77c99135c2c46c Mon Sep 17 00:00:00 2001
From: Marcus Edel <marcus.edel@fu-berlin.de>
Date: Wed, 3 Feb 2021 01:03:11 +0100
Subject: [PATCH 141/253] Test file is no no longer used.

---
 src/mlpack/tests/function_test.cpp | 681 -----------------------------
 1 file changed, 681 deletions(-)
 delete mode 100644 src/mlpack/tests/function_test.cpp

diff --git a/src/mlpack/tests/function_test.cpp b/src/mlpack/tests/function_test.cpp
deleted file mode 100644
index 5486ac1e87..0000000000
--- a/src/mlpack/tests/function_test.cpp
+++ /dev/null
@@ -1,681 +0,0 @@
-/**
- * @file tests/function_test.cpp
- * @author Ryan Curtin
- * @author Shikhar Bhardwaj
- *
- * Test the Function<> class to see that it properly adds functionality.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-#include <mlpack/core.hpp>
-#include <mlpack/core/optimizers/function.hpp>
-#include <mlpack/methods/logistic_regression/logistic_regression_function.hpp>
-#include <mlpack/core/optimizers/sdp/sdp.hpp>
-#include <mlpack/core/optimizers/sdp/lrsdp.hpp>
-#include <mlpack/core/optimizers/aug_lagrangian/aug_lagrangian.hpp>
-
-#include <boost/test/unit_test.hpp>
-#include "test_tools.hpp"
-
-using namespace mlpack;
-using namespace mlpack::optimization;
-using namespace ens::traits; // For some SFINAE checks.
-using namespace mlpack::regression;
-
-/**
- * Utility class with no functions.
- */
-class EmptyTestFunction { };
-
-/**
- * Utility class with Evaluate() but no Evaluate().
- */
-class EvaluateTestFunction
-{
- public:
-  double Evaluate(const arma::mat& coordinates)
-  {
-    return arma::accu(coordinates);
-  }
-
-  double Evaluate(const arma::mat& coordinates,
-                  const size_t begin,
-                  const size_t batchSize)
-  {
-    return arma::accu(coordinates) + begin + batchSize;
-  }
-};
-
-/**
- * Utility class with Gradient() but no Evaluate().
- */
-class GradientTestFunction
-{
- public:
-  void Gradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-
-  void Gradient(const arma::mat& coordinates,
-                const size_t /* begin */,
-                arma::mat& gradient,
-                const size_t /* batchSize */)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-};
-
-/**
- * Utility class with Gradient() and Evaluate().
- */
-class EvaluateGradientTestFunction
-{
- public:
-  double Evaluate(const arma::mat& coordinates)
-  {
-    return arma::accu(coordinates);
-  }
-
-  double Evaluate(const arma::mat& coordinates,
-                  const size_t /* begin */,
-                  const size_t /* batchSize */)
-  {
-    return arma::accu(coordinates);
-  }
-
-  void Gradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-
-  void Gradient(const arma::mat& coordinates,
-                const size_t /* begin */,
-                arma::mat& gradient,
-                const size_t /* batchSize */)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-};
-
-/**
- * Utility class with EvaluateWithGradient().
- */
-class EvaluateWithGradientTestFunction
-{
- public:
-  double EvaluateWithGradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-    return arma::accu(coordinates);
-  }
-
-  double EvaluateWithGradient(const arma::mat& coordinates,
-                              const size_t /* begin */,
-                              arma::mat& gradient,
-                              const size_t /* batchSize */)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-    return arma::accu(coordinates);
-  }
-};
-
-/**
- * Utility class with all three functions.
- */
-class EvaluateAndWithGradientTestFunction
-{
- public:
-  double Evaluate(const arma::mat& coordinates)
-  {
-    return arma::accu(coordinates);
-  }
-
-  double Evaluate(const arma::mat& coordinates,
-                  const size_t begin,
-                  const size_t batchSize)
-  {
-    return arma::accu(coordinates) + batchSize + begin;
-  }
-
-  void Gradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-
-  void Gradient(const arma::mat& coordinates,
-                const size_t /* begin */,
-                arma::mat& gradient,
-                const size_t /* batchSize */)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-
-  double EvaluateWithGradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-    return arma::accu(coordinates);
-  }
-
-  double EvaluateWithGradient(const arma::mat& coordinates,
-                              const size_t /* begin */,
-                              arma::mat& gradient,
-                              const size_t /* batchSize */)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-    return arma::accu(coordinates);
-  }
-};
-
-/**
- * Utility class with const Evaluate() and non-const Gradient().
- */
-class EvaluateAndNonConstGradientTestFunction
-{
- public:
-  double Evaluate(const arma::mat& coordinates) const
-  {
-    return arma::accu(coordinates);
-  }
-
-  void Gradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-};
-
-/**
- * Utility class with const Evaluate() and non-const Gradient().
- */
-class EvaluateAndStaticGradientTestFunction
-{
- public:
-  double Evaluate(const arma::mat& coordinates) const
-  {
-    return arma::accu(coordinates);
-  }
-
-  static void Gradient(const arma::mat& coordinates, arma::mat& gradient)
-  {
-    gradient.ones(coordinates.n_rows, coordinates.n_cols);
-  }
-};
-
-BOOST_AUTO_TEST_SUITE(FunctionTest);
-
-/**
- * Make sure that an empty class doesn't have any methods added to it.
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientEmptyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<EmptyTestFunction>,
-                                       EvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<EmptyTestFunction>,
-                                       GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EmptyTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, false);
-  BOOST_REQUIRE_EQUAL(hasGradient, false);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we don't add any functions if we only have Evaluate().
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientEvaluateOnlyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<EvaluateTestFunction>,
-                                       EvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<EvaluateTestFunction>,
-                                       GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, false);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we don't add any functions if we only have Gradient().
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientGradientOnlyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<GradientTestFunction>,
-                                       EvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<GradientTestFunction>,
-                                       GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<GradientTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, false);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we add EvaluateWithGradient() when we have both Evaluate() and
- * Gradient().
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientBothTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateGradientTestFunction>,
-                           EvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateGradientTestFunction>,
-                           GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateGradientTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we add Evaluate() and Gradient() when we have only
- * EvaluateWithGradient().
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientEvaluateWithGradientTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateWithGradientTestFunction>,
-                           EvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateWithGradientTestFunction>,
-                           GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateWithGradientTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we add no methods when we already have all three.
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientAllThreeTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateAndWithGradientTestFunction>,
-                           EvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateAndWithGradientTestFunction>,
-                           GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateAndWithGradientTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-BOOST_AUTO_TEST_CASE(LogisticRegressionEvaluateWithGradientTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<LogisticRegressionFunction<>>,
-                           EvaluateConstForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<LogisticRegressionFunction<>>,
-                           GradientConstForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<LogisticRegressionFunction<>>,
-                              EvaluateWithGradientConstForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-BOOST_AUTO_TEST_CASE(SDPTest)
-{
-  typedef AugLagrangianFunction<LRSDPFunction<SDP<arma::mat>>> FunctionType;
-
-  const bool hasEvaluate =
-      HasEvaluate<Function<FunctionType>, EvaluateConstForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<FunctionType>, GradientConstForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<FunctionType>,
-                              EvaluateWithGradientConstForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure that an empty class doesn't have any methods added to it.
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWithGradientEmptyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<EmptyTestFunction>,
-                                       DecomposableEvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<EmptyTestFunction>,
-                                       DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EmptyTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, false);
-  BOOST_REQUIRE_EQUAL(hasGradient, false);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we don't add any functions if we only have Evaluate().
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWithGradientEvaluateOnlyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<EvaluateTestFunction>,
-                                       DecomposableEvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<EvaluateTestFunction>,
-                                       DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, false);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we don't add any functions if we only have Gradient().
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWithGradientGradientOnlyTest)
-{
-  const bool hasEvaluate = HasEvaluate<Function<GradientTestFunction>,
-                                       DecomposableEvaluateForm>::value;
-  const bool hasGradient = HasGradient<Function<GradientTestFunction>,
-                                       DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<GradientTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, false);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, false);
-}
-
-/**
- * Make sure we add EvaluateWithGradient() when we have both Evaluate() and
- * Gradient().
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWithGradientBothTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateGradientTestFunction>,
-                           DecomposableEvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateGradientTestFunction>,
-                           DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateGradientTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we add Evaluate() and Gradient() when we have only
- * EvaluateWithGradient().
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWGradientEvaluateWithGradientTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateWithGradientTestFunction>,
-                           DecomposableEvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateWithGradientTestFunction>,
-                           DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateWithGradientTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  Function<EvaluateWithGradientTestFunction> f;
-  arma::mat coordinates(10, 10, arma::fill::ones);
-  arma::mat gradient;
-  f.Gradient(coordinates, 0, gradient, 5);
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we add no methods when we already have all three.
- */
-BOOST_AUTO_TEST_CASE(AddDecomposableEvaluateWithGradientAllThreeTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateAndWithGradientTestFunction>,
-                  DecomposableEvaluateForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateAndWithGradientTestFunction>,
-                           DecomposableGradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateAndWithGradientTestFunction>,
-                              DecomposableEvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we can properly create EvaluateWithGradient() even when one of the
- * functions is non-const.
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientMixedTypesTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateAndNonConstGradientTestFunction>,
-                  EvaluateConstForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateAndNonConstGradientTestFunction>,
-                  GradientForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateAndNonConstGradientTestFunction>,
-                              EvaluateWithGradientForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-/**
- * Make sure we can properly create EvaluateWithGradient() even when one of the
- * functions is static.
- */
-BOOST_AUTO_TEST_CASE(AddEvaluateWithGradientMixedTypesStaticTest)
-{
-  const bool hasEvaluate =
-      HasEvaluate<Function<EvaluateAndStaticGradientTestFunction>,
-                  EvaluateConstForm>::value;
-  const bool hasGradient =
-      HasGradient<Function<EvaluateAndStaticGradientTestFunction>,
-                  GradientStaticForm>::value;
-  const bool hasEvaluateWithGradient =
-      HasEvaluateWithGradient<Function<EvaluateAndStaticGradientTestFunction>,
-                              EvaluateWithGradientConstForm>::value;
-
-  BOOST_REQUIRE_EQUAL(hasEvaluate, true);
-  BOOST_REQUIRE_EQUAL(hasGradient, true);
-  BOOST_REQUIRE_EQUAL(hasEvaluateWithGradient, true);
-}
-
-class A
-{
- public:
-  size_t NumFunctions() const;
-  size_t NumFeatures() const;
-  double Evaluate(const arma::mat&, const size_t, const size_t) const;
-  void Gradient(const arma::mat&, const size_t, arma::mat&, const size_t) const;
-  void Gradient(const arma::mat&, const size_t, arma::sp_mat&, const size_t)
-      const;
-  void PartialGradient(const arma::mat&, const size_t, arma::sp_mat&) const;
-};
-
-class B
-{
- public:
-  size_t NumFunctions();
-  size_t NumFeatures();
-  double Evaluate(const arma::mat&, const size_t, const size_t);
-  void Gradient(const arma::mat&, const size_t, arma::mat&, const size_t);
-  void Gradient(const arma::mat&, const size_t, arma::sp_mat&, const size_t);
-  void PartialGradient(const arma::mat&, const size_t, arma::sp_mat&);
-};
-
-class C
-{
- public:
-  size_t NumConstraints() const;
-  double Evaluate(const arma::mat&) const;
-  void Gradient(const arma::mat&, arma::mat&) const;
-  double EvaluateConstraint(const size_t, const arma::mat&) const;
-  void GradientConstraint(const size_t, const arma::mat&, arma::mat&) const;
-};
-
-class D
-{
- public:
-  size_t NumConstraints();
-  double Evaluate(const arma::mat&);
-  void Gradient(const arma::mat&, arma::mat&);
-  double EvaluateConstraint(const size_t, const arma::mat&);
-  void GradientConstraint(const size_t, const arma::mat&, arma::mat&);
-};
-
-
-/**
- * Test the correctness of the static check for DecomposableFunctionType API.
- */
-BOOST_AUTO_TEST_CASE(DecomposableFunctionTypeCheckTest)
-{
-  static_assert(CheckNumFunctions<A>::value,
-      "CheckNumFunctions static check failed.");
-  static_assert(CheckNumFunctions<B>::value,
-      "CheckNumFunctions static check failed.");
-  static_assert(!CheckNumFunctions<C>::value,
-      "CheckNumFunctions static check failed.");
-  static_assert(!CheckNumFunctions<D>::value,
-      "CheckNumFunctions static check failed.");
-
-  static_assert(CheckDecomposableEvaluate<A>::value,
-      "CheckDecomposableEvaluate static check failed.");
-  static_assert(CheckDecomposableEvaluate<B>::value,
-      "CheckDecomposableEvaluate static check failed.");
-  static_assert(!CheckDecomposableEvaluate<C>::value,
-      "CheckDecomposableEvaluate static check failed.");
-  static_assert(!CheckDecomposableEvaluate<D>::value,
-      "CheckDecomposableEvaluate static check failed.");
-
-  static_assert(CheckDecomposableGradient<A>::value,
-      "CheckDecomposableGradient static check failed.");
-  static_assert(CheckDecomposableGradient<B>::value,
-      "CheckDecomposableGradient static check failed.");
-  static_assert(!CheckDecomposableGradient<C>::value,
-      "CheckDecomposableGradient static check failed.");
-  static_assert(!CheckDecomposableGradient<D>::value,
-      "CheckDecomposableGradient static check failed.");
-}
-
-/**
- * Test the correctness of the static check for LagrangianFunctionType API.
- */
-BOOST_AUTO_TEST_CASE(LagrangianFunctionTypeCheckTest)
-{
-  static_assert(!CheckEvaluate<A>::value, "CheckEvaluate static check failed.");
-  static_assert(!CheckEvaluate<B>::value, "CheckEvaluate static check failed.");
-  static_assert(CheckEvaluate<C>::value, "CheckEvaluate static check failed.");
-  static_assert(CheckEvaluate<D>::value, "CheckEvaluate static check failed.");
-
-  static_assert(!CheckGradient<A>::value, "CheckGradient static check failed.");
-  static_assert(!CheckGradient<B>::value, "CheckGradient static check failed.");
-  static_assert(CheckGradient<C>::value, "CheckGradient static check failed.");
-  static_assert(CheckGradient<D>::value, "CheckGradient static check failed.");
-
-  static_assert(!CheckNumConstraints<A>::value,
-      "CheckNumConstraints static check failed.");
-  static_assert(!CheckNumConstraints<B>::value,
-      "CheckNumConstraints static check failed.");
-  static_assert(CheckNumConstraints<C>::value,
-      "CheckNumConstraints static check failed.");
-  static_assert(CheckNumConstraints<D>::value,
-      "CheckNumConstraints static check failed.");
-
-  static_assert(!CheckEvaluateConstraint<A>::value,
-      "CheckEvaluateConstraint static check failed.");
-  static_assert(!CheckEvaluateConstraint<B>::value,
-      "CheckEvaluateConstraint static check failed.");
-  static_assert(CheckEvaluateConstraint<C>::value,
-      "CheckEvaluateConstraint static check failed.");
-  static_assert(CheckEvaluateConstraint<D>::value,
-      "CheckEvaluateConstraint static check failed.");
-
-  static_assert(!CheckGradientConstraint<A>::value,
-      "CheckGradientConstraint static check failed.");
-  static_assert(!CheckGradientConstraint<B>::value,
-      "CheckGradientConstraint static check failed.");
-  static_assert(CheckGradientConstraint<C>::value,
-      "CheckGradientConstraint static check failed.");
-  static_assert(CheckGradientConstraint<D>::value,
-      "CheckGradientConstraint static check failed.");
-}
-
-/**
- * Test the correctness of the static check for SparseFunctionType API.
- */
-BOOST_AUTO_TEST_CASE(SparseFunctionTypeCheckTest)
-{
-  static_assert(CheckSparseGradient<A>::value,
-      "CheckSparseGradient static check failed.");
-  static_assert(CheckSparseGradient<B>::value,
-      "CheckSparseGradient static check failed.");
-  static_assert(!CheckSparseGradient<C>::value,
-      "CheckSparseGradient static check failed.");
-  static_assert(!CheckSparseGradient<D>::value,
-      "CheckSparseGradient static check failed.");
-}
-
-/**
- * Test the correctness of the static check for SparseFunctionType API.
- */
-BOOST_AUTO_TEST_CASE(ResolvableFunctionTypeCheckTest)
-{
-  static_assert(CheckNumFeatures<A>::value,
-      "CheckNumFeatures static check failed.");
-  static_assert(CheckNumFeatures<B>::value,
-      "CheckNumFeatures static check failed.");
-  static_assert(!CheckNumFeatures<C>::value,
-      "CheckNumFeatures static check failed.");
-  static_assert(!CheckNumFeatures<D>::value,
-      "CheckNumFeatures static check failed.");
-
-  static_assert(CheckPartialGradient<A>::value,
-      "CheckPartialGradient static check failed.");
-  static_assert(CheckPartialGradient<B>::value,
-      "CheckPartialGradient static check failed.");
-  static_assert(!CheckPartialGradient<C>::value,
-      "CheckPartialGradient static check failed.");
-  static_assert(!CheckPartialGradient<D>::value,
-      "CheckPartialGradient static check failed.");
-}
-
-BOOST_AUTO_TEST_SUITE_END();

From b2366ab1088cf08e6698309cb1ae3c7caae162d1 Mon Sep 17 00:00:00 2001
From: Marcus Edel <marcus.edel@fu-berlin.de>
Date: Wed, 3 Feb 2021 01:21:35 +0100
Subject: [PATCH 142/253] brew cask instal is no longer supported, use brew
 install --cask instead.

---
 .ci/macos-steps.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.ci/macos-steps.yaml b/.ci/macos-steps.yaml
index c437344050..85e92fe3b3 100644
--- a/.ci/macos-steps.yaml
+++ b/.ci/macos-steps.yaml
@@ -22,7 +22,7 @@ steps:
     fi
 
     if [ "a$(julia.version)" != "a" ]; then
-      brew cask install julia
+      brew install --cask julia
     fi
 
     git clone --depth 1 https://github.com/mlpack/jenkins-conf.git conf

From 66fcef9e0ccf7e622cdfc1da8db15f0191e5b073 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Thu, 4 Feb 2021 09:15:25 +0530
Subject: [PATCH 143/253] Removed redundant is_Mat_type restrictor

---
 src/mlpack/core/data/split_data.hpp | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 1225e6cd8d..4067e8af09 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -183,8 +183,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  *       sample is visited in linear order. (Default true.)
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value ||
-                          arma::is_Mat_only<LabelsType>::value> >
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value>
 void Split(const arma::Mat<T>& input,
            const LabelsType& inputLabel,
            arma::Mat<T>& trainData,
@@ -315,8 +314,7 @@ void Split(const arma::Mat<T>& input,
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value ||
-                          arma::is_Mat_only<LabelsType>::value> >
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value>
 std::tuple<arma::Mat<T>, arma::Mat<T>, LabelsType, LabelsType>
 Split(const arma::Mat<T>& input,
       const LabelsType& inputLabel,

From 0b06b2bfde43ce468a2207b120e48d85d6b39482 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Thu, 4 Feb 2021 09:35:46 +0530
Subject: [PATCH 144/253] Improved documentation

---
 src/mlpack/core/data/split_data.hpp | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 4067e8af09..561366de2b 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -381,7 +381,8 @@ Split(const arma::Mat<T>& input,
  * Example usage below.  This overload places the split dataset into the four
  * output parameters given (trainData, testData, trainLabel, and testLabel).
  *
- * The input dataset must be of type arma::field and have a single row.
+ * The input dataset must be of type arma::field. It should have the shape -
+ * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -461,7 +462,8 @@ void Split(FieldType& input,
  * Example usage below. This overload places the split dataset into the two
  * output parameters given (trainData, testData).
  *
- * The input dataset must be of type arma::field and have a single row.
+ * The input dataset must be of type arma::field. It should have the shape -
+ * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -524,7 +526,8 @@ void Split(const FieldType& input,
  * FieldType containing the test data, an arma::field<arma::vec> containing the
  * training labels, and an arma::field<arma::vec> containing the test labels.
  *
- * The input dataset must be of type arma::field and have a single row.
+ * The input dataset must be of type arma::field. It should have the shape -
+ * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
@@ -573,7 +576,8 @@ Split(FieldType& input,
  * with two elements: an FieldType containing the training data and an
  * FieldType containing the test data.
  *
- * The input dataset must be of type arma::field and have a single row.
+ * The input dataset must be of type arma::field. It should have the shape -
+ * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
  * 
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *

From 7da50e3ba577906beb005808fc5efad71d7fe178 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Thu, 4 Feb 2021 12:25:24 +0530
Subject: [PATCH 145/253] Fixed brackets

---
 src/mlpack/core/data/split_data.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 561366de2b..e9358d23c9 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -183,7 +183,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  *       sample is visited in linear order. (Default true.)
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value>
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value> >
 void Split(const arma::Mat<T>& input,
            const LabelsType& inputLabel,
            arma::Mat<T>& trainData,
@@ -314,7 +314,7 @@ void Split(const arma::Mat<T>& input,
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */
 template<typename T, typename LabelsType,
-         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value>
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value> >
 std::tuple<arma::Mat<T>, arma::Mat<T>, LabelsType, LabelsType>
 Split(const arma::Mat<T>& input,
       const LabelsType& inputLabel,

From cbb534daa150606b5b280902d4829741e14d39bb Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Thu, 4 Feb 2021 16:38:12 +0530
Subject: [PATCH 146/253] Added test case for matrix labels

---
 src/mlpack/tests/split_data_test.cpp | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 996c6ccfa4..d3d445796e 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -199,6 +199,26 @@ TEST_CASE("SplitLabeledDataResultMat", "[SplitDataTest]")
   CheckDuplication(std::get<2>(value), std::get<3>(value));
 }
 
+TEST_CASE("SplitMatrixLabeledDataResultMat", "[SplitDataTest]")
+{
+  mat input(2, 10);
+  input.randu();
+
+  const mat labels(2, 10, fill::randu);
+
+  const auto value = Split(input, labels, 0.2);
+  REQUIRE(std::get<0>(value).n_cols == 8);
+  REQUIRE(std::get<1>(value).n_cols == 2);
+  REQUIRE(std::get<2>(value).n_cols == 8);
+  REQUIRE(std::get<3>(value).n_cols == 2);
+
+  mat input_concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
+  mat labels_concat = arma::join_rows(std::get<2>(value), std::get<3>(value));
+  // Order matters here.
+  CheckMatrices(input, input_concat);
+  CheckMatrices(labels, labels_concat);
+}
+
 /**
  * The same test as above, but on a larger dataset.
  */

From 0ed4da96cdb8e6ebdecf2c6f09b85f4b49c9a51f Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 01:32:55 +0530
Subject: [PATCH 147/253] Added LP lookup layer

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp   | 289 ++++++++++++++++++
 .../methods/ann/layer/lp_pooling_impl.hpp     | 141 +++++++++
 src/mlpack/tests/ann_layer_test.cpp           |  48 +++
 3 files changed, 478 insertions(+)
 create mode 100644 src/mlpack/methods/ann/layer/lp_pooling.hpp
 create mode 100644 src/mlpack/methods/ann/layer/lp_pooling_impl.hpp

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
new file mode 100644
index 0000000000..e698f89e93
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -0,0 +1,289 @@
+/**
+ * @file methods/ann/layer/lp_pooling.hpp
+ * @author Abhinav Anan
+ *
+ * Definition of the LpPooling layer class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_LP_POOLING_HPP
+#define MLPACK_METHODS_ANN_LAYER_LP_POOLING_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+/**
+ * Implementation of the LPPooling.
+ *
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ */
+template <
+    typename InputDataType = arma::mat,
+    typename OutputDataType = arma::mat
+>
+class LpPooling
+{
+ public:
+  //! Create the LpPooling object.
+  LpPooling();
+
+  /**
+   * Create the LpPooling object using the specified number of units.
+   *
+   * @param kernelWidth Width of the pooling window.
+   * @param kernelHeight Height of the pooling window.
+   * @param strideWidth Width of the stride operation.
+   * @param strideHeight Width of the stride operation.
+   * @param floor Set to true to use floor method.
+   */
+  LpPooling(const size_t norm_type,
+              const size_t kernelWidth,
+              const size_t kernelHeight,
+              const size_t strideWidth = 1,
+              const size_t strideHeight = 1,
+              const bool floor = true);
+
+  /**
+   * Ordinary feed forward pass of a neural network, evaluating the function
+   * f(x) by propagating the activity forward through f.
+   *
+   * @param input Input data used for evaluating the specified function.
+   * @param output Resulting output activation.
+   */
+  template<typename eT>
+  void Forward(const arma::Mat<eT>& input, arma::Mat<eT>& output);
+
+  /**
+   * Ordinary feed backward pass of a neural network, using 3rd-order tensors as
+   * input, calculating the function f(x) by propagating x backwards through f.
+   * Using the results from the feed forward pass.
+   *
+   * @param * (input) The propagated input activation.
+   * @param gy The backpropagated error.
+   * @param g The calculated gradient.
+   */
+  template<typename eT>
+  void Backward(const arma::Mat<eT>& /* input */,
+                const arma::Mat<eT>& gy,
+                arma::Mat<eT>& g);
+
+  //! Get the output parameter.
+  OutputDataType const& OutputParameter() const { return outputParameter; }
+  //! Modify the output parameter.
+  OutputDataType& OutputParameter() { return outputParameter; }
+
+  //! Get the delta.
+  OutputDataType const& Delta() const { return delta; }
+  //! Modify the delta.
+  OutputDataType& Delta() { return delta; }
+
+  //! Get the intput width.
+  size_t const& InputWidth() const { return inputWidth; }
+  //! Modify the input width.
+  size_t& InputWidth() { return inputWidth; }
+
+  //! Get the input height.
+  size_t const& InputHeight() const { return inputHeight; }
+  //! Modify the input height.
+  size_t& InputHeight() { return inputHeight; }
+
+  //! Get the output width.
+  size_t const& OutputWidth() const { return outputWidth; }
+  //! Modify the output width.
+  size_t& OutputWidth() { return outputWidth; }
+
+  //! Get the output height.
+  size_t const& OutputHeight() const { return outputHeight; }
+  //! Modify the output height.
+  size_t& OutputHeight() { return outputHeight; }
+
+  //! Get the input size.
+  size_t InputSize() const { return inSize; }
+
+  //! Get the output size.
+  size_t OutputSize() const { return outSize; }
+
+  //! Get the norm_type.
+  size_t NormType() const { return norm_type; }
+  //! Modify the norm_type.
+  size_t& NormType() const { return norm_type; }
+
+  //! Get the kernel width.
+  size_t KernelWidth() const { return kernelWidth; }
+  //! Modify the kernel width.
+  size_t& KernelWidth() { return kernelWidth; }
+
+  //! Get the kernel height.
+  size_t KernelHeight() const { return kernelHeight; }
+  //! Modify the kernel height.
+  size_t& KernelHeight() { return kernelHeight; }
+
+  //! Get the stride width.
+  size_t StrideWidth() const { return strideWidth; }
+  //! Modify the stride width.
+  size_t& StrideWidth() { return strideWidth; }
+
+  //! Get the stride height.
+  size_t StrideHeight() const { return strideHeight; }
+  //! Modify the stride height.
+  size_t& StrideHeight() { return strideHeight; }
+
+  //! Get the value of the rounding operation
+  bool const& Floor() const { return floor; }
+  //! Modify the value of the rounding operation
+  bool& Floor() { return floor; }
+
+  //! Get the value of the deterministic parameter.
+  bool Deterministic() const { return deterministic; }
+  //! Modify the value of the deterministic parameter.
+  bool& Deterministic() { return deterministic; }
+
+  //! Get the size of the weights.
+  size_t WeightSize() const { return 0; }
+
+  /**
+   * Serialize the layer.
+   */
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */);
+
+ private:
+  /**
+   * Apply pooling to the input and store the results.
+   *
+   * @param input The input to be apply the pooling rule.
+   * @param output The pooled result.
+   */
+  template<typename eT>
+  void Pooling(const arma::Mat<eT>& input, arma::Mat<eT>& output)
+  {
+    for (size_t j = 0, colidx = 0; j < output.n_cols;
+         ++j, colidx += strideHeight)
+    {
+      for (size_t i = 0, rowidx = 0; i < output.n_rows;
+           ++i, rowidx += strideWidth)
+      {
+        arma::mat subInput = input(
+            arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
+            arma::span(colidx, colidx + kernelHeight - 1 - offset));
+
+        output(i, j) = arma::pow(arma::accu(arma::pow(subInput, norm_type)), 1.0/norm_type);
+      }
+    }
+  }
+
+  /**
+   * Apply unpooling to the input and store the results.
+   *
+   * @param input The input to be apply the unpooling rule.
+   * @param output The pooled result.
+   */
+  template<typename eT>
+  void Unpooling(const arma::Mat<eT>& input,
+                 const arma::Mat<eT>& error,
+                 arma::Mat<eT>& output)
+  {
+    const size_t rStep = input.n_rows / error.n_rows - offset;
+    const size_t cStep = input.n_cols / error.n_cols - offset;
+
+    arma::Mat<eT> unpooledError;
+    for (size_t j = 0; j < input.n_cols - cStep; j += cStep)
+    {
+      for (size_t i = 0; i < input.n_rows - rStep; i += rStep)
+      {
+        const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
+            arma::span(j, j + cStep - 1));
+        size_t sum = arma::pow(arma::accu(arma::pow(inputArea, norm_type)), (norm_type-1) / norm_type);
+        unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
+        unpooledError.fill(error(i / rStep, j / cStep));
+        unpooledError %= arma::pow(inputArea, norm_type - 1);
+        unpooledError /= sum;
+        output(arma::span(i, i + rStep - 1 - offset),
+            arma::span(j, j + cStep - 1 - offset)) += unpooledError;
+      }
+    }
+  }
+
+  //! Locally-stored norm_type.
+  size_t norm_type;
+
+  //! Locally-stored width of the pooling window.
+  size_t kernelWidth;
+
+  //! Locally-stored height of the pooling window.
+  size_t kernelHeight;
+
+  //! Locally-stored width of the stride operation.
+  size_t strideWidth;
+
+  //! Locally-stored height of the stride operation.
+  size_t strideHeight;
+
+  //! Rounding operation used.
+  bool floor;
+
+  //! Locally-stored number of input channels.
+  size_t inSize;
+
+  //! Locally-stored number of output channels.
+  size_t outSize;
+
+  //! Locally-stored input width.
+  size_t inputWidth;
+
+  //! Locally-stored input height.
+  size_t inputHeight;
+
+  //! Locally-stored output width.
+  size_t outputWidth;
+
+  //! Locally-stored output height.
+  size_t outputHeight;
+
+  //! Locally-stored reset parameter used to initialize the module once.
+  bool reset;
+
+  //! If true use maximum a posteriori during the forward pass.
+  bool deterministic;
+
+  //! Locally-stored stored rounding offset.
+  size_t offset;
+
+  //! Locally-stored number of input units.
+  size_t batchSize;
+
+  //! Locally-stored output parameter.
+  arma::cube outputTemp;
+
+  //! Locally-stored transformed input parameter.
+  arma::cube inputTemp;
+
+  //! Locally-stored transformed output parameter.
+  arma::cube gTemp;
+
+  //! Locally-stored delta object.
+  OutputDataType delta;
+
+  //! Locally-stored gradient object.
+  OutputDataType gradient;
+
+  //! Locally-stored output parameter object.
+  OutputDataType outputParameter;
+}; // class LpPooling
+
+
+} // namespace ann
+} // namespace mlpack
+
+// Include implementation.
+#include "lp_pooling_impl.hpp"
+
+#endif
diff --git a/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
new file mode 100644
index 0000000000..9f1133aee8
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
@@ -0,0 +1,141 @@
+/**
+ * @file methods/ann/layer/lp_pooling_impl.hpp
+ * @author Marcus Edel
+ * @author Nilay Jain
+ *
+ * Implementation of the lpPooling layer class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_LP_POOLING_IMPL_HPP
+#define MLPACK_METHODS_ANN_LAYER_LP_POOLING_IMPL_HPP
+
+// In case it hasn't yet been included.
+#include "lp_pooling.hpp"
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+template<typename InputDataType, typename OutputDataType>
+LpPooling<InputDataType, OutputDataType>::LpPooling()
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+LpPooling<InputDataType, OutputDataType>::LpPooling(
+    const size_t norm_type,
+    const size_t kernelWidth,
+    const size_t kernelHeight,
+    const size_t strideWidth,
+    const size_t strideHeight,
+    const bool floor) :
+    kernelWidth(kernelWidth),
+    kernelHeight(kernelHeight),
+    strideWidth(strideWidth),
+    strideHeight(strideHeight),
+    floor(floor),
+    inSize(0),
+    outSize(0),
+    inputWidth(0),
+    inputHeight(0),
+    outputWidth(0),
+    outputHeight(0),
+    reset(false),
+    deterministic(false),
+    offset(0),
+    batchSize(0)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void LpPooling<InputDataType, OutputDataType>::Forward(
+    const arma::Mat<eT>& input, arma::Mat<eT>& output)
+{
+  batchSize = input.n_cols;
+  inSize = input.n_elem / (inputWidth * inputHeight * batchSize);
+  inputTemp = arma::cube(const_cast<arma::Mat<eT>&>(input).memptr(),
+      inputWidth, inputHeight, batchSize * inSize, false, false);
+
+  if (floor)
+  {
+    outputWidth = std::floor((inputWidth -
+        (double) kernelWidth) / (double) strideWidth + 1);
+    outputHeight = std::floor((inputHeight -
+        (double) kernelHeight) / (double) strideHeight + 1);
+
+    offset = 0;
+  }
+  else
+  {
+    outputWidth = std::ceil((inputWidth -
+        (double) kernelWidth) / (double) strideWidth + 1);
+    outputHeight = std::ceil((inputHeight -
+        (double) kernelHeight) / (double) strideHeight + 1);
+
+    offset = 1;
+  }
+
+  outputTemp = arma::zeros<arma::Cube<eT> >(outputWidth, outputHeight,
+      batchSize * inSize);
+
+  for (size_t s = 0; s < inputTemp.n_slices; s++)
+    Pooling(inputTemp.slice(s), outputTemp.slice(s));
+
+  output = arma::Mat<eT>(outputTemp.memptr(), outputTemp.n_elem / batchSize,
+      batchSize);
+
+  outputWidth = outputTemp.n_rows;
+  outputHeight = outputTemp.n_cols;
+  outSize = batchSize * inSize;
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void LpPooling<InputDataType, OutputDataType>::Backward(
+  const arma::Mat<eT>& /* input */,
+  const arma::Mat<eT>& gy,
+  arma::Mat<eT>& g)
+{
+  arma::cube mappedError = arma::cube(((arma::Mat<eT>&) gy).memptr(),
+      outputWidth, outputHeight, outSize, false, false);
+
+  gTemp = arma::zeros<arma::cube>(inputTemp.n_rows,
+      inputTemp.n_cols, inputTemp.n_slices);
+
+  for (size_t s = 0; s < mappedError.n_slices; s++)
+  {
+    Unpooling(inputTemp.slice(s), mappedError.slice(s), gTemp.slice(s));
+  }
+
+  g = arma::mat(gTemp.memptr(), gTemp.n_elem / batchSize, batchSize);
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename Archive>
+void LpPooling<InputDataType, OutputDataType>::serialize(
+    Archive& ar,
+    const uint32_t /* version */)
+{
+  ar(CEREAL_NVP(norm_type));
+  ar(CEREAL_NVP(kernelWidth));
+  ar(CEREAL_NVP(kernelHeight));
+  ar(CEREAL_NVP(strideWidth));
+  ar(CEREAL_NVP(strideHeight));
+  ar(CEREAL_NVP(batchSize));
+  ar(CEREAL_NVP(floor));
+  ar(CEREAL_NVP(inputWidth));
+  ar(CEREAL_NVP(inputHeight));
+  ar(CEREAL_NVP(outputWidth));
+  ar(CEREAL_NVP(outputHeight));
+}
+
+} // namespace ann
+} // namespace mlpack
+
+#endif
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 5e24a995e7..012269e479 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -3838,6 +3838,54 @@ TEST_CASE("TransposedConvolutionLayerPaddingTest", "[ANNLayerTest]")
   REQUIRE(arma::accu(delta) == 0.0);
 }
 
+/**
+ * Simple test for Lp Pooling layer.
+ */
+TEST_CASE("LpPoolingTestCase", "[ANNLayerTest]")
+{
+  // For rectangular input to pooling layers.
+  arma::mat input = arma::mat(8, 1);
+  arma::mat output;
+  input.zeros();
+  input(0) = input(6) = 30;
+  input(1) = input(7) = 120;
+  input(2) = input(4) = 272;
+  input(3) = input(5) = 315;
+  // Output-Size should be 1 x 2.
+  // Square output.
+  Lp<> module1(4, 2, 2, 2, 2);
+  module1.InputHeight() = 2;
+  module1.InputWidth() = 4;
+  module1.Forward(input, output);
+  // Calculated using torch.nn.LPPool2d().
+  REQUIRE(arma::accu(output) - 706.0 == Approx(0.0).margin(2e-5));
+  REQUIRE(output.n_elem == 2);
+
+  // For Square input.
+  input = arma::mat(16, 1);
+  input.zeros();
+  input(0) = 4;
+  input(1) = 3;
+  input(3) = 12;
+  input(7) = 35;
+  input(8) = 6;
+  input(11) = 7;
+  input(12) = 8;
+  input(15) = 24;
+  // Output-Size should be 2 x 2.
+  // Square output.
+  Lp<> module3(2, 2, 2, 2, 2);
+  module3.InputHeight() = 4;
+  module3.InputWidth() = 4;
+  module3.Forward(input, output);
+  // Calculated using torch.nn.LPPool2d().
+  REQUIRE(arma::accu(output) - 77.0 == Approx(0.0).margin(2e-5));
+  REQUIRE(output.n_elem == 4);
+
+}
+
+
+
 /**
  * Simple test for Max Pooling layer.
  */

From 89a56d7e878c0da22bd21f77cc8800cdf95c5d59 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 01:46:03 +0530
Subject: [PATCH 148/253] Added LP lookup layer

---
 src/mlpack/tests/ann_layer_test.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 012269e479..6608304f3d 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -3853,7 +3853,7 @@ TEST_CASE("LpPoolingTestCase", "[ANNLayerTest]")
   input(3) = input(5) = 315;
   // Output-Size should be 1 x 2.
   // Square output.
-  Lp<> module1(4, 2, 2, 2, 2);
+  LpPooling<> module1(4, 2, 2, 2, 2);
   module1.InputHeight() = 2;
   module1.InputWidth() = 4;
   module1.Forward(input, output);
@@ -3874,7 +3874,7 @@ TEST_CASE("LpPoolingTestCase", "[ANNLayerTest]")
   input(15) = 24;
   // Output-Size should be 2 x 2.
   // Square output.
-  Lp<> module3(2, 2, 2, 2, 2);
+  LpPooling<> module3(2, 2, 2, 2, 2);
   module3.InputHeight() = 4;
   module3.InputWidth() = 4;
   module3.Forward(input, output);

From 7772c73332bed0816ca10a33eb90bfa37b88879f Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 02:20:20 +0530
Subject: [PATCH 149/253] minor changes

---
 src/mlpack/methods/ann/layer/CMakeLists.txt  |  2 ++
 src/mlpack/methods/ann/layer/layer_types.hpp |  2 ++
 src/mlpack/methods/ann/layer_names.hpp       | 11 +++++++++++
 3 files changed, 15 insertions(+)

diff --git a/src/mlpack/methods/ann/layer/CMakeLists.txt b/src/mlpack/methods/ann/layer/CMakeLists.txt
index b4726b0c6f..5fe560edd4 100644
--- a/src/mlpack/methods/ann/layer/CMakeLists.txt
+++ b/src/mlpack/methods/ann/layer/CMakeLists.txt
@@ -63,6 +63,8 @@ set(SOURCES
   log_softmax_impl.hpp
   lookup.hpp
   lookup_impl.hpp
+  lp_pooling.hpp
+  lp_pooling_impl.hpp
   lstm.hpp
   lstm_impl.hpp
   max_pooling.hpp
diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index 1d7fd0ccba..d27a5a6d25 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -38,6 +38,7 @@
 #include <mlpack/methods/ann/layer/multiply_constant.hpp>
 #include <mlpack/methods/ann/layer/max_pooling.hpp>
 #include <mlpack/methods/ann/layer/mean_pooling.hpp>
+#include <mlpack/methods/ann/layer/lp_pooling.hpp>
 #include <mlpack/methods/ann/layer/noisylinear.hpp>
 #include <mlpack/methods/ann/layer/adaptive_max_pooling.hpp>
 #include <mlpack/methods/ann/layer/adaptive_mean_pooling.hpp>
@@ -282,6 +283,7 @@ using LayerTypes = boost::variant<
     LSTM<arma::mat, arma::mat>*,
     MaxPooling<arma::mat, arma::mat>*,
     MeanPooling<arma::mat, arma::mat>*,
+    LpPooling<arma::mat, arma::mat>*,
     MiniBatchDiscrimination<arma::mat, arma::mat>*,
     MultiplyConstant<arma::mat, arma::mat>*,
     MultiplyMerge<arma::mat, arma::mat>*,
diff --git a/src/mlpack/methods/ann/layer_names.hpp b/src/mlpack/methods/ann/layer_names.hpp
index be1b1f7fcb..15596efea3 100644
--- a/src/mlpack/methods/ann/layer_names.hpp
+++ b/src/mlpack/methods/ann/layer_names.hpp
@@ -206,6 +206,17 @@ class LayerNameVisitor : public boost::static_visitor<std::string>
     return "meanpooling";
   }
 
+  /**
+   * Return the name of the given layer of type LpPooling as a string.
+   *
+   * @param * Given layer of type LpPooling.
+   * @return The string representation of the layer.
+   */
+  std::string LayerString(LpPooling<>* /*layer*/) const
+  {
+    return "lppooling";
+  }
+
   /**
    * Return the name of the given layer of type MultiplyConstant as a string.
    *

From 826b1713918a8481386055c45e3160a9321e024c Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 02:28:02 +0530
Subject: [PATCH 150/253] minor

---
 src/mlpack/tests/ann_layer_test.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index 6608304f3d..cbd66116bf 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -3841,7 +3841,7 @@ TEST_CASE("TransposedConvolutionLayerPaddingTest", "[ANNLayerTest]")
 /**
  * Simple test for Lp Pooling layer.
  */
-TEST_CASE("LpPoolingTestCase", "[ANNLayerTest]")
+BOOST_AUTO_TEST_CASE(LpMaxPoolingTestCase)
 {
   // For rectangular input to pooling layers.
   arma::mat input = arma::mat(8, 1);

From a88994e48bb72057204b0fbf8c75b10838096127 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 02:43:09 +0530
Subject: [PATCH 151/253] minor

---
 src/mlpack/methods/ann/layer/layer.hpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/mlpack/methods/ann/layer/layer.hpp b/src/mlpack/methods/ann/layer/layer.hpp
index 947395fd6b..9cf806b7e4 100644
--- a/src/mlpack/methods/ann/layer/layer.hpp
+++ b/src/mlpack/methods/ann/layer/layer.hpp
@@ -47,6 +47,7 @@
 #include "linear3d.hpp"
 #include "log_softmax.hpp"
 #include "lookup.hpp"
+#include "lp_pooling.hpp"
 #include "lstm.hpp"
 #include "max_pooling.hpp"
 #include "mean_pooling.hpp"

From c1c0cfbc18c8a4492cf2f0bcab744a01b057b3e7 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 02:49:15 +0530
Subject: [PATCH 152/253] minor change

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index e698f89e93..ff360f41e7 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -175,7 +175,7 @@ class LpPooling
             arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
             arma::span(colidx, colidx + kernelHeight - 1 - offset));
 
-        output(i, j) = arma::pow(arma::accu(arma::pow(subInput, norm_type)), 1.0/norm_type);
+        output(i, j) = cmath::pow(arma::accu(arma::pow(subInput, norm_type)), 1.0/norm_type);
       }
     }
   }
@@ -201,7 +201,7 @@ class LpPooling
       {
         const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
             arma::span(j, j + cStep - 1));
-        size_t sum = arma::pow(arma::accu(arma::pow(inputArea, norm_type)), (norm_type-1) / norm_type);
+        size_t sum = cmath::pow(arma::accu(arma::pow(inputArea, norm_type)), (norm_type-1) / norm_type);
         unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
         unpooledError.fill(error(i / rStep, j / cStep));
         unpooledError %= arma::pow(inputArea, norm_type - 1);

From 66dc153ab2504adee07d41015b6288efc37db178 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 02:58:44 +0530
Subject: [PATCH 153/253] minor fix

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp   | 25 ++++++++-----------
 .../methods/ann/layer/lp_pooling_impl.hpp     |  1 -
 src/mlpack/tests/ann_layer_test.cpp           |  3 ---
 3 files changed, 10 insertions(+), 19 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index ff360f41e7..6205a0fba1 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -38,6 +38,7 @@ class LpPooling
   /**
    * Create the LpPooling object using the specified number of units.
    *
+   * @param norm_type Parameter for type of norm.
    * @param kernelWidth Width of the pooling window.
    * @param kernelHeight Height of the pooling window.
    * @param strideWidth Width of the stride operation.
@@ -45,11 +46,11 @@ class LpPooling
    * @param floor Set to true to use floor method.
    */
   LpPooling(const size_t norm_type,
-              const size_t kernelWidth,
-              const size_t kernelHeight,
-              const size_t strideWidth = 1,
-              const size_t strideHeight = 1,
-              const bool floor = true);
+            const size_t kernelWidth,
+            const size_t kernelHeight,
+            const size_t strideWidth = 1,
+            const size_t strideHeight = 1,
+            const bool floor = true);
 
   /**
    * Ordinary feed forward pass of a neural network, evaluating the function
@@ -141,11 +142,6 @@ class LpPooling
   //! Modify the value of the rounding operation
   bool& Floor() { return floor; }
 
-  //! Get the value of the deterministic parameter.
-  bool Deterministic() const { return deterministic; }
-  //! Modify the value of the deterministic parameter.
-  bool& Deterministic() { return deterministic; }
-
   //! Get the size of the weights.
   size_t WeightSize() const { return 0; }
 
@@ -175,7 +171,8 @@ class LpPooling
             arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
             arma::span(colidx, colidx + kernelHeight - 1 - offset));
 
-        output(i, j) = cmath::pow(arma::accu(arma::pow(subInput, norm_type)), 1.0/norm_type);
+        output(i, j) = cmath::pow(arma::accu(arma::pow(subInput,
+            norm_type)), 1.0/norm_type);
       }
     }
   }
@@ -201,7 +198,8 @@ class LpPooling
       {
         const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
             arma::span(j, j + cStep - 1));
-        size_t sum = cmath::pow(arma::accu(arma::pow(inputArea, norm_type)), (norm_type-1) / norm_type);
+        size_t sum = cmath::pow(arma::accu(arma::pow(inputArea, norm_type)),
+            (norm_type-1) / norm_type);
         unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
         unpooledError.fill(error(i / rStep, j / cStep));
         unpooledError %= arma::pow(inputArea, norm_type - 1);
@@ -251,9 +249,6 @@ class LpPooling
   //! Locally-stored reset parameter used to initialize the module once.
   bool reset;
 
-  //! If true use maximum a posteriori during the forward pass.
-  bool deterministic;
-
   //! Locally-stored stored rounding offset.
   size_t offset;
 
diff --git a/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
index 9f1133aee8..e646796360 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
@@ -45,7 +45,6 @@ LpPooling<InputDataType, OutputDataType>::LpPooling(
     outputWidth(0),
     outputHeight(0),
     reset(false),
-    deterministic(false),
     offset(0),
     batchSize(0)
 {
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index cbd66116bf..feead2800a 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -3881,11 +3881,8 @@ BOOST_AUTO_TEST_CASE(LpMaxPoolingTestCase)
   // Calculated using torch.nn.LPPool2d().
   REQUIRE(arma::accu(output) - 77.0 == Approx(0.0).margin(2e-5));
   REQUIRE(output.n_elem == 4);
-
 }
 
-
-
 /**
  * Simple test for Max Pooling layer.
  */

From c9934c3975d03f9b441cafe59847b4481d40b0c8 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 21:18:52 +0530
Subject: [PATCH 154/253] minor fix

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index 6205a0fba1..aa413c02dc 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -115,7 +115,7 @@ class LpPooling
   //! Get the norm_type.
   size_t NormType() const { return norm_type; }
   //! Modify the norm_type.
-  size_t& NormType() const { return norm_type; }
+  size_t& NormType() { return norm_type; }
 
   //! Get the kernel width.
   size_t KernelWidth() const { return kernelWidth; }

From 92a8bd69f9c4c79efe83695e29cb5f312489d755 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 21:30:09 +0530
Subject: [PATCH 155/253] minor change

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp | 4 ++--
 src/mlpack/tests/ann_layer_test.cpp         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index aa413c02dc..0f6a2bdb83 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -171,7 +171,7 @@ class LpPooling
             arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
             arma::span(colidx, colidx + kernelHeight - 1 - offset));
 
-        output(i, j) = cmath::pow(arma::accu(arma::pow(subInput,
+        output(i, j) = pow(arma::accu(arma::pow(subInput,
             norm_type)), 1.0/norm_type);
       }
     }
@@ -198,7 +198,7 @@ class LpPooling
       {
         const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
             arma::span(j, j + cStep - 1));
-        size_t sum = cmath::pow(arma::accu(arma::pow(inputArea, norm_type)),
+        size_t sum = pow(arma::accu(arma::pow(inputArea, norm_type)),
             (norm_type-1) / norm_type);
         unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
         unpooledError.fill(error(i / rStep, j / cStep));
diff --git a/src/mlpack/tests/ann_layer_test.cpp b/src/mlpack/tests/ann_layer_test.cpp
index feead2800a..dbb5266798 100644
--- a/src/mlpack/tests/ann_layer_test.cpp
+++ b/src/mlpack/tests/ann_layer_test.cpp
@@ -3841,7 +3841,7 @@ TEST_CASE("TransposedConvolutionLayerPaddingTest", "[ANNLayerTest]")
 /**
  * Simple test for Lp Pooling layer.
  */
-BOOST_AUTO_TEST_CASE(LpMaxPoolingTestCase)
+TEST_CASE("LpMaxPoolingTestCase", "[ANNLayerTest]")
 {
   // For rectangular input to pooling layers.
   arma::mat input = arma::mat(8, 1);

From ada4e570e8d7d43bfeadc7e94dd274e533cc2e09 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Sat, 6 Feb 2021 22:35:12 +0530
Subject: [PATCH 156/253] minor fix

---
 src/mlpack/methods/ann/layer/lp_pooling.hpp   | 24 +++++++++----------
 .../methods/ann/layer/lp_pooling_impl.hpp     |  5 ++--
 2 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index 0f6a2bdb83..aa0f043c33 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -38,14 +38,14 @@ class LpPooling
   /**
    * Create the LpPooling object using the specified number of units.
    *
-   * @param norm_type Parameter for type of norm.
+   * @param normType Parameter for type of norm.
    * @param kernelWidth Width of the pooling window.
    * @param kernelHeight Height of the pooling window.
    * @param strideWidth Width of the stride operation.
    * @param strideHeight Width of the stride operation.
    * @param floor Set to true to use floor method.
    */
-  LpPooling(const size_t norm_type,
+  LpPooling(const size_t normType,
             const size_t kernelWidth,
             const size_t kernelHeight,
             const size_t strideWidth = 1,
@@ -112,10 +112,10 @@ class LpPooling
   //! Get the output size.
   size_t OutputSize() const { return outSize; }
 
-  //! Get the norm_type.
-  size_t NormType() const { return norm_type; }
-  //! Modify the norm_type.
-  size_t& NormType() { return norm_type; }
+  //! Get the normType.
+  size_t NormType() const { return normType; }
+  //! Modify the normType.
+  size_t& NormType() { return normType; }
 
   //! Get the kernel width.
   size_t KernelWidth() const { return kernelWidth; }
@@ -172,7 +172,7 @@ class LpPooling
             arma::span(colidx, colidx + kernelHeight - 1 - offset));
 
         output(i, j) = pow(arma::accu(arma::pow(subInput,
-            norm_type)), 1.0/norm_type);
+            normType)), 1.0/normType);
       }
     }
   }
@@ -198,11 +198,11 @@ class LpPooling
       {
         const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
             arma::span(j, j + cStep - 1));
-        size_t sum = pow(arma::accu(arma::pow(inputArea, norm_type)),
-            (norm_type-1) / norm_type);
+        size_t sum = pow(arma::accu(arma::pow(inputArea, normType)),
+            (normType-1) / normType);
         unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
         unpooledError.fill(error(i / rStep, j / cStep));
-        unpooledError %= arma::pow(inputArea, norm_type - 1);
+        unpooledError %= arma::pow(inputArea, normType - 1);
         unpooledError /= sum;
         output(arma::span(i, i + rStep - 1 - offset),
             arma::span(j, j + cStep - 1 - offset)) += unpooledError;
@@ -210,8 +210,8 @@ class LpPooling
     }
   }
 
-  //! Locally-stored norm_type.
-  size_t norm_type;
+  //! Locally-stored norm type.
+  size_t normType;
 
   //! Locally-stored width of the pooling window.
   size_t kernelWidth;
diff --git a/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
index e646796360..0abe08ada6 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling_impl.hpp
@@ -27,12 +27,13 @@ LpPooling<InputDataType, OutputDataType>::LpPooling()
 
 template<typename InputDataType, typename OutputDataType>
 LpPooling<InputDataType, OutputDataType>::LpPooling(
-    const size_t norm_type,
+    const size_t normType,
     const size_t kernelWidth,
     const size_t kernelHeight,
     const size_t strideWidth,
     const size_t strideHeight,
     const bool floor) :
+    normType(normType),
     kernelWidth(kernelWidth),
     kernelHeight(kernelHeight),
     strideWidth(strideWidth),
@@ -121,7 +122,7 @@ void LpPooling<InputDataType, OutputDataType>::serialize(
     Archive& ar,
     const uint32_t /* version */)
 {
-  ar(CEREAL_NVP(norm_type));
+  ar(CEREAL_NVP(normType));
   ar(CEREAL_NVP(kernelWidth));
   ar(CEREAL_NVP(kernelHeight));
   ar(CEREAL_NVP(strideWidth));

From b0f6470767d9cc6e708169be698a3174f090f0c8 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Mon, 8 Feb 2021 09:10:00 +0530
Subject: [PATCH 157/253] Update layer_types.hpp

---
 src/mlpack/methods/ann/layer/layer_types.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index d27a5a6d25..091d7ece35 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -220,6 +220,7 @@ class AdaptiveMeanPooling;
 
 using MoreTypes = boost::variant<
         Linear3D<arma::mat, arma::mat, NoRegularizer>*,
+        LpPooling<arma::mat, arma::mat>*,
         Glimpse<arma::mat, arma::mat>*,
         Highway<arma::mat, arma::mat>*,
         MultiheadAttention<arma::mat, arma::mat, NoRegularizer>*,
@@ -283,7 +284,6 @@ using LayerTypes = boost::variant<
     LSTM<arma::mat, arma::mat>*,
     MaxPooling<arma::mat, arma::mat>*,
     MeanPooling<arma::mat, arma::mat>*,
-    LpPooling<arma::mat, arma::mat>*,
     MiniBatchDiscrimination<arma::mat, arma::mat>*,
     MultiplyConstant<arma::mat, arma::mat>*,
     MultiplyMerge<arma::mat, arma::mat>*,

From 709eb40dbe731a6baab317c4c2361e540e78a02d Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 02:45:23 +0530
Subject: [PATCH 158/253] minor

---
 src/mlpack/methods/ann/layer/kmax_pooling.hpp | 310 ++++++++++++++++++
 .../methods/ann/layer/kmax_pooling_impl.hpp   | 165 ++++++++++
 2 files changed, 475 insertions(+)
 create mode 100644 src/mlpack/methods/ann/layer/kmax_pooling.hpp
 create mode 100644 src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp

diff --git a/src/mlpack/methods/ann/layer/kmax_pooling.hpp b/src/mlpack/methods/ann/layer/kmax_pooling.hpp
new file mode 100644
index 0000000000..098a9d100a
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/kmax_pooling.hpp
@@ -0,0 +1,310 @@
+/**
+ * @file methods/ann/layer/max_pooling.hpp
+ * @author Marcus Edel
+ * @author Nilay Jain
+ *
+ * Definition of the MaxPooling class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_MAX_POOLING_HPP
+#define MLPACK_METHODS_ANN_LAYER_MAX_POOLING_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+/*
+ * The max pooling rule for convolution neural networks. Take the maximum value
+ * within the receptive block.
+ */
+class MaxPoolingRule
+{
+ public:
+  /*
+   * Return the maximum value within the receptive block.
+   *
+   * @param input Input used to perform the pooling operation.
+   */
+  template<typename MatType>
+  size_t Pooling(const MatType& input)
+  {
+    return arma::as_scalar(arma::find(input.max() == input, 1));
+  }
+};
+
+/**
+ * Implementation of the MaxPooling layer.
+ *
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ */
+template <
+    typename InputDataType = arma::mat,
+    typename OutputDataType = arma::mat
+>
+class MaxPooling
+{
+ public:
+  //! Create the MaxPooling object.
+  MaxPooling();
+
+  /**
+   * Create the MaxPooling object using the specified number of units.
+   *
+   * @param kernelWidth Width of the pooling window.
+   * @param kernelHeight Height of the pooling window.
+   * @param strideWidth Width of the stride operation.
+   * @param strideHeight Width of the stride operation.
+   * @param floor Rounding operator (floor or ceil).
+   */
+  MaxPooling(const size_t kernelWidth,
+             const size_t kernelHeight,
+             const size_t strideWidth = 1,
+             const size_t strideHeight = 1,
+             const bool floor = true);
+
+  /**
+   * Ordinary feed forward pass of a neural network, evaluating the function
+   * f(x) by propagating the activity forward through f.
+   *
+   * @param input Input data used for evaluating the specified function.
+   * @param output Resulting output activation.
+   */
+  template<typename eT>
+  void Forward(const arma::Mat<eT>& input, arma::Mat<eT>& output);
+
+  /**
+   * Ordinary feed backward pass of a neural network, using 3rd-order tensors as
+   * input, calculating the function f(x) by propagating x backwards through f.
+   * Using the results from the feed forward pass.
+   *
+   * @param * (input) The propagated input activation.
+   * @param gy The backpropagated error.
+   * @param g The calculated gradient.
+   */
+  template<typename eT>
+  void Backward(const arma::Mat<eT>& /* input */,
+                const arma::Mat<eT>& gy,
+                arma::Mat<eT>& g);
+
+  //! Get the output parameter.
+  const OutputDataType& OutputParameter() const { return outputParameter; }
+  //! Modify the output parameter.
+  OutputDataType& OutputParameter() { return outputParameter; }
+
+  //! Get the delta.
+  const OutputDataType& Delta() const { return delta; }
+  //! Modify the delta.
+  OutputDataType& Delta() { return delta; }
+
+  //! Get the input width.
+  size_t InputWidth() const { return inputWidth; }
+  //! Modify the input width.
+  size_t& InputWidth() { return inputWidth; }
+
+  //! Get the input height.
+  size_t InputHeight() const { return inputHeight; }
+  //! Modify the input height.
+  size_t& InputHeight() { return inputHeight; }
+
+  //! Get the output width.
+  size_t OutputWidth() const { return outputWidth; }
+  //! Modify the output width.
+  size_t& OutputWidth() { return outputWidth; }
+
+  //! Get the output height.
+  size_t OutputHeight() const { return outputHeight; }
+  //! Modify the output height.
+  size_t& OutputHeight() { return outputHeight; }
+
+  //! Get the input size.
+  size_t InputSize() const { return inSize; }
+
+  //! Get the output size.
+  size_t OutputSize() const { return outSize; }
+
+  //! Get the kernel width.
+  size_t KernelWidth() const { return kernelWidth; }
+  //! Modify the kernel width.
+  size_t& KernelWidth() { return kernelWidth; }
+
+  //! Get the kernel height.
+  size_t KernelHeight() const { return kernelHeight; }
+  //! Modify the kernel height.
+  size_t& KernelHeight() { return kernelHeight; }
+
+  //! Get the stride width.
+  size_t StrideWidth() const { return strideWidth; }
+  //! Modify the stride width.
+  size_t& StrideWidth() { return strideWidth; }
+
+  //! Get the stride height.
+  size_t StrideHeight() const { return strideHeight; }
+  //! Modify the stride height.
+  size_t& StrideHeight() { return strideHeight; }
+
+  //! Get the value of the rounding operation.
+  bool Floor() const { return floor; }
+  //! Modify the value of the rounding operation.
+  bool& Floor() { return floor; }
+
+  //! Get the value of the deterministic parameter.
+  bool Deterministic() const { return deterministic; }
+  //! Modify the value of the deterministic parameter.
+  bool& Deterministic() { return deterministic; }
+
+  //! Get the size of the weights.
+  size_t WeightSize() const { return 0; }
+
+  /**
+   * Serialize the layer.
+   */
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */);
+
+ private:
+ /**
+   * Apply pooling to the input and store the results.
+   *
+   * @param input The input to be apply the pooling rule.
+   * @param output The pooled result.
+   * @param poolingIndices The pooled indices.
+   */
+  template<typename eT>
+  void PoolingOperation(const arma::Mat<eT>& input,
+                        arma::Mat<eT>& output,
+                        arma::Mat<eT>& poolingIndices)
+  {
+    for (size_t j = 0, colidx = 0; j < output.n_cols;
+        ++j, colidx += strideHeight)
+    {
+      for (size_t i = 0, rowidx = 0; i < output.n_rows;
+          ++i, rowidx += strideWidth)
+      {
+        arma::mat subInput = input(
+            arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
+            arma::span(colidx, colidx + kernelHeight - 1 - offset));
+
+        const size_t idx = pooling.Pooling(subInput);
+        output(i, j) = subInput(idx);
+
+        if (!deterministic)
+        {
+          arma::Mat<size_t> subIndices = indices(arma::span(rowidx,
+              rowidx + kernelWidth - 1 - offset),
+              arma::span(colidx, colidx + kernelHeight - 1 - offset));
+
+          poolingIndices(i, j) = subIndices(idx);
+        }
+      }
+    }
+  }
+
+  /**
+   * Apply unpooling to the input and store the results.
+   *
+   * @param error The backward error.
+   * @param output The pooled result.
+   * @param poolingIndices The pooled indices.
+   */
+  template<typename eT>
+  void Unpooling(const arma::Mat<eT>& error,
+                 arma::Mat<eT>& output,
+                 arma::Mat<eT>& poolingIndices)
+  {
+    for (size_t i = 0; i < poolingIndices.n_elem; ++i)
+    {
+      output(poolingIndices(i)) += error(i);
+    }
+  }
+
+  //! Locally-stored width of the pooling window.
+  size_t kernelWidth;
+
+  //! Locally-stored height of the pooling window.
+  size_t kernelHeight;
+
+  //! Locally-stored width of the stride operation.
+  size_t strideWidth;
+
+  //! Locally-stored height of the stride operation.
+  size_t strideHeight;
+
+  //! Rounding operation used.
+  bool floor;
+
+  //! Locally-stored number of input channels.
+  size_t inSize;
+
+  //! Locally-stored number of output channels.
+  size_t outSize;
+
+  //! Locally-stored reset parameter used to initialize the module once.
+  bool reset;
+
+  //! Locally-stored input width.
+  size_t inputWidth;
+
+  //! Locally-stored input height.
+  size_t inputHeight;
+
+  //! Locally-stored output width.
+  size_t outputWidth;
+
+  //! Locally-stored output height.
+  size_t outputHeight;
+
+  //! If true use maximum a posteriori during the forward pass.
+  bool deterministic;
+
+  //! Locally-stored stored rounding offset.
+  size_t offset;
+
+  //! Locally-stored number of input units.
+  size_t batchSize;
+
+  //! Locally-stored output parameter.
+  arma::cube outputTemp;
+
+  //! Locally-stored transformed input parameter.
+  arma::cube inputTemp;
+
+  //! Locally-stored transformed output parameter.
+  arma::cube gTemp;
+
+  //! Locally-stored pooling strategy.
+  MaxPoolingRule pooling;
+
+  //! Locally-stored delta object.
+  OutputDataType delta;
+
+  //! Locally-stored gradient object.
+  OutputDataType gradient;
+
+  //! Locally-stored output parameter object.
+  OutputDataType outputParameter;
+
+  //! Locally-stored indices matrix parameter.
+  arma::Mat<size_t> indices;
+
+  //! Locally-stored indices column parameter.
+  arma::Col<size_t> indicesCol;
+
+  //! Locally-stored pooling indicies.
+  std::vector<arma::cube> poolingIndices;
+}; // class MaxPooling
+
+} // namespace ann
+} // namespace mlpack
+
+// Include implementation.
+#include "max_pooling_impl.hpp"
+
+#endif
diff --git a/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp b/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp
new file mode 100644
index 0000000000..cbc17904c4
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp
@@ -0,0 +1,165 @@
+/**
+ * @file methods/ann/layer/max_pooling_impl.hpp
+ * @author Marcus Edel
+ * @author Nilay Jain
+ *
+ * Implementation of the MaxPooling class.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_MAX_POOLING_IMPL_HPP
+#define MLPACK_METHODS_ANN_LAYER_MAX_POOLING_IMPL_HPP
+
+// In case it hasn't yet been included.
+#include "max_pooling.hpp"
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+template<typename InputDataType, typename OutputDataType>
+MaxPooling<InputDataType, OutputDataType>::MaxPooling()
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+MaxPooling<InputDataType, OutputDataType>::MaxPooling(
+    const size_t kernelWidth,
+    const size_t kernelHeight,
+    const size_t strideWidth,
+    const size_t strideHeight,
+    const bool floor) :
+    kernelWidth(kernelWidth),
+    kernelHeight(kernelHeight),
+    strideWidth(strideWidth),
+    strideHeight(strideHeight),
+    floor(floor),
+    inSize(0),
+    outSize(0),
+    reset(false),
+    inputWidth(0),
+    inputHeight(0),
+    outputWidth(0),
+    outputHeight(0),
+    deterministic(false),
+    offset(0),
+    batchSize(0)
+{
+  // Nothing to do here.
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void MaxPooling<InputDataType, OutputDataType>::Forward(
+  const arma::Mat<eT>& input, arma::Mat<eT>& output)
+{
+  batchSize = input.n_cols;
+  inSize = input.n_elem / (inputWidth * inputHeight * batchSize);
+  inputTemp = arma::cube(const_cast<arma::Mat<eT>&>(input).memptr(),
+      inputWidth, inputHeight, batchSize * inSize, false, false);
+
+  if (floor)
+  {
+    outputWidth = std::floor((inputWidth -
+        (double) kernelWidth) / (double) strideWidth + 1);
+    outputHeight = std::floor((inputHeight -
+        (double) kernelHeight) / (double) strideHeight + 1);
+    offset = 0;
+  }
+  else
+  {
+    outputWidth = std::ceil((inputWidth -
+        (double) kernelWidth) / (double) strideWidth + 1);
+    outputHeight = std::ceil((inputHeight -
+        (double) kernelHeight) / (double) strideHeight + 1);
+    offset = 1;
+  }
+
+  outputTemp = arma::zeros<arma::Cube<eT> >(outputWidth, outputHeight,
+      batchSize * inSize);
+
+  if (!deterministic)
+  {
+    poolingIndices.push_back(outputTemp);
+  }
+
+  if (!reset)
+  {
+    size_t elements = inputWidth * inputHeight;
+    indicesCol = arma::linspace<arma::Col<size_t> >(0, (elements - 1),
+        elements);
+
+    indices = arma::Mat<size_t>(indicesCol.memptr(), inputWidth, inputHeight);
+
+    reset = true;
+  }
+
+  for (size_t s = 0; s < inputTemp.n_slices; s++)
+  {
+    if (!deterministic)
+    {
+      PoolingOperation(inputTemp.slice(s), outputTemp.slice(s),
+        poolingIndices.back().slice(s));
+    }
+    else
+    {
+      PoolingOperation(inputTemp.slice(s), outputTemp.slice(s),
+          inputTemp.slice(s));
+    }
+  }
+
+  output = arma::Mat<eT>(outputTemp.memptr(), outputTemp.n_elem / batchSize,
+      batchSize);
+
+  outputWidth = outputTemp.n_rows;
+  outputHeight = outputTemp.n_cols;
+  outSize = batchSize * inSize;
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename eT>
+void MaxPooling<InputDataType, OutputDataType>::Backward(
+    const arma::Mat<eT>& /* input */, const arma::Mat<eT>& gy, arma::Mat<eT>& g)
+{
+  arma::cube mappedError = arma::cube(((arma::Mat<eT>&) gy).memptr(),
+      outputWidth, outputHeight, outSize, false, false);
+
+  gTemp = arma::zeros<arma::cube>(inputTemp.n_rows,
+      inputTemp.n_cols, inputTemp.n_slices);
+
+  for (size_t s = 0; s < mappedError.n_slices; s++)
+  {
+    Unpooling(mappedError.slice(s), gTemp.slice(s),
+        poolingIndices.back().slice(s));
+  }
+
+  poolingIndices.pop_back();
+
+  g = arma::mat(gTemp.memptr(), gTemp.n_elem / batchSize, batchSize);
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename Archive>
+void MaxPooling<InputDataType, OutputDataType>::serialize(
+    Archive& ar,
+    const uint32_t /* version */)
+{
+  ar(CEREAL_NVP(kernelWidth));
+  ar(CEREAL_NVP(kernelHeight));
+  ar(CEREAL_NVP(strideWidth));
+  ar(CEREAL_NVP(strideHeight));
+  ar(CEREAL_NVP(batchSize));
+  ar(CEREAL_NVP(floor));
+  ar(CEREAL_NVP(inputWidth));
+  ar(CEREAL_NVP(inputHeight));
+  ar(CEREAL_NVP(outputWidth));
+  ar(CEREAL_NVP(outputHeight));
+}
+
+} // namespace ann
+} // namespace mlpack
+
+#endif

From 03115231bc956588ad0815ea44000c5052a8f78a Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 03:47:23 +0530
Subject: [PATCH 159/253] Implemented ISRLU Activation Function

---
 src/mlpack/methods/ann/layer/CMakeLists.txt   |   2 +
 src/mlpack/methods/ann/layer/isrlu.hpp        | 145 ++++++++++++++++++
 src/mlpack/methods/ann/layer/isrlu_impl.hpp   |  70 +++++++++
 src/mlpack/methods/ann/layer/layer_types.hpp  |   2 +
 .../tests/activation_functions_test.cpp       |  64 ++++++++
 5 files changed, 283 insertions(+)
 create mode 100644 src/mlpack/methods/ann/layer/isrlu.hpp
 create mode 100644 src/mlpack/methods/ann/layer/isrlu_impl.hpp

diff --git a/src/mlpack/methods/ann/layer/CMakeLists.txt b/src/mlpack/methods/ann/layer/CMakeLists.txt
index b4726b0c6f..e7894b140b 100644
--- a/src/mlpack/methods/ann/layer/CMakeLists.txt
+++ b/src/mlpack/methods/ann/layer/CMakeLists.txt
@@ -46,6 +46,8 @@ set(SOURCES
   hard_tanh_impl.hpp
   highway.hpp
   highway_impl.hpp
+  isrlu.hpp
+  isrlu_impl.hpp
   join.hpp
   join_impl.hpp
   layer.hpp
diff --git a/src/mlpack/methods/ann/layer/isrlu.hpp b/src/mlpack/methods/ann/layer/isrlu.hpp
new file mode 100644
index 0000000000..d8fad5be47
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/isrlu.hpp
@@ -0,0 +1,145 @@
+/**
+ * @file methods/ann/layer/isrlu.hpp
+ * @author Abhinav Anand
+ *
+ * Definition of the ISRLU activation function as described by Jonathan T. Barron.
+ *
+ * For more information, read the following paper.
+ *
+ * @code
+ * @article{
+ *   author  = {Carlile, Brad and Delamarter, Guy and Kinney, Paul and Marti, Akiko and Whitney, Brian},
+ *   title   = {Improving deep learning by inverse square root linear units (ISRLUs)},
+ *   year    = {2017},
+ *   url     = {https://arxiv.org/pdf/1710.09967.pdf}
+ * }
+ * @endcode
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_ISRLU_HPP
+#define MLPACK_METHODS_ANN_LAYER_ISRLU_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+/**
+ * The ISRLU activation function, defined by
+ *
+ * @f{eqnarray*}{
+ * f(x) &=& \left\{
+ *   \begin{array}{lr}
+ *    x & : x \ge 0 \\
+ *    x(\frac{1}{1 + \alpha x^2}) & : x < 0
+ *   \end{array}
+ * \right. \\
+ * f'(x) &=& \left\{
+ *   \begin{array}{lr}
+ *    x & : 1 \ge 0 \\
+ *    (\frac{1}{1 + \alpha x^2})^3 & : x < 0
+ *   \end{array}
+ * \right. 
+ * @f}
+ *
+ * In the deterministic mode, there is no computation of the derivative.
+ *
+ * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
+ *         arma::sp_mat or arma::cube).
+ */
+template <
+    typename InputDataType = arma::mat,
+    typename OutputDataType = arma::mat
+>
+class ISRLU
+{
+ public:
+  /**
+   * Create the ISRLU object using the specified parameter.
+   *
+   * @param alpha Scale parameter controls the value to which an ISRLU
+   *        saturates for negative inputs.
+   */
+  ISRLU(const double alpha = 1.0);
+
+  /**
+   * Ordinary feed forward pass of a neural network, evaluating the function
+   * f(x) by propagating the activity forward through f.
+   *
+   * @param input Input data used for evaluating the specified function.
+   * @param output Resulting output activation.
+   */
+  template<typename InputType, typename OutputType>
+  void Forward(const InputType& input, OutputType& output);
+
+  /**
+   * Ordinary feed backward pass of a neural network, calculating the function
+   * f(x) by propagating x backwards through f. Using the results from the feed
+   * forward pass.
+   *
+   * @param input The propagated input activation f(x).
+   * @param gy The backpropagated error.
+   * @param g The calculated gradient.
+   */
+  template<typename DataType>
+  void Backward(const DataType& input, const DataType& gy, DataType& g);
+
+  //! Get the output parameter.
+  OutputDataType const& OutputParameter() const { return outputParameter; }
+  //! Modify the output parameter.
+  OutputDataType& OutputParameter() { return outputParameter; }
+
+  //! Get the delta.
+  OutputDataType const& Delta() const { return delta; }
+  //! Modify the delta.
+  OutputDataType& Delta() { return delta; }
+
+  //! Get the non zero gradient.
+  double const& Alpha() const { return alpha; }
+  //! Modify the non zero gradient.
+  double& Alpha() { return alpha; }
+
+  //! Get the value of deterministic parameter.
+  bool Deterministic() const { return deterministic; }
+  //! Modify the value of deterministic parameter.
+  bool& Deterministic() { return deterministic; }
+
+  //! Get size of weights.
+  size_t WeightSize() { return 0; }
+
+  /**
+   * Serialize the layer.
+   */
+  template<typename Archive>
+  void serialize(Archive& ar, const uint32_t /* version */);
+
+ private:
+  //! Locally-stored delta object.
+  OutputDataType delta;
+
+  //! Locally-stored output parameter object.
+  OutputDataType outputParameter;
+
+  //! Locally stored first derivative of the activation function.
+  arma::mat derivative;
+
+  //! ISRLU Hyperparameter (alpha > 0).
+  double alpha;
+
+  //! If true the derivative computation is disabled, see notes above.
+  bool deterministic;
+}; // class ISRLU
+
+} // namespace ann
+} // namespace mlpack
+
+// Include implementation.
+#include "isrlu_impl.hpp"
+
+#endif
diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
new file mode 100644
index 0000000000..2774f6bb12
--- /dev/null
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -0,0 +1,70 @@
+/**
+ * @file methods/ann/layer/isrlu_impl.hpp
+ * @author Gaurav Singh
+ *
+ * Implementation of the ISRLU activation function as described by Jonathan T. Barron.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_LAYER_ISRLU_IMPL_HPP
+#define MLPACK_METHODS_ANN_LAYER_V_IMPL_HPP
+
+// In case it hasn't yet been included.
+#include "isrlu.hpp"
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+
+template<typename InputDataType, typename OutputDataType>
+ISRLU<InputDataType, OutputDataType>::ISRLU(const double alpha) :
+    alpha(alpha),
+    deterministic(false)
+{}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename InputType, typename OutputType>
+void ISRLU<InputDataType, OutputDataType>::Forward(
+    const InputType& input, OutputType& output)
+{
+  output = arma::ones<OutputDataType>(arma::size(input));
+  for (size_t i = 0; i < input.n_elem; ++i)
+  {
+    output(i) = (input(i) >= 0) ? input(i) : input(i) *
+                (1 / std::sqrt(1 + alpha*input(i)*input(i)));
+  }
+
+  if (!deterministic)
+  {
+    derivative.set_size(arma::size(input));
+    for (size_t i = 0; i < input.n_elem; ++i)
+    {
+      derivative(i) = (input(i) >= 0) ? 1 :
+          std:pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
+    }
+  }
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename DataType>
+void ISRLU<InputDataType, OutputDataType>::Backward(
+    const DataType& /* input */, const DataType& gy, DataType& g)
+{
+  g = gy % derivative;
+}
+
+template<typename InputDataType, typename OutputDataType>
+template<typename Archive>
+void ISRLU<InputDataType, OutputDataType>::serialize(
+    Archive& ar,
+    const uint32_t /* version */)
+{
+  ar(CEREAL_NVP(alpha));
+}
+
+} // namespace ann
+} // namespace mlpack
+
+#endif
diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index 1d7fd0ccba..72c3df52ce 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -52,6 +52,7 @@
 #include <mlpack/methods/ann/layer/virtual_batch_norm.hpp>
 #include <mlpack/methods/ann/layer/hardshrink.hpp>
 #include <mlpack/methods/ann/layer/celu.hpp>
+#include <mlpack/methods/ann/layer/isrlu.hpp>
 #include <mlpack/methods/ann/layer/softshrink.hpp>
 #include <mlpack/methods/ann/layer/radial_basis_function.hpp>
 
@@ -272,6 +273,7 @@ using LayerTypes = boost::variant<
     FlexibleReLU<arma::mat, arma::mat>*,
     GRU<arma::mat, arma::mat>*,
     HardTanH<arma::mat, arma::mat>*,
+    ISRLU<arma::mat, arma::mat>*,
     Join<arma::mat, arma::mat>*,
     LayerNorm<arma::mat, arma::mat>*,
     LeakyReLU<arma::mat, arma::mat>*,
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index d88c0a5109..3ac6437cd0 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -558,6 +558,54 @@ void CheckCELUDerivativeCorrect(const arma::colvec input,
   }
 }
 
+/**
+ * Implementation of the ISRLU activation function test. The function is
+ * implemented as ISRLU layer in the file isrlu.hpp.
+ *
+ * @param input Input data used for evaluating the ISRLU activation function.
+ * @param target Target data used to evaluate the ISRLU activation.
+ */
+void CheckISRLUActivationCorrect(const arma::colvec input,
+                                const arma::colvec target)
+{
+  // Initialize ISRLU object with alpha = 1.0.
+  ISRLU<> lrf(1.0);
+
+  // Test the activation function using the entire vector as input.
+  arma::colvec activations;
+  lrf.Forward(input, activations);
+  for (size_t i = 0; i < activations.n_elem; ++i)
+  {
+    REQUIRE(activations.at(i) == Approx(target.at(i)).epsilon(1e-5));
+  }
+}
+
+/**
+ * Implementation of the ISRLU activation function derivative test. The function
+ * is implemented as ISRLU layer in the file isrlu.hpp.
+ *
+ * @param input Input data used for evaluating the ISRLU activation function.
+ * @param target Target data used to evaluate the ISRLU activation.
+ */
+void CheckISRLUDerivativeCorrect(const arma::colvec input,
+                                const arma::colvec target)
+{
+  // Initialize ISRLU object with alpha = 1.0.
+  ISRLU<> lrf(1.0);
+
+  // Test the calculation of the derivatives using the entire vector as input.
+  arma::colvec derivatives, activations;
+
+  // This error vector will be set to 1 to get the derivatives.
+  arma::colvec error = arma::ones<arma::colvec>(input.n_elem);
+  lrf.Forward(input, activations);
+  lrf.Backward(activations, error, derivatives);
+  for (size_t i = 0; i < derivatives.n_elem; ++i)
+  {
+    REQUIRE(derivatives.at(i) == Approx(target.at(i)).epsilon(1e-5));
+  }
+}
+
 /**
  * Implementation of the Softmin activation function test. The function is
  * implemented as Softmin layer in the file softmin.hpp.
@@ -991,6 +1039,22 @@ TEST_CASE("CELUFunctionTest", "[ActivationFunctionsTest]")
   CheckCELUDerivativeCorrect(desiredActivations, desiredDerivatives);
 }
 
+/**
+ * Basic test of the ISRLU activation function.
+ */
+TEST_CASE("ISRLUFunctionTest", "[ActivationFunctionsTest]")
+{
+  const arma::colvec desiredActivations("-0.89442719 3.2 4.5 \
+                                         -0.99995020 1 -0.70710678 2 0");
+
+  const arma::colvec desiredDerivatives("0.74535599 1 1 \
+                                         0.70712438 1 \
+                                         0.81649658 1 1");
+
+  CheckISRLUActivationCorrect(activationData, desiredActivations);
+  CheckISRLUDerivativeCorrect(desiredActivations, desiredDerivatives);
+}
+
 /**
  * Basic test of the inverse quadratic function.
  */

From 638be09256da8c3e93e54c06c5f9b0e0cbcec61b Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 03:58:31 +0530
Subject: [PATCH 160/253] minor change

---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp   |   2 +-
 src/mlpack/methods/ann/layer/kmax_pooling.hpp | 310 ------------------
 .../methods/ann/layer/kmax_pooling_impl.hpp   | 165 ----------
 3 files changed, 1 insertion(+), 476 deletions(-)
 delete mode 100644 src/mlpack/methods/ann/layer/kmax_pooling.hpp
 delete mode 100644 src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 2774f6bb12..8e74241305 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -1,6 +1,6 @@
 /**
  * @file methods/ann/layer/isrlu_impl.hpp
- * @author Gaurav Singh
+ * @author Abhinav Anand
  *
  * Implementation of the ISRLU activation function as described by Jonathan T. Barron.
  *
diff --git a/src/mlpack/methods/ann/layer/kmax_pooling.hpp b/src/mlpack/methods/ann/layer/kmax_pooling.hpp
deleted file mode 100644
index 098a9d100a..0000000000
--- a/src/mlpack/methods/ann/layer/kmax_pooling.hpp
+++ /dev/null
@@ -1,310 +0,0 @@
-/**
- * @file methods/ann/layer/max_pooling.hpp
- * @author Marcus Edel
- * @author Nilay Jain
- *
- * Definition of the MaxPooling class.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-#ifndef MLPACK_METHODS_ANN_LAYER_MAX_POOLING_HPP
-#define MLPACK_METHODS_ANN_LAYER_MAX_POOLING_HPP
-
-#include <mlpack/prereqs.hpp>
-
-namespace mlpack {
-namespace ann /** Artificial Neural Network. */ {
-
-/*
- * The max pooling rule for convolution neural networks. Take the maximum value
- * within the receptive block.
- */
-class MaxPoolingRule
-{
- public:
-  /*
-   * Return the maximum value within the receptive block.
-   *
-   * @param input Input used to perform the pooling operation.
-   */
-  template<typename MatType>
-  size_t Pooling(const MatType& input)
-  {
-    return arma::as_scalar(arma::find(input.max() == input, 1));
-  }
-};
-
-/**
- * Implementation of the MaxPooling layer.
- *
- * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
- *         arma::sp_mat or arma::cube).
- * @tparam OutputDataType Type of the output data (arma::colvec, arma::mat,
- *         arma::sp_mat or arma::cube).
- */
-template <
-    typename InputDataType = arma::mat,
-    typename OutputDataType = arma::mat
->
-class MaxPooling
-{
- public:
-  //! Create the MaxPooling object.
-  MaxPooling();
-
-  /**
-   * Create the MaxPooling object using the specified number of units.
-   *
-   * @param kernelWidth Width of the pooling window.
-   * @param kernelHeight Height of the pooling window.
-   * @param strideWidth Width of the stride operation.
-   * @param strideHeight Width of the stride operation.
-   * @param floor Rounding operator (floor or ceil).
-   */
-  MaxPooling(const size_t kernelWidth,
-             const size_t kernelHeight,
-             const size_t strideWidth = 1,
-             const size_t strideHeight = 1,
-             const bool floor = true);
-
-  /**
-   * Ordinary feed forward pass of a neural network, evaluating the function
-   * f(x) by propagating the activity forward through f.
-   *
-   * @param input Input data used for evaluating the specified function.
-   * @param output Resulting output activation.
-   */
-  template<typename eT>
-  void Forward(const arma::Mat<eT>& input, arma::Mat<eT>& output);
-
-  /**
-   * Ordinary feed backward pass of a neural network, using 3rd-order tensors as
-   * input, calculating the function f(x) by propagating x backwards through f.
-   * Using the results from the feed forward pass.
-   *
-   * @param * (input) The propagated input activation.
-   * @param gy The backpropagated error.
-   * @param g The calculated gradient.
-   */
-  template<typename eT>
-  void Backward(const arma::Mat<eT>& /* input */,
-                const arma::Mat<eT>& gy,
-                arma::Mat<eT>& g);
-
-  //! Get the output parameter.
-  const OutputDataType& OutputParameter() const { return outputParameter; }
-  //! Modify the output parameter.
-  OutputDataType& OutputParameter() { return outputParameter; }
-
-  //! Get the delta.
-  const OutputDataType& Delta() const { return delta; }
-  //! Modify the delta.
-  OutputDataType& Delta() { return delta; }
-
-  //! Get the input width.
-  size_t InputWidth() const { return inputWidth; }
-  //! Modify the input width.
-  size_t& InputWidth() { return inputWidth; }
-
-  //! Get the input height.
-  size_t InputHeight() const { return inputHeight; }
-  //! Modify the input height.
-  size_t& InputHeight() { return inputHeight; }
-
-  //! Get the output width.
-  size_t OutputWidth() const { return outputWidth; }
-  //! Modify the output width.
-  size_t& OutputWidth() { return outputWidth; }
-
-  //! Get the output height.
-  size_t OutputHeight() const { return outputHeight; }
-  //! Modify the output height.
-  size_t& OutputHeight() { return outputHeight; }
-
-  //! Get the input size.
-  size_t InputSize() const { return inSize; }
-
-  //! Get the output size.
-  size_t OutputSize() const { return outSize; }
-
-  //! Get the kernel width.
-  size_t KernelWidth() const { return kernelWidth; }
-  //! Modify the kernel width.
-  size_t& KernelWidth() { return kernelWidth; }
-
-  //! Get the kernel height.
-  size_t KernelHeight() const { return kernelHeight; }
-  //! Modify the kernel height.
-  size_t& KernelHeight() { return kernelHeight; }
-
-  //! Get the stride width.
-  size_t StrideWidth() const { return strideWidth; }
-  //! Modify the stride width.
-  size_t& StrideWidth() { return strideWidth; }
-
-  //! Get the stride height.
-  size_t StrideHeight() const { return strideHeight; }
-  //! Modify the stride height.
-  size_t& StrideHeight() { return strideHeight; }
-
-  //! Get the value of the rounding operation.
-  bool Floor() const { return floor; }
-  //! Modify the value of the rounding operation.
-  bool& Floor() { return floor; }
-
-  //! Get the value of the deterministic parameter.
-  bool Deterministic() const { return deterministic; }
-  //! Modify the value of the deterministic parameter.
-  bool& Deterministic() { return deterministic; }
-
-  //! Get the size of the weights.
-  size_t WeightSize() const { return 0; }
-
-  /**
-   * Serialize the layer.
-   */
-  template<typename Archive>
-  void serialize(Archive& ar, const uint32_t /* version */);
-
- private:
- /**
-   * Apply pooling to the input and store the results.
-   *
-   * @param input The input to be apply the pooling rule.
-   * @param output The pooled result.
-   * @param poolingIndices The pooled indices.
-   */
-  template<typename eT>
-  void PoolingOperation(const arma::Mat<eT>& input,
-                        arma::Mat<eT>& output,
-                        arma::Mat<eT>& poolingIndices)
-  {
-    for (size_t j = 0, colidx = 0; j < output.n_cols;
-        ++j, colidx += strideHeight)
-    {
-      for (size_t i = 0, rowidx = 0; i < output.n_rows;
-          ++i, rowidx += strideWidth)
-      {
-        arma::mat subInput = input(
-            arma::span(rowidx, rowidx + kernelWidth - 1 - offset),
-            arma::span(colidx, colidx + kernelHeight - 1 - offset));
-
-        const size_t idx = pooling.Pooling(subInput);
-        output(i, j) = subInput(idx);
-
-        if (!deterministic)
-        {
-          arma::Mat<size_t> subIndices = indices(arma::span(rowidx,
-              rowidx + kernelWidth - 1 - offset),
-              arma::span(colidx, colidx + kernelHeight - 1 - offset));
-
-          poolingIndices(i, j) = subIndices(idx);
-        }
-      }
-    }
-  }
-
-  /**
-   * Apply unpooling to the input and store the results.
-   *
-   * @param error The backward error.
-   * @param output The pooled result.
-   * @param poolingIndices The pooled indices.
-   */
-  template<typename eT>
-  void Unpooling(const arma::Mat<eT>& error,
-                 arma::Mat<eT>& output,
-                 arma::Mat<eT>& poolingIndices)
-  {
-    for (size_t i = 0; i < poolingIndices.n_elem; ++i)
-    {
-      output(poolingIndices(i)) += error(i);
-    }
-  }
-
-  //! Locally-stored width of the pooling window.
-  size_t kernelWidth;
-
-  //! Locally-stored height of the pooling window.
-  size_t kernelHeight;
-
-  //! Locally-stored width of the stride operation.
-  size_t strideWidth;
-
-  //! Locally-stored height of the stride operation.
-  size_t strideHeight;
-
-  //! Rounding operation used.
-  bool floor;
-
-  //! Locally-stored number of input channels.
-  size_t inSize;
-
-  //! Locally-stored number of output channels.
-  size_t outSize;
-
-  //! Locally-stored reset parameter used to initialize the module once.
-  bool reset;
-
-  //! Locally-stored input width.
-  size_t inputWidth;
-
-  //! Locally-stored input height.
-  size_t inputHeight;
-
-  //! Locally-stored output width.
-  size_t outputWidth;
-
-  //! Locally-stored output height.
-  size_t outputHeight;
-
-  //! If true use maximum a posteriori during the forward pass.
-  bool deterministic;
-
-  //! Locally-stored stored rounding offset.
-  size_t offset;
-
-  //! Locally-stored number of input units.
-  size_t batchSize;
-
-  //! Locally-stored output parameter.
-  arma::cube outputTemp;
-
-  //! Locally-stored transformed input parameter.
-  arma::cube inputTemp;
-
-  //! Locally-stored transformed output parameter.
-  arma::cube gTemp;
-
-  //! Locally-stored pooling strategy.
-  MaxPoolingRule pooling;
-
-  //! Locally-stored delta object.
-  OutputDataType delta;
-
-  //! Locally-stored gradient object.
-  OutputDataType gradient;
-
-  //! Locally-stored output parameter object.
-  OutputDataType outputParameter;
-
-  //! Locally-stored indices matrix parameter.
-  arma::Mat<size_t> indices;
-
-  //! Locally-stored indices column parameter.
-  arma::Col<size_t> indicesCol;
-
-  //! Locally-stored pooling indicies.
-  std::vector<arma::cube> poolingIndices;
-}; // class MaxPooling
-
-} // namespace ann
-} // namespace mlpack
-
-// Include implementation.
-#include "max_pooling_impl.hpp"
-
-#endif
diff --git a/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp b/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp
deleted file mode 100644
index cbc17904c4..0000000000
--- a/src/mlpack/methods/ann/layer/kmax_pooling_impl.hpp
+++ /dev/null
@@ -1,165 +0,0 @@
-/**
- * @file methods/ann/layer/max_pooling_impl.hpp
- * @author Marcus Edel
- * @author Nilay Jain
- *
- * Implementation of the MaxPooling class.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-#ifndef MLPACK_METHODS_ANN_LAYER_MAX_POOLING_IMPL_HPP
-#define MLPACK_METHODS_ANN_LAYER_MAX_POOLING_IMPL_HPP
-
-// In case it hasn't yet been included.
-#include "max_pooling.hpp"
-
-namespace mlpack {
-namespace ann /** Artificial Neural Network. */ {
-
-template<typename InputDataType, typename OutputDataType>
-MaxPooling<InputDataType, OutputDataType>::MaxPooling()
-{
-  // Nothing to do here.
-}
-
-template<typename InputDataType, typename OutputDataType>
-MaxPooling<InputDataType, OutputDataType>::MaxPooling(
-    const size_t kernelWidth,
-    const size_t kernelHeight,
-    const size_t strideWidth,
-    const size_t strideHeight,
-    const bool floor) :
-    kernelWidth(kernelWidth),
-    kernelHeight(kernelHeight),
-    strideWidth(strideWidth),
-    strideHeight(strideHeight),
-    floor(floor),
-    inSize(0),
-    outSize(0),
-    reset(false),
-    inputWidth(0),
-    inputHeight(0),
-    outputWidth(0),
-    outputHeight(0),
-    deterministic(false),
-    offset(0),
-    batchSize(0)
-{
-  // Nothing to do here.
-}
-
-template<typename InputDataType, typename OutputDataType>
-template<typename eT>
-void MaxPooling<InputDataType, OutputDataType>::Forward(
-  const arma::Mat<eT>& input, arma::Mat<eT>& output)
-{
-  batchSize = input.n_cols;
-  inSize = input.n_elem / (inputWidth * inputHeight * batchSize);
-  inputTemp = arma::cube(const_cast<arma::Mat<eT>&>(input).memptr(),
-      inputWidth, inputHeight, batchSize * inSize, false, false);
-
-  if (floor)
-  {
-    outputWidth = std::floor((inputWidth -
-        (double) kernelWidth) / (double) strideWidth + 1);
-    outputHeight = std::floor((inputHeight -
-        (double) kernelHeight) / (double) strideHeight + 1);
-    offset = 0;
-  }
-  else
-  {
-    outputWidth = std::ceil((inputWidth -
-        (double) kernelWidth) / (double) strideWidth + 1);
-    outputHeight = std::ceil((inputHeight -
-        (double) kernelHeight) / (double) strideHeight + 1);
-    offset = 1;
-  }
-
-  outputTemp = arma::zeros<arma::Cube<eT> >(outputWidth, outputHeight,
-      batchSize * inSize);
-
-  if (!deterministic)
-  {
-    poolingIndices.push_back(outputTemp);
-  }
-
-  if (!reset)
-  {
-    size_t elements = inputWidth * inputHeight;
-    indicesCol = arma::linspace<arma::Col<size_t> >(0, (elements - 1),
-        elements);
-
-    indices = arma::Mat<size_t>(indicesCol.memptr(), inputWidth, inputHeight);
-
-    reset = true;
-  }
-
-  for (size_t s = 0; s < inputTemp.n_slices; s++)
-  {
-    if (!deterministic)
-    {
-      PoolingOperation(inputTemp.slice(s), outputTemp.slice(s),
-        poolingIndices.back().slice(s));
-    }
-    else
-    {
-      PoolingOperation(inputTemp.slice(s), outputTemp.slice(s),
-          inputTemp.slice(s));
-    }
-  }
-
-  output = arma::Mat<eT>(outputTemp.memptr(), outputTemp.n_elem / batchSize,
-      batchSize);
-
-  outputWidth = outputTemp.n_rows;
-  outputHeight = outputTemp.n_cols;
-  outSize = batchSize * inSize;
-}
-
-template<typename InputDataType, typename OutputDataType>
-template<typename eT>
-void MaxPooling<InputDataType, OutputDataType>::Backward(
-    const arma::Mat<eT>& /* input */, const arma::Mat<eT>& gy, arma::Mat<eT>& g)
-{
-  arma::cube mappedError = arma::cube(((arma::Mat<eT>&) gy).memptr(),
-      outputWidth, outputHeight, outSize, false, false);
-
-  gTemp = arma::zeros<arma::cube>(inputTemp.n_rows,
-      inputTemp.n_cols, inputTemp.n_slices);
-
-  for (size_t s = 0; s < mappedError.n_slices; s++)
-  {
-    Unpooling(mappedError.slice(s), gTemp.slice(s),
-        poolingIndices.back().slice(s));
-  }
-
-  poolingIndices.pop_back();
-
-  g = arma::mat(gTemp.memptr(), gTemp.n_elem / batchSize, batchSize);
-}
-
-template<typename InputDataType, typename OutputDataType>
-template<typename Archive>
-void MaxPooling<InputDataType, OutputDataType>::serialize(
-    Archive& ar,
-    const uint32_t /* version */)
-{
-  ar(CEREAL_NVP(kernelWidth));
-  ar(CEREAL_NVP(kernelHeight));
-  ar(CEREAL_NVP(strideWidth));
-  ar(CEREAL_NVP(strideHeight));
-  ar(CEREAL_NVP(batchSize));
-  ar(CEREAL_NVP(floor));
-  ar(CEREAL_NVP(inputWidth));
-  ar(CEREAL_NVP(inputHeight));
-  ar(CEREAL_NVP(outputWidth));
-  ar(CEREAL_NVP(outputHeight));
-}
-
-} // namespace ann
-} // namespace mlpack
-
-#endif

From 43fb21edcc9bf264b2ba634642d8d60b99c3c3c5 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 09:24:58 +0530
Subject: [PATCH 161/253] Minor code quality changes

---
 src/mlpack/methods/ann/layer/isrlu.hpp         | 3 ++-
 src/mlpack/methods/ann/layer/isrlu_impl.hpp    | 4 ++--
 src/mlpack/tests/activation_functions_test.cpp | 4 ++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu.hpp b/src/mlpack/methods/ann/layer/isrlu.hpp
index d8fad5be47..7d8eda954b 100644
--- a/src/mlpack/methods/ann/layer/isrlu.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu.hpp
@@ -8,7 +8,8 @@
  *
  * @code
  * @article{
- *   author  = {Carlile, Brad and Delamarter, Guy and Kinney, Paul and Marti, Akiko and Whitney, Brian},
+ *   author  = {Carlile, Brad and Delamarter, Guy and Kinney, Paul and Marti,
+ *              Akiko and Whitney, Brian},
  *   title   = {Improving deep learning by inverse square root linear units (ISRLUs)},
  *   year    = {2017},
  *   url     = {https://arxiv.org/pdf/1710.09967.pdf}
diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 8e74241305..651f1f1a28 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -10,7 +10,7 @@
  * http://www.opensource.org/licenses/BSD-3-Clause for more information.
  */
 #ifndef MLPACK_METHODS_ANN_LAYER_ISRLU_IMPL_HPP
-#define MLPACK_METHODS_ANN_LAYER_V_IMPL_HPP
+#define MLPACK_METHODS_ANN_LAYER_ISRLU_IMPL_HPP
 
 // In case it hasn't yet been included.
 #include "isrlu.hpp"
@@ -42,7 +42,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
     for (size_t i = 0; i < input.n_elem; ++i)
     {
       derivative(i) = (input(i) >= 0) ? 1 :
-          std:pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
+          std::pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
     }
   }
 }
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index 3ac6437cd0..847051cfac 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -566,7 +566,7 @@ void CheckCELUDerivativeCorrect(const arma::colvec input,
  * @param target Target data used to evaluate the ISRLU activation.
  */
 void CheckISRLUActivationCorrect(const arma::colvec input,
-                                const arma::colvec target)
+                                 const arma::colvec target)
 {
   // Initialize ISRLU object with alpha = 1.0.
   ISRLU<> lrf(1.0);
@@ -588,7 +588,7 @@ void CheckISRLUActivationCorrect(const arma::colvec input,
  * @param target Target data used to evaluate the ISRLU activation.
  */
 void CheckISRLUDerivativeCorrect(const arma::colvec input,
-                                const arma::colvec target)
+                                 const arma::colvec target)
 {
   // Initialize ISRLU object with alpha = 1.0.
   ISRLU<> lrf(1.0);

From cf9af9204500433a80e676f0bbacf0e7420442f9 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 10:59:05 +0530
Subject: [PATCH 162/253] changed layer_types

---
 src/mlpack/methods/ann/layer/layer_types.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index 72c3df52ce..718dd8c12e 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -235,7 +235,8 @@ using MoreTypes = boost::variant<
         VirtualBatchNorm<arma::mat, arma::mat>*,
         RBF<arma::mat, arma::mat, GaussianFunction>*,
         BaseLayer<GaussianFunction, arma::mat, arma::mat>*,
-        PositionalEncoding<arma::mat, arma::mat>*
+        PositionalEncoding<arma::mat, arma::mat>*,
+        ISRLU<arma::mat, arma::mat>*
 >;
 
 template <typename... CustomLayers>
@@ -273,7 +274,6 @@ using LayerTypes = boost::variant<
     FlexibleReLU<arma::mat, arma::mat>*,
     GRU<arma::mat, arma::mat>*,
     HardTanH<arma::mat, arma::mat>*,
-    ISRLU<arma::mat, arma::mat>*,
     Join<arma::mat, arma::mat>*,
     LayerNorm<arma::mat, arma::mat>*,
     LeakyReLU<arma::mat, arma::mat>*,

From 3c3d936f14dff7801bcd68c3eedf870c091b930d Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Tue, 9 Feb 2021 11:51:31 +0530
Subject: [PATCH 163/253]   fixed test  case

---
 src/mlpack/tests/activation_functions_test.cpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index 847051cfac..642aa84dc4 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -1047,9 +1047,9 @@ TEST_CASE("ISRLUFunctionTest", "[ActivationFunctionsTest]")
   const arma::colvec desiredActivations("-0.89442719 3.2 4.5 \
                                          -0.99995020 1 -0.70710678 2 0");
 
-  const arma::colvec desiredDerivatives("0.74535599 1 1 \
-                                         0.70712438 1 \
-                                         0.81649658 1 1");
+  const arma::colvec desiredDerivatives("0.41408666 1 1 \
+                                         0.35357980 1 \
+                                         0.54433105 1 1");
 
   CheckISRLUActivationCorrect(activationData, desiredActivations);
   CheckISRLUDerivativeCorrect(desiredActivations, desiredDerivatives);

From f2284403dfa82872a6500577aec9adbb53a20262 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Thu, 11 Feb 2021 01:35:26 +0530
Subject: [PATCH 164/253] Apply suggestions from code review

Co-authored-by: kartikdutt18 <39593019+kartikdutt18@users.noreply.github.com>
---
 src/mlpack/methods/ann/layer/lp_pooling.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/lp_pooling.hpp b/src/mlpack/methods/ann/layer/lp_pooling.hpp
index aa0f043c33..8423dda79f 100644
--- a/src/mlpack/methods/ann/layer/lp_pooling.hpp
+++ b/src/mlpack/methods/ann/layer/lp_pooling.hpp
@@ -172,7 +172,7 @@ class LpPooling
             arma::span(colidx, colidx + kernelHeight - 1 - offset));
 
         output(i, j) = pow(arma::accu(arma::pow(subInput,
-            normType)), 1.0/normType);
+            normType)), 1.0 / normType);
       }
     }
   }
@@ -199,7 +199,7 @@ class LpPooling
         const arma::Mat<eT>& inputArea = input(arma::span(i, i + rStep - 1),
             arma::span(j, j + cStep - 1));
         size_t sum = pow(arma::accu(arma::pow(inputArea, normType)),
-            (normType-1) / normType);
+            (normType - 1) / normType);
         unpooledError = arma::Mat<eT>(inputArea.n_rows, inputArea.n_cols);
         unpooledError.fill(error(i / rStep, j / cStep));
         unpooledError %= arma::pow(inputArea, normType - 1);

From 1160f1f5f2b45440324e1c2e0cc2da153d1340bf Mon Sep 17 00:00:00 2001
From: Ale Presacco <pressalex@hotmail.com>
Date: Wed, 10 Feb 2021 17:56:26 -0600
Subject: [PATCH 165/253] Update convolution.hpp

Adding a description about how the input matrix of the CNN layer should be organized
---
 src/mlpack/methods/ann/layer/convolution.hpp | 22 ++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/convolution.hpp b/src/mlpack/methods/ann/layer/convolution.hpp
index 1571c3e414..2ab22ddbfd 100644
--- a/src/mlpack/methods/ann/layer/convolution.hpp
+++ b/src/mlpack/methods/ann/layer/convolution.hpp
@@ -29,8 +29,26 @@ namespace ann /** Artificial Neural Network. */ {
 /**
  * Implementation of the Convolution class. The Convolution class represents a
  * single layer of a neural network.
- *
- * @tparam ForwardConvolutionRule Convolution to perform forward process.
+ *Example about how to organize the input matrix of the CNN. Say that I pass a matrix M(2744x100) to model.Add<Convolution<>>, which I have obtained from "flattening" 
+ *100 images (or Mel cepstral coefficients, if we talk about speech, or whatever you like) of dimension 196x14. In other words, the first 196 columns of each row of M 
+ *will be made of the 196 columns of the first row of each of the 100 images (or Mel cepstral coefficients). Then the next 295 columns of M (196 - 393) will be made 
+ *of the 196 columns of the second row of the 100 images (or Mel cepstral coefficients), etc. I want my input to be 196x14 for, so my add will be something like this:
+ 
+ *model.Add<Convolution<>>
+ *(1, // Number of input activation maps.
+    *14, // Number of output activation maps.
+        *3, // Filter width.
+            *3, // Filter height.
+                *1, // Stride along width.
+                    *1, // Stride along height.
+                        *0, // Padding width.
+                            *0, // Padding height.
+                                *196, // Input width.
+                                    *14 // Input height.
+                                        *);
+ *By doing so, will recreate the original 196x14 matrix for each image (or Mel cepstral coefficients) that will be used as input for the 14 filters of this example.
+
+* @tparam ForwardConvolutionRule Convolution to perform forward process.
  * @tparam BackwardConvolutionRule Convolution to perform backward process.
  * @tparam GradientConvolutionRule Convolution to calculate gradient.
  * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,

From 1ae6336ab4d49cb56c2f30ae1796542ed5407d99 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Fri, 12 Feb 2021 05:17:23 +0530
Subject: [PATCH 166/253] Update pixel_shuffle_impl.hpp

Updated Cereal_nvp
---
 .../methods/ann/layer/pixel_shuffle_impl.hpp  | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 796ee54071..17c7c93980 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -133,16 +133,17 @@ void PixelShuffle<InputDataType, OutputDataType>::serialize(
     Archive& ar,
     const unsigned int /* version */)
 {
-  ar & BOOST_SERIALIZATION_NVP(delta);
-  ar & BOOST_SERIALIZATION_NVP(outputParameter);
-  ar & BOOST_SERIALIZATION_NVP(upscaleFactor);
-  ar & BOOST_SERIALIZATION_NVP(height);
-  ar & BOOST_SERIALIZATION_NVP(width);
-  ar & BOOST_SERIALIZATION_NVP(size);
-  ar & BOOST_SERIALIZATION_NVP(batchSize);
-  ar & BOOST_SERIALIZATION_NVP(outputHeight);
-  ar & BOOST_SERIALIZATION_NVP(outputWidth);
-  ar & BOOST_SERIALIZATION_NVP(sizeOut);
+  ar(CEREAL_NVP(delta));
+  ar(CEREAL_NVP(outputParameter));
+  ar(CEREAL_NVP(upscaleFactor));
+  ar(CEREAL_NVP(height));
+  ar(CEREAL_NVP(width));
+  ar(CEREAL_NVP(size));
+  ar(CEREAL_NVP(batchSize));
+  ar(CEREAL_NVP(outputHeight));
+  ar(CEREAL_NVP(outputHeight));
+  ar(CEREAL_NVP(outputWidth));
+  ar(CEREAL_NVP(sizeOut));
 }
 
 } // namespace ann

From 1aae47ae0b3cc35bb5aff54d9f4a12f4f70a939f Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Fri, 12 Feb 2021 06:36:04 +0530
Subject: [PATCH 167/253] Update layer_types.hpp

Added pixel shuffle to more_types
---
 src/mlpack/methods/ann/layer/layer_types.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/layer_types.hpp b/src/mlpack/methods/ann/layer/layer_types.hpp
index 14bac39a81..c1e1987f70 100644
--- a/src/mlpack/methods/ann/layer/layer_types.hpp
+++ b/src/mlpack/methods/ann/layer/layer_types.hpp
@@ -220,6 +220,7 @@ class AdaptiveMeanPooling;
 
 using MoreTypes = boost::variant<
         Linear3D<arma::mat, arma::mat, NoRegularizer>*,
+        PixelShuffle<arma::mat, arma::mat>*,
         Glimpse<arma::mat, arma::mat>*,
         Highway<arma::mat, arma::mat>*,
         MultiheadAttention<arma::mat, arma::mat, NoRegularizer>*,
@@ -290,7 +291,6 @@ using LayerTypes = boost::variant<
     NoisyLinear<arma::mat, arma::mat>*,
     Padding<arma::mat, arma::mat>*,
     PReLU<arma::mat, arma::mat>*,
-    PixelShuffle<arma::mat, arma::mat>*,
     Softmax<arma::mat, arma::mat>*,
     SpatialDropout<arma::mat, arma::mat>*,
     TransposedConvolution<NaiveConvolution<ValidConvolution>,

From a2da41c0a0aaf38429b7cd06a7cb042a68aae003 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 12 Feb 2021 12:55:15 -0500
Subject: [PATCH 168/253] Update src/mlpack/methods/ann/layer/convolution.hpp

---
 src/mlpack/methods/ann/layer/convolution.hpp | 50 ++++++++++++--------
 1 file changed, 30 insertions(+), 20 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/convolution.hpp b/src/mlpack/methods/ann/layer/convolution.hpp
index 2ab22ddbfd..5459f34733 100644
--- a/src/mlpack/methods/ann/layer/convolution.hpp
+++ b/src/mlpack/methods/ann/layer/convolution.hpp
@@ -29,26 +29,36 @@ namespace ann /** Artificial Neural Network. */ {
 /**
  * Implementation of the Convolution class. The Convolution class represents a
  * single layer of a neural network.
- *Example about how to organize the input matrix of the CNN. Say that I pass a matrix M(2744x100) to model.Add<Convolution<>>, which I have obtained from "flattening" 
- *100 images (or Mel cepstral coefficients, if we talk about speech, or whatever you like) of dimension 196x14. In other words, the first 196 columns of each row of M 
- *will be made of the 196 columns of the first row of each of the 100 images (or Mel cepstral coefficients). Then the next 295 columns of M (196 - 393) will be made 
- *of the 196 columns of the second row of the 100 images (or Mel cepstral coefficients), etc. I want my input to be 196x14 for, so my add will be something like this:
- 
- *model.Add<Convolution<>>
- *(1, // Number of input activation maps.
-    *14, // Number of output activation maps.
-        *3, // Filter width.
-            *3, // Filter height.
-                *1, // Stride along width.
-                    *1, // Stride along height.
-                        *0, // Padding width.
-                            *0, // Padding height.
-                                *196, // Input width.
-                                    *14 // Input height.
-                                        *);
- *By doing so, will recreate the original 196x14 matrix for each image (or Mel cepstral coefficients) that will be used as input for the 14 filters of this example.
-
-* @tparam ForwardConvolutionRule Convolution to perform forward process.
+ * Example usage:
+ * 
+ * Suppose we want to pass a matrix M (2744x100) to a `Convolution` layer;
+ * in this example, `M` was obtained from "flattening" 100 images (or Mel
+ * cepstral coefficients, if we talk about speech, or whatever you like) of
+ * dimension 196x14. In other words, the first 196 columns of each row of M
+ * will be made of the 196 columns of the first row of each of the 100 images
+ * (or Mel cepstral coefficients). Then the next 295 columns of M (196 - 393)
+ * will be made of the 196 columns of the second row of the 100 images (or Mel
+ * cepstral coefficients), etc.  Given that the size of our 2-D input images is
+ * 196x14, the parameters for our `Convolution` layer will be something like
+ * this:
+ *
+ * ```
+ * Convolution<> c(1, // Number of input activation maps.
+ *                 14, // Number of output activation maps.
+ *                 3, // Filter width.
+ *                 3, // Filter height.
+ *                 1, // Stride along width.
+ *                 1, // Stride along height.
+ *                 0, // Padding width.
+ *                 0, // Padding height.
+ *                 196, // Input width.
+ *                 14); // Input height.
+ * ```
+ *
+ * This `Convolution<>` layer will treat each column of the input matrix `M` as  * a 2-D image (or object) of the original 196x14 size, using this as the input
+ * for the 14 filters of this example.
+ *
+ * @tparam ForwardConvolutionRule Convolution to perform forward process.
  * @tparam BackwardConvolutionRule Convolution to perform backward process.
  * @tparam GradientConvolutionRule Convolution to calculate gradient.
  * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,

From efcba7760369c835ad44a2a00105840081f0185a Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Sat, 13 Feb 2021 04:31:06 +0530
Subject: [PATCH 169/253] Update isrlu_impl.hpp

Use elementwise multiplication  while calculating `output(i)` and  used `output(i)` while calculating `derivative(i)`
---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 651f1f1a28..b69ffbf8bb 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -32,8 +32,8 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
   output = arma::ones<OutputDataType>(arma::size(input));
   for (size_t i = 0; i < input.n_elem; ++i)
   {
-    output(i) = (input(i) >= 0) ? input(i) : input(i) *
-                (1 / std::sqrt(1 + alpha*input(i)*input(i)));
+    output(i) = (input(i) >= 0) ? input(i) : input(i) %
+                (1 / std::sqrt(1 + alpha * (input(i) % input(i))));
   }
 
   if (!deterministic)
@@ -42,7 +42,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
     for (size_t i = 0; i < input.n_elem; ++i)
     {
       derivative(i) = (input(i) >= 0) ? 1 :
-          std::pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
+          std::pow(output(i), 3) / std::pow(input(i), 3);
     }
   }
 }

From 517a3a5e8d1ccfa75fa90e6e4e2239fa0494585b Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Sun, 14 Feb 2021 12:54:35 +0530
Subject: [PATCH 170/253] Added Hard Swish Function Implementation and Test
 Skeleton

---
 .../ann/activation_functions/CMakeLists.txt   |   1 +
 .../hard_swish_function.hpp                   | 116 ++++++++++++++++++
 .../tests/activation_functions_test.cpp       |  20 +++
 3 files changed, 137 insertions(+)
 create mode 100644 src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp

diff --git a/src/mlpack/methods/ann/activation_functions/CMakeLists.txt b/src/mlpack/methods/ann/activation_functions/CMakeLists.txt
index fd4e765006..d5c0868c1c 100644
--- a/src/mlpack/methods/ann/activation_functions/CMakeLists.txt
+++ b/src/mlpack/methods/ann/activation_functions/CMakeLists.txt
@@ -19,6 +19,7 @@ set(SOURCES
   multi_quadratic_function.hpp
   poisson1_function.hpp
   gaussian_function.hpp
+  hard_swish_function.hpp
 )
 
 # Add directory name to sources.
diff --git a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
new file mode 100644
index 0000000000..d3526da428
--- /dev/null
+++ b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
@@ -0,0 +1,116 @@
+/**
+ * @file methods/ann/activation_functions/hard_swish_function.hpp
+ * @author Anush Kini
+ *
+ * Definition and implementation of the Hard Swish function as described by
+ * Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R,
+ * Vasudevan V and Le QV.
+ * For more information, see the following paper.
+ *
+ * @code
+ * @misc{
+ *   author = {Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W,
+ *            Zhu Y, Pang R, Vasudevan V and Le QV},
+ *   title = {Searching for MobileNetV3},
+ *   year = {2019}
+ * }
+ * @endcode
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_METHODS_ANN_ACTIVATION_FUNCTIONS_HARD_SWISH_FUNCTION_HPP
+#define MLPACK_METHODS_ANN_ACTIVATION_FUNCTIONS_HARD_SWISH_FUNCTION_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace ann /** Artificial Neural Network. */ {
+/**
+ * The Hard Swish function, defined by
+ *
+ * @f{eqnarray*}{
+ *   f(x) &=& \begin{cases}
+ *     0 & x \leq -3\\
+ *     x & x \geq +3\\
+ *     \frac{x * (x + 3)}{6} & otherwise\\
+ *   \end{cases} \\
+ *   f'(x) &=& \begin{cases}
+ *     0 & x \leq -3\\
+ *     1 & x \geq +3\\
+ *     \frac{2x + 3}{6} & otherwise\\
+ *   \end{cases}
+ * @f}
+ */
+class HardSwishFunction
+{
+ public:
+  /**
+   * Computes the Hard Swish function.
+   *
+   * @param x Input data.
+   * @return f(x).
+   */
+  static double Fn(const double x)
+  {
+    double x2 = x + 3.0;
+    x2 = x2 > 0.0 ? x2 : 0.0;
+    x2 = x2 < 6.0 ? x2 : 6.0;
+    x2 = x * x2 / 6.0;
+
+    return x2;
+  }
+
+  /**
+   * Computes the Hard Swish function.
+   *
+   * @param x Input data.
+   * @param y The resulting output activation.
+   */
+  template <typename InputVecType, typename OutputVecType>
+  static void Fn(const InputVecType &x, OutputVecType &y)
+  {
+    y.set_size(size(x));
+
+    for (size_t i = 0; i < x.n_elem; i++)
+      y(i) = Fn(x(i));
+  }
+
+  /**
+   * Computes the first derivative of the Hard Swish function.
+   *
+   * @param y Input data.
+   * @return f'(x).
+   */
+  static double Deriv(const double y)
+  {
+    if (y <= -3)
+      return 0;
+    else if (y >= 3)
+      return 1;
+
+    return (2*y + 3.0)/6.0;
+  }
+
+  /**
+   * Computes the first derivatives of the Hard Swish function.
+   *
+   * @param y Input activations.
+   * @param x The resulting derivatives.
+   */
+  template <typename InputVecType, typename OutputVecType>
+  static void Deriv(const InputVecType &y, OutputVecType &x)
+  {
+    x.set_size(size(y));
+
+    for (size_t i = 0; i < y.n_elem; i++)
+      x(i) = Deriv(y(i));
+  }
+}; // class HardSwishFunction
+
+} // namespace ann
+} // namespace mlpack
+
+#endif
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index d88c0a5109..f99f9781e8 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -1134,3 +1134,23 @@ TEST_CASE("SoftminFunctionTest", "[ActivationFunctionsTest]")
   CheckSoftminDerivativeCorrect(activationData,
                                 desiredDerivatives);
 }
+
+/**
+ * Basic test of the Hard Swish function.
+ */
+TEST_CASE("HardSwishFunctionTest", "[ActivationFunctionsTest]")
+{
+  // Randomly generated data.
+  const arma::colvec activationData("3.6544 -1.9714 -5.2277 1.5448 2.1164");
+
+  // Calculated from torch.nn.Hardswish.
+  const arma::colvec desiredActivations("3.6544 -0.3380 0 1.1701 1.8047");
+
+  // Hand Calculated Values.
+  const arma::colvec desiredDerivatives("1 ");
+
+  CheckSoftminActivationCorrect(activationData,
+                                desiredActivations);
+  CheckSoftminDerivativeCorrect(activationData,
+                                desiredDerivatives);
+}

From 990803af2b4904279c49cd2374e13f2918be21f9 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Sun, 14 Feb 2021 19:31:57 +0530
Subject: [PATCH 171/253] Fixes for failing test

---
 src/mlpack/methods/ann/layer/base_layer.hpp    | 13 +++++++++++++
 src/mlpack/tests/activation_functions_test.cpp | 16 +++++++++-------
 2 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/base_layer.hpp b/src/mlpack/methods/ann/layer/base_layer.hpp
index 8429c818a7..ae49f30fe6 100644
--- a/src/mlpack/methods/ann/layer/base_layer.hpp
+++ b/src/mlpack/methods/ann/layer/base_layer.hpp
@@ -27,6 +27,7 @@
 #include <mlpack/methods/ann/activation_functions/elliot_function.hpp>
 #include <mlpack/methods/ann/activation_functions/elish_function.hpp>
 #include <mlpack/methods/ann/activation_functions/gaussian_function.hpp>
+#include <mlpack/methods/ann/activation_functions/hard_swish_function.hpp>
 
 namespace mlpack {
 namespace ann /** Artificial Neural Network. */ {
@@ -50,6 +51,7 @@ namespace ann /** Artificial Neural Network. */ {
  *  - ELiSHLayer
  *  - ElliotLayer
  *  - GaussianLayer
+ *  - HardSwishLayer
  *
  * @tparam ActivationFunction Activation function used for the embedding layer.
  * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
@@ -277,6 +279,17 @@ template <
 using GaussianFunctionLayer = BaseLayer<
     ActivationFunction, InputDataType, OutputDataType>;
 
+/**
+ * Standard HardSwish-Layer using the HardSwish activation function.
+ */
+template <
+    class ActivationFunction = HardSwishFunction,
+    typename InputDataType = arma::mat,
+    typename OutputDataType = arma::mat
+>
+using HardSwishFunctionLayer = BaseLayer<
+    ActivationFunction, InputDataType, OutputDataType>;
+
 } // namespace ann
 } // namespace mlpack
 
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index f99f9781e8..56682880da 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -32,6 +32,7 @@
 #include <mlpack/methods/ann/activation_functions/spline_function.hpp>
 #include <mlpack/methods/ann/activation_functions/poisson1_function.hpp>
 #include <mlpack/methods/ann/activation_functions/gaussian_function.hpp>
+#include <mlpack/methods/ann/activation_functions/hard_swish_function.hpp>
 
 #include "catch.hpp"
 
@@ -1143,14 +1144,15 @@ TEST_CASE("HardSwishFunctionTest", "[ActivationFunctionsTest]")
   // Randomly generated data.
   const arma::colvec activationData("3.6544 -1.9714 -5.2277 1.5448 2.1164");
 
-  // Calculated from torch.nn.Hardswish.
-  const arma::colvec desiredActivations("3.6544 -0.3380 0 1.1701 1.8047");
+  // Hand Calculated Values. from torch.nn.Hardswish.
+  const arma::colvec desiredActivations("3.6544 -0.3379636 0.0 \
+                                         1.1701345 1.8047248");
 
   // Hand Calculated Values.
-  const arma::colvec desiredDerivatives("1 ");
+  const arma::colvec desiredDerivatives("1.0 0.38734546 0.5 \
+                                         0.89004483 1.1015749");
 
-  CheckSoftminActivationCorrect(activationData,
-                                desiredActivations);
-  CheckSoftminDerivativeCorrect(activationData,
-                                desiredDerivatives);
+  CheckActivationCorrect<HardSwishFunction>(activationData, desiredActivations);
+  CheckDerivativeCorrect<HardSwishFunction>
+      (desiredActivations, desiredDerivatives);
 }

From 665c750e1f56a12cf014eac180b1862a9b9efaa1 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Sun, 14 Feb 2021 22:48:25 +0530
Subject: [PATCH 172/253] Some more comment fixes

---
 .../methods/ann/activation_functions/hard_swish_function.hpp    | 2 +-
 src/mlpack/tests/activation_functions_test.cpp                  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
index d3526da428..f2780aac6e 100644
--- a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
+++ b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
@@ -97,7 +97,7 @@ class HardSwishFunction
   /**
    * Computes the first derivatives of the Hard Swish function.
    *
-   * @param y Input activations.
+   * @param y Input data.
    * @param x The resulting derivatives.
    */
   template <typename InputVecType, typename OutputVecType>
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index 56682880da..20631566e9 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -1144,7 +1144,7 @@ TEST_CASE("HardSwishFunctionTest", "[ActivationFunctionsTest]")
   // Randomly generated data.
   const arma::colvec activationData("3.6544 -1.9714 -5.2277 1.5448 2.1164");
 
-  // Hand Calculated Values. from torch.nn.Hardswish.
+  // Hand Calculated Values.
   const arma::colvec desiredActivations("3.6544 -0.3379636 0.0 \
                                          1.1701345 1.8047248");
 

From 7b70a820f8511d58ecfabcbcca71b14732ca585b Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Mon, 15 Feb 2021 02:37:02 +0530
Subject: [PATCH 173/253] Code  style fix

Co-authored-by: kartikdutt18 <39593019+kartikdutt18@users.noreply.github.com>
---
 src/mlpack/methods/ann/layer/pixel_shuffle.hpp      |  1 +
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 13 ++++---------
 2 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
index c62b0f0ecb..48d89c2fe2 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
@@ -50,6 +50,7 @@ class PixelShuffle
  public:
   //! Create the PixelShuffle object.
   PixelShuffle();
+
   /**
    * Create the PixelShuffle object using the specified parameters.
    * The number of input channels should be an integral multiple of the square
diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 17c7c93980..9edb09c2eb 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -20,15 +20,7 @@ namespace ann /** Artificial Neural Network. */ {
 
 template<typename InputDataType, typename OutputDataType>
 PixelShuffle<InputDataType, OutputDataType>::PixelShuffle() :
-    upscaleFactor(0),
-    height(0),
-    width(0),
-    size(0),
-    batchSize(0),
-    outputHeight(0),
-    outputWidth(0),
-    sizeOut(0),
-    reset(false)
+    PixelShuffle(0, 0, 0, 0)
 {
   // Nothing to do here.
 }
@@ -65,6 +57,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
     outputWidth = width * upscaleFactor;
     reset = true;
   }
+
   output.zeros(outputHeight * outputWidth * sizeOut, batchSize);
   for (size_t n = 0; n < batchSize; n++)
   {
@@ -90,6 +83,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
         }
       }
     }
+
     output.col(n) = outputImage;
   }
 }
@@ -123,6 +117,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
         }
       }
     }
+
     g.col(n) = gImage;
   }
 }

From 3856cdd00ca20995a06d0f16a20935fde538b60e Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Mon, 15 Feb 2021 10:03:06 +0530
Subject: [PATCH 174/253] Review fixes

---
 .../methods/ann/activation_functions/hard_swish_function.hpp  | 2 +-
 src/mlpack/tests/activation_functions_test.cpp                | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
index f2780aac6e..d308358f31 100644
--- a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
+++ b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
@@ -91,7 +91,7 @@ class HardSwishFunction
     else if (y >= 3)
       return 1;
 
-    return (2*y + 3.0)/6.0;
+    return (2 * y + 3.0) / 6.0;
   }
 
   /**
diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index 20631566e9..5e4c5aa217 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -1144,11 +1144,11 @@ TEST_CASE("HardSwishFunctionTest", "[ActivationFunctionsTest]")
   // Randomly generated data.
   const arma::colvec activationData("3.6544 -1.9714 -5.2277 1.5448 2.1164");
 
-  // Hand Calculated Values.
+  // Hand-calculated values.
   const arma::colvec desiredActivations("3.6544 -0.3379636 0.0 \
                                          1.1701345 1.8047248");
 
-  // Hand Calculated Values.
+  // Hand-calculated values.
   const arma::colvec desiredDerivatives("1.0 0.38734546 0.5 \
                                          0.89004483 1.1015749");
 

From 0fe77567948df2aaa1ce711003c2fcdefc49d8cc Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Mon, 15 Feb 2021 10:24:01 +0530
Subject: [PATCH 175/253] Update isrlu_impl.hpp

---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index b69ffbf8bb..8ee468849f 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -33,7 +33,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
   for (size_t i = 0; i < input.n_elem; ++i)
   {
     output(i) = (input(i) >= 0) ? input(i) : input(i) %
-                (1 / std::sqrt(1 + alpha * (input(i) % input(i))));
+                (1 / arma::sqrt(1 + alpha * (input(i) % input(i))));
   }
 
   if (!deterministic)
@@ -42,7 +42,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
     for (size_t i = 0; i < input.n_elem; ++i)
     {
       derivative(i) = (input(i) >= 0) ? 1 :
-          std::pow(output(i), 3) / std::pow(input(i), 3);
+          arma::pow(output(i), 3) / arma::pow(input(i), 3);
     }
   }
 }

From e29da13c01d03986dff8f9ef3d502ba48e294362 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Mon, 15 Feb 2021 16:33:30 -0500
Subject: [PATCH 176/253] Update src/mlpack/methods/ann/layer/convolution.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/methods/ann/layer/convolution.hpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/convolution.hpp b/src/mlpack/methods/ann/layer/convolution.hpp
index 5459f34733..5ea92f37ea 100644
--- a/src/mlpack/methods/ann/layer/convolution.hpp
+++ b/src/mlpack/methods/ann/layer/convolution.hpp
@@ -55,7 +55,8 @@ namespace ann /** Artificial Neural Network. */ {
  *                 14); // Input height.
  * ```
  *
- * This `Convolution<>` layer will treat each column of the input matrix `M` as  * a 2-D image (or object) of the original 196x14 size, using this as the input
+ * This `Convolution<>` layer will treat each column of the input matrix `M` as
+ * a 2-D image (or object) of the original 196x14 size, using this as the input
  * for the 14 filters of this example.
  *
  * @tparam ForwardConvolutionRule Convolution to perform forward process.

From 48deeeb3a6b35cf6c5b14913bc3b2bf915eb834c Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 16 Feb 2021 04:36:30 +0530
Subject: [PATCH 177/253] Changes % to *

---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 8ee468849f..5d73ce0710 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -32,8 +32,8 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
   output = arma::ones<OutputDataType>(arma::size(input));
   for (size_t i = 0; i < input.n_elem; ++i)
   {
-    output(i) = (input(i) >= 0) ? input(i) : input(i) %
-                (1 / arma::sqrt(1 + alpha * (input(i) % input(i))));
+    output(i) = (input(i) >= 0) ? input(i) : input(i) *
+                (1 / std::sqrt(1 + alpha * (input(i) * input(i))));
   }
 
   if (!deterministic)
@@ -42,7 +42,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
     for (size_t i = 0; i < input.n_elem; ++i)
     {
       derivative(i) = (input(i) >= 0) ? 1 :
-          arma::pow(output(i), 3) / arma::pow(input(i), 3);
+          std::pow(output(i), 3) / std::pow(input(i), 3);
     }
   }
 }

From f9fbf4d9b51151f9e92cf892eba2bd483c114ebe Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Wed, 17 Feb 2021 03:21:43 +0530
Subject: [PATCH 178/253] Removed space.

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 5d73ce0710..5e08aaa707 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -33,7 +33,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
   for (size_t i = 0; i < input.n_elem; ++i)
   {
     output(i) = (input(i) >= 0) ? input(i) : input(i) *
-                (1 / std::sqrt(1 + alpha * (input(i) * input(i))));
+        (1 / std::sqrt(1 + alpha * (input(i) * input(i))));
   }
 
   if (!deterministic)

From 1994c4fc419e0623938039389fba90e571e56940 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Thu, 18 Feb 2021 11:15:15 +0530
Subject: [PATCH 179/253] Fn implementation changed to if else statements

---
 .../ann/activation_functions/hard_swish_function.hpp   | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
index d308358f31..d387e86474 100644
--- a/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
+++ b/src/mlpack/methods/ann/activation_functions/hard_swish_function.hpp
@@ -55,12 +55,12 @@ class HardSwishFunction
    */
   static double Fn(const double x)
   {
-    double x2 = x + 3.0;
-    x2 = x2 > 0.0 ? x2 : 0.0;
-    x2 = x2 < 6.0 ? x2 : 6.0;
-    x2 = x * x2 / 6.0;
+    if (x <= -3)
+      return 0;
+    else if (x >= 3)
+      return x;
 
-    return x2;
+    return x * (x + 3) / 6;
   }
 
   /**

From f6b626d7178716d2f414647586aabddf223fb43e Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Fri, 19 Feb 2021 03:13:49 +0530
Subject: [PATCH 180/253]  Moved  derivative to  backward

---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 5e08aaa707..fc022929ad 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -35,16 +35,6 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
     output(i) = (input(i) >= 0) ? input(i) : input(i) *
         (1 / std::sqrt(1 + alpha * (input(i) * input(i))));
   }
-
-  if (!deterministic)
-  {
-    derivative.set_size(arma::size(input));
-    for (size_t i = 0; i < input.n_elem; ++i)
-    {
-      derivative(i) = (input(i) >= 0) ? 1 :
-          std::pow(output(i), 3) / std::pow(input(i), 3);
-    }
-  }
 }
 
 template<typename InputDataType, typename OutputDataType>
@@ -52,6 +42,15 @@ template<typename DataType>
 void ISRLU<InputDataType, OutputDataType>::Backward(
     const DataType& /* input */, const DataType& gy, DataType& g)
 {
+  if (!deterministic)
+  {
+    derivative.set_size(arma::size(input));
+    for (size_t i = 0; i < input.n_elem; ++i)
+    {
+      derivative(i) = (input(i) >= 0) ? 1 :
+          std::pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
+    }
+  }
   g = gy % derivative;
 }
 

From 4394e99151cb05d4d45a0e5fb507396035c5d3fb Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Fri, 19 Feb 2021 03:15:22 +0530
Subject: [PATCH 181/253] minor change

---
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index fc022929ad..57f196b3fe 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -40,7 +40,7 @@ void ISRLU<InputDataType, OutputDataType>::Forward(
 template<typename InputDataType, typename OutputDataType>
 template<typename DataType>
 void ISRLU<InputDataType, OutputDataType>::Backward(
-    const DataType& /* input */, const DataType& gy, DataType& g)
+    const DataType& input, const DataType& gy, DataType& g)
 {
   if (!deterministic)
   {

From f7289b8fd7ae085f87c5c1503c0971608f925f28 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Fri, 19 Feb 2021 21:37:53 +0530
Subject: [PATCH 182/253] Integrated Anush's Code

---
 src/mlpack/core/data/split_data.hpp  | 93 +++++++++-------------------
 src/mlpack/tests/split_data_test.cpp | 45 +++-----------
 2 files changed, 37 insertions(+), 101 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index e9358d23c9..5d8c6aa720 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -23,6 +23,8 @@ namespace data {
  * It is recommended to have the input labels between the range [0, n) where n
  * is the number of different labels. The NormalizeLabels() function in
  * mlpack::data can be used for this.
+ * Expects labels to be of type arma::Row<>.
+ * Throws a runtime error if this is not the case.
  * Example usage below. This overload places the stratified dataset into the
  * four output parameters given (trainData, testData, trainLabel,
  * and testLabel).
@@ -52,56 +54,27 @@ namespace data {
  * @param shuffleData If true, the sample order is shuffled; otherwise, each
  *     sample is visited in linear order. (Default true.)
  */
-template<typename T, typename U>
+template<typename T, typename LabelsType,
+         typename = std::enable_if_t<arma::is_arma_type<LabelsType>::value> >
 void StratifiedSplit(const arma::Mat<T>& input,
-                     const arma::Row<U>& inputLabel,
+                     const LabelsType& inputLabel,
                      arma::Mat<T>& trainData,
                      arma::Mat<T>& testData,
-                     arma::Row<U>& trainLabel,
-                     arma::Row<U>& testLabel,
+                     LabelsType& trainLabel,
+                     LabelsType& testLabel,
                      const double testRatio,
                      const bool shuffleData = true)
 {
-  /**
-   * Basic idea:
-   * Let us say we have to stratify a dataset based on labels:
-   * 0 0 0 0 0 (5 0s)
-   * 1 1 1 1 1 1 1 1 1 1 1 (11 1s)
-   *
-   * Let our test ratio be 0.2.
-   * Then, the number of 0 labels in our test set = floor(5 * 0.2) = 1.
-   * The number of 1 labels in our test set = floor(11 * 0.2) = 2.
-   *
-   * In our first pass over the dataset,
-   * We visit each label and keep count of each label in our 'labelCounts' uvec.
-   *
-   * We then take a second pass over the dataset.
-   * We now maintain an additional uvec 'testLabelCounts' to hold the label
-   * counts of our test set.
-   *
-   * In this pass, when we encounter a label we check the 'testLabelCounts' uvec
-   * for the count of this label in the test set.
-   * If this count is less than the required number of labels in the test set,
-   * we add the data to the test set and increment the label count in the uvec.
-   * If this count is equal to or more than the required count in the test set,
-   * we add this data to the train set.
-   *
-   * Based on the above steps, we get the following labels in the split set:
-   * Train set (4 0s, 9 1s)
-   * 0 0 0 0
-   * 1 1 1 1 1 1 1 1 1
-   *
-   * Test set (1 0s, 2 1s)
-   * 0
-   * 1 1
-   */
+  if (!arma::is_Row<LabelsType>::value)
+    throw std::runtime_error("data::Split(): when stratified sampling is done,"
+        "labels must have type `arma::Row<>`!");
   size_t trainIdx = 0;
   size_t testIdx = 0;
   size_t trainSize = 0;
   size_t testSize = 0;
   arma::uvec labelCounts;
   arma::uvec testLabelCounts;
-  U maxLabel = inputLabel.max();
+  auto maxLabel = inputLabel.max();
 
   labelCounts.zeros(maxLabel+1);
   testLabelCounts.zeros(maxLabel+1);
@@ -114,7 +87,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
     order = arma::shuffle(order);
   }
 
-  for (U label : inputLabel)
+  for (auto label : inputLabel)
   {
     ++labelCounts[label];
   }
@@ -132,7 +105,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
 
   for (arma::uword i : order)
   {
-    U label = inputLabel[i];
+    auto label = inputLabel[i];
     if (testLabelCounts[label] < floor(labelCounts[label] * testRatio))
     {
       testLabelCounts[label] += 1;
@@ -197,36 +170,26 @@ void Split(const arma::Mat<T>& input,
   const size_t trainSize = input.n_cols - testSize;
   trainData.set_size(input.n_rows, trainSize);
   testData.set_size(input.n_rows, testSize);
-  trainLabel.set_size(trainSize);
-  testLabel.set_size(testSize);
 
+  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
+      input.n_cols);
   if (shuffleData)
   {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(
-        0, input.n_cols - 1, input.n_cols));
-    if (trainSize > 0)
-    {
-      trainData = input.cols(order.subvec(0, trainSize - 1));
-      trainLabel = inputLabel.cols(order.subvec(0, trainSize - 1));
-    }
-    if (trainSize < input.n_cols)
-    {
-    testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
-    testLabel = inputLabel.cols(order.subvec(trainSize, input.n_cols - 1));
-    }
+    trainLabel.set_size(1, trainSize);
+    trainData = input.cols(order.subvec(0, trainSize - 1));
+
+    for (size_t i = 0; i < trainSize; i++)
+      trainLabel(0, i) = inputLabel(0, order(i));
   }
   else
+
+  if (trainSize < input.n_cols)
   {
-    if (trainSize > 0)
-    {
-      trainData = input.cols(0, trainSize - 1);
-      trainLabel = inputLabel.subvec(0, trainSize - 1);
-    }
-    if (trainSize < input.n_cols)
-    {
-      testData = input.cols(trainSize , input.n_cols - 1);
-      testLabel = inputLabel.subvec(trainSize , input.n_cols - 1);
-    }
+    testLabel.set_size(1, testSize);
+    testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
+
+    for (size_t i = trainSize; i < input.n_cols; i++)
+      testLabel(0, i - trainSize) = inputLabel(0, order(i));
   }
 }
 
@@ -309,7 +272,7 @@ void Split(const arma::Mat<T>& input,
  *     sample is visited in linear order. (Default true).
  * @param stratifyData If true, the train and test splits are stratified
  *     so that the ratio of each class in the training and test sets is the same
- *     as in the original dataset.
+ *     as in the original dataset. Expects labels to be of type arma::Row<>.
  * @return std::tuple containing trainData (arma::Mat<T>), testData
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */
diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index d3d445796e..41227097f3 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -322,47 +322,20 @@ TEST_CASE("StratifiedSplitDataResultTest", "[SplitDataTest]")
   CheckMatEqual(input, concat);
 }
 
+
 /**
- * Check if data is stratified according to labels on a larger data set.
- * Example calculation to find resultant number of samples in the train and
- * test set:
- *
- * Since there are 256 0s and the test ratio is 0.3,
- * Number of 0s in the test set = 76 ( floor(256 * 0.3) = floor(76.8) ).
- * Number of 0s in the train set = 180 ( 256 - 76 ).
+ * Check that Split() with stratifyData true throws a runtime error if labels
+ * are not of type arma::Row<>.
  */
-TEST_CASE("StratifiedSplitLargerDataResultTest", "[SplitDataTest]")
+TEST_CASE("StratifiedSplitRunTimeErrorTest", "[SplitDataTest]")
 {
   mat input(3, 480);
+  mat labels(2, 480);
   input.randu();
+  labels.randu();
 
-  // 256 0s, 128 1s, 64 2s and 32 3s.
-  Row<size_t> zero_label(256);
-  Row<size_t> one_label(128);
-  Row<size_t> two_label(64);
-  Row<size_t> three_label(32);
-
-  zero_label.fill(0);
-  one_label.fill(1);
-  two_label.fill(2);
-  three_label.fill(3);
-
-  Row<size_t> labels = arma::join_rows(zero_label, one_label);
-  labels = arma::join_rows(labels, two_label);
-  labels = arma::join_rows(labels, three_label);
   const double test_ratio = 0.3;
 
-  const auto value = Split(input, labels, test_ratio, false, true);
-  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 0)).n_rows == 180);
-  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 1)).n_rows == 90);
-  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 2)).n_rows == 45);
-  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 3)).n_rows == 23);
-
-  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 0)).n_rows == 76);
-  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 1)).n_rows == 38);
-  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 2)).n_rows == 19);
-  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 3)).n_rows == 9);
-
-  mat concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
-  CheckMatEqual(input, concat);
-}
+  REQUIRE_THROWS_AS(Split(input, labels, test_ratio, false, true),
+      std::runtime_error);
+}
\ No newline at end of file

From 00778322a60661555cb8200d45e28e218df59528 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Sat, 20 Feb 2021 16:59:18 +0530
Subject: [PATCH 183/253] Fixed errors and added the accidentally removed
 testcase

---
 src/mlpack/core/data/split_data.hpp  | 23 +++++++++--------
 src/mlpack/tests/split_data_test.cpp | 38 ++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 5d8c6aa720..a4d10e389d 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -1,3 +1,4 @@
+
 /**
  * @file core/data/split_data.hpp
  * @author Tham Ngap Wei, Keon Kim
@@ -174,6 +175,9 @@ void Split(const arma::Mat<T>& input,
   arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
       input.n_cols);
   if (shuffleData)
+    order = arma::shuffle(order);
+
+  if (trainSize > 0)
   {
     trainLabel.set_size(1, trainSize);
     trainData = input.cols(order.subvec(0, trainSize - 1));
@@ -181,7 +185,6 @@ void Split(const arma::Mat<T>& input,
     for (size_t i = 0; i < trainSize; i++)
       trainLabel(0, i) = inputLabel(0, order(i));
   }
-  else
 
   if (trainSize < input.n_cols)
   {
@@ -346,7 +349,7 @@ Split(const arma::Mat<T>& input,
  *
  * The input dataset must be of type arma::field. It should have the shape -
  * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
- * 
+ *
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
  * @code
@@ -385,7 +388,7 @@ void Split(FieldType& input,
            FieldType& testData,
            arma::field<arma::vec>& testLabels,
            const double testRatio,
-           const bool shuffleData = true) 
+           const bool shuffleData = true)
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
@@ -406,7 +409,7 @@ void Split(FieldType& input,
       trainData[i] = input(0, order(i));
 
     for (size_t i = 0; i < trainSize; i++)
-      trainLabels(0, i) = inputLabel[i];
+      trainLabels(0, i) = inputLabel(0, order(i));
   }
 
   if (testSize <= input.n_cols)
@@ -416,7 +419,7 @@ void Split(FieldType& input,
 
     testLabels.set_size(1, testSize);
     for (size_t i = trainSize; i < input.n_cols; i++)
-      testLabels(0, i - trainSize) = inputLabel[i];
+      testLabels(0, i - trainSize) = inputLabel(0, order(i));
   }
 }
 
@@ -427,7 +430,7 @@ void Split(FieldType& input,
  *
  * The input dataset must be of type arma::field. It should have the shape -
  * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
- * 
+ *
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
  * @code
@@ -491,7 +494,7 @@ void Split(const FieldType& input,
  *
  * The input dataset must be of type arma::field. It should have the shape -
  * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
- * 
+ *
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
  * @code
@@ -506,7 +509,7 @@ void Split(const FieldType& input,
  * @param shuffleData If true, the sample order is shuffled; otherwise, each
  *       sample is visited in linear order. (Default true).
  * @return std::tuple containing trainData (FieldType), testData
- *      (FieldType), trainLabel (arma::field<arma::vec>), and 
+ *      (FieldType), trainLabel (arma::field<arma::vec>), and
  *                   testLabel (arma::field<arma::vec>).
  */
 template <class FieldType,
@@ -541,7 +544,7 @@ Split(FieldType& input,
  *
  * The input dataset must be of type arma::field. It should have the shape -
  * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
- * 
+ *
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *
  * @code
@@ -576,4 +579,4 @@ Split(const FieldType& input,
 } // namespace data
 } // namespace mlpack
 
-#endif
+#endif
\ No newline at end of file
diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 41227097f3..f6136b8d99 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -322,6 +322,44 @@ TEST_CASE("StratifiedSplitDataResultTest", "[SplitDataTest]")
   CheckMatEqual(input, concat);
 }
 
+/**
+ * Check if data is stratified according to labels on a larger data set.
+ * Example calculation to find resultant number of samples in the train and
+ * test set:
+ *
+ * Since there are 256 0s and the test ratio is 0.3,
+ * Number of 0s in the test set = 76 ( floor(256 * 0.3) = floor(76.8) ).
+ * Number of 0s in the train set = 180 ( 256 - 76 ).
+ */
+TEST_CASE("StratifiedSplitLargerDataResultTest", "[SplitDataTest]")
+{
+  mat input(3, 480);
+  input.randu();
+  // 256 0s, 128 1s, 64 2s and 32 3s.
+  Row<size_t> zero_label(256);
+  Row<size_t> one_label(128);
+  Row<size_t> two_label(64);
+  Row<size_t> three_label(32);
+  zero_label.fill(0);
+  one_label.fill(1);
+  two_label.fill(2);
+  three_label.fill(3);
+  Row<size_t> labels = arma::join_rows(zero_label, one_label);
+  labels = arma::join_rows(labels, two_label);
+  labels = arma::join_rows(labels, three_label);
+  const double test_ratio = 0.3;
+  const auto value = Split(input, labels, test_ratio, false, true);
+  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 0)).n_rows == 180);
+  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 1)).n_rows == 90);
+  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 2)).n_rows == 45);
+  REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 3)).n_rows == 23);
+  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 0)).n_rows == 76);
+  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 1)).n_rows == 38);
+  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 2)).n_rows == 19);
+  REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 3)).n_rows == 9);
+  mat concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
+  CheckMatEqual(input, concat);
+}
 
 /**
  * Check that Split() with stratifyData true throws a runtime error if labels

From dfd5f142d80480d4c19f088e832689cca3c8f0eb Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Sun, 21 Feb 2021 20:37:58 +0530
Subject: [PATCH 184/253]      fixed test case

---
 src/mlpack/tests/activation_functions_test.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/activation_functions_test.cpp b/src/mlpack/tests/activation_functions_test.cpp
index 642aa84dc4..2a64068891 100644
--- a/src/mlpack/tests/activation_functions_test.cpp
+++ b/src/mlpack/tests/activation_functions_test.cpp
@@ -1052,7 +1052,7 @@ TEST_CASE("ISRLUFunctionTest", "[ActivationFunctionsTest]")
                                          0.54433105 1 1");
 
   CheckISRLUActivationCorrect(activationData, desiredActivations);
-  CheckISRLUDerivativeCorrect(desiredActivations, desiredDerivatives);
+  CheckISRLUDerivativeCorrect(activationData, desiredDerivatives);
 }
 
 /**

From fd201b7d5e31e538af573a35731c98bff74f7948 Mon Sep 17 00:00:00 2001
From: Abhinav Anand <abhinav.anand2807@gmail.com>
Date: Mon, 22 Feb 2021 06:38:37 +0530
Subject: [PATCH 185/253] removed deterministic parameter and improved co

---
 src/mlpack/methods/ann/layer/isrlu.hpp      |  8 --------
 src/mlpack/methods/ann/layer/isrlu_impl.hpp | 14 +++++---------
 2 files changed, 5 insertions(+), 17 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu.hpp b/src/mlpack/methods/ann/layer/isrlu.hpp
index 7d8eda954b..b0a786c6ba 100644
--- a/src/mlpack/methods/ann/layer/isrlu.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu.hpp
@@ -47,7 +47,6 @@ namespace ann /** Artificial Neural Network. */ {
  * \right. 
  * @f}
  *
- * In the deterministic mode, there is no computation of the derivative.
  *
  * @tparam InputDataType Type of the input data (arma::colvec, arma::mat,
  *         arma::sp_mat or arma::cube).
@@ -106,11 +105,6 @@ class ISRLU
   //! Modify the non zero gradient.
   double& Alpha() { return alpha; }
 
-  //! Get the value of deterministic parameter.
-  bool Deterministic() const { return deterministic; }
-  //! Modify the value of deterministic parameter.
-  bool& Deterministic() { return deterministic; }
-
   //! Get size of weights.
   size_t WeightSize() { return 0; }
 
@@ -133,8 +127,6 @@ class ISRLU
   //! ISRLU Hyperparameter (alpha > 0).
   double alpha;
 
-  //! If true the derivative computation is disabled, see notes above.
-  bool deterministic;
 }; // class ISRLU
 
 } // namespace ann
diff --git a/src/mlpack/methods/ann/layer/isrlu_impl.hpp b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
index 57f196b3fe..a91830f51d 100644
--- a/src/mlpack/methods/ann/layer/isrlu_impl.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu_impl.hpp
@@ -20,8 +20,7 @@ namespace ann /** Artificial Neural Network. */ {
 
 template<typename InputDataType, typename OutputDataType>
 ISRLU<InputDataType, OutputDataType>::ISRLU(const double alpha) :
-    alpha(alpha),
-    deterministic(false)
+    alpha(alpha)
 {}
 
 template<typename InputDataType, typename OutputDataType>
@@ -42,14 +41,11 @@ template<typename DataType>
 void ISRLU<InputDataType, OutputDataType>::Backward(
     const DataType& input, const DataType& gy, DataType& g)
 {
-  if (!deterministic)
+  derivative.set_size(arma::size(input));
+  for (size_t i = 0; i < input.n_elem; ++i)
   {
-    derivative.set_size(arma::size(input));
-    for (size_t i = 0; i < input.n_elem; ++i)
-    {
-      derivative(i) = (input(i) >= 0) ? 1 :
-          std::pow(1 / std::sqrt(1 + alpha*input(i)*input(i)), 3);
-    }
+    derivative(i) = (input(i) >= 0) ? 1 :
+        std::pow(1 / std::sqrt(1 + alpha * input(i) * input(i)), 3);
   }
   g = gy % derivative;
 }

From a2db3c92ed682f49d2a4360bf27b42fcb1607dd8 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Mon, 22 Feb 2021 18:26:45 +0530
Subject: [PATCH 186/253] Apply suggestions from code review

Co-authored-by: Anush Kini <33577829+Abilityguy@users.noreply.github.com>
Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/data/split_data.hpp  | 26 +++++++++++++-------------
 src/mlpack/tests/split_data_test.cpp |  3 +--
 2 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index a4d10e389d..f4a75d871b 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -1,4 +1,3 @@
-
 /**
  * @file core/data/split_data.hpp
  * @author Tham Ngap Wei, Keon Kim
@@ -67,7 +66,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
                      const bool shuffleData = true)
 {
   if (!arma::is_Row<LabelsType>::value)
-    throw std::runtime_error("data::Split(): when stratified sampling is done,"
+    throw std::runtime_error("data::Split(): when stratified sampling is done, "
         "labels must have type `arma::Row<>`!");
   size_t trainIdx = 0;
   size_t testIdx = 0;
@@ -75,7 +74,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
   size_t testSize = 0;
   arma::uvec labelCounts;
   arma::uvec testLabelCounts;
-  auto maxLabel = inputLabel.max();
+  typename LabelsType::elem_type maxLabel = inputLabel.max();
 
   labelCounts.zeros(maxLabel+1);
   testLabelCounts.zeros(maxLabel+1);
@@ -88,7 +87,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
     order = arma::shuffle(order);
   }
 
-  for (auto label : inputLabel)
+  for (typename LabelsType::elem_type label : inputLabel)
   {
     ++labelCounts[label];
   }
@@ -106,7 +105,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
 
   for (arma::uword i : order)
   {
-    auto label = inputLabel[i];
+    typename LabelsType::elem_type label = inputLabel[i];
     if (testLabelCounts[label] < floor(labelCounts[label] * testRatio))
     {
       testLabelCounts[label] += 1;
@@ -182,7 +181,7 @@ void Split(const arma::Mat<T>& input,
     trainLabel.set_size(1, trainSize);
     trainData = input.cols(order.subvec(0, trainSize - 1));
 
-    for (size_t i = 0; i < trainSize; i++)
+    for (size_t i = 0; i < trainSize; ++i)
       trainLabel(0, i) = inputLabel(0, order(i));
   }
 
@@ -191,7 +190,7 @@ void Split(const arma::Mat<T>& input,
     testLabel.set_size(1, testSize);
     testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
 
-    for (size_t i = trainSize; i < input.n_cols; i++)
+    for (size_t i = trainSize; i < input.n_cols; ++i)
       testLabel(0, i - trainSize) = inputLabel(0, order(i));
   }
 }
@@ -398,6 +397,7 @@ void Split(FieldType& input,
 
   arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
       input.n_cols);
+
   if (shuffleData)
     order = arma::shuffle(order);
 
@@ -405,20 +405,20 @@ void Split(FieldType& input,
   {
     trainLabels.set_size(1, trainSize);
 
-    for (size_t i = 0; i < trainSize; i++)
+    for (size_t i = 0; i < trainSize; ++i)
       trainData[i] = input(0, order(i));
 
-    for (size_t i = 0; i < trainSize; i++)
+    for (size_t i = 0; i < trainSize; ++i)
       trainLabels(0, i) = inputLabel(0, order(i));
   }
 
   if (testSize <= input.n_cols)
   {
-    for (size_t i = trainSize; i < input.n_cols - 1; i++)
+    for (size_t i = trainSize; i < input.n_cols - 1; ++i)
      testData[i - trainSize] = input(0, order(i));
 
     testLabels.set_size(1, testSize);
-    for (size_t i = trainSize; i < input.n_cols; i++)
+    for (size_t i = trainSize; i < input.n_cols; ++i)
       testLabels(0, i - trainSize) = inputLabel(0, order(i));
   }
 }
@@ -480,7 +480,7 @@ void Split(const FieldType& input,
 
   if (testSize <= input.n_cols)
   {
-    for (size_t i = trainSize; i < input.n_cols - 1; i++)
+    for (size_t i = trainSize; i < input.n_cols - 1; ++i)
        testData[i - trainSize] = input(0, order(i));
   }
 }
@@ -579,4 +579,4 @@ Split(const FieldType& input,
 } // namespace data
 } // namespace mlpack
 
-#endif
\ No newline at end of file
+#endif
diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index f6136b8d99..74862469ba 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -144,7 +144,6 @@ TEST_CASE("SplitDataResultField", "[SplitDataTest]")
   CheckFields(input, concat);
 }
 
-
 TEST_CASE("ZeroRatioSplitData", "[SplitDataTest]")
 {
   mat input(2, 10);
@@ -376,4 +375,4 @@ TEST_CASE("StratifiedSplitRunTimeErrorTest", "[SplitDataTest]")
 
   REQUIRE_THROWS_AS(Split(input, labels, test_ratio, false, true),
       std::runtime_error);
-}
\ No newline at end of file
+}

From 1b2ffe201f9139a4dc91c01fcadaee66ebdc56f4 Mon Sep 17 00:00:00 2001
From: Heisenbuug <deathcoderx@gmail.com>
Date: Mon, 22 Feb 2021 19:08:50 +0530
Subject: [PATCH 187/253] Checking

---
 .../tests/feedforward_network_2_test.cpp      | 33 ++++++++++---------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_2_test.cpp b/src/mlpack/tests/feedforward_network_2_test.cpp
index 456367912c..104561cf03 100644
--- a/src/mlpack/tests/feedforward_network_2_test.cpp
+++ b/src/mlpack/tests/feedforward_network_2_test.cpp
@@ -31,12 +31,12 @@ using namespace mlpack::kmeans;
 /**
  * Train and evaluate a model with the specified structure.
  */
-template<typename MatType = arma::mat, typename ModelType>
-void TestNetwork(ModelType& model,
-                 MatType& trainData,
-                 MatType& trainLabels,
-                 MatType& testData,
-                 MatType& testLabels,
+template <typename MatType = arma::mat, typename ModelType>
+void TestNetwork(ModelType &model,
+                 MatType &trainData,
+                 MatType &trainLabels,
+                 MatType &testData,
+                 MatType &testLabels,
                  const size_t maxEpochs,
                  const double classificationErrorThreshold)
 {
@@ -50,7 +50,8 @@ void TestNetwork(ModelType& model,
   for (size_t i = 0; i < predictionTemp.n_cols; ++i)
   {
     prediction(i) = arma::as_scalar(arma::find(
-        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) + 1;
+                        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) +
+                    1;
   }
 
   size_t correct = arma::accu(prediction == testLabels);
@@ -65,7 +66,8 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+  if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot load dataset thyroid_train.csv")
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -77,7 +79,8 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   }
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv")
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -99,9 +102,9 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   KMeans<> kmeans;
   kmeans.Cluster(trainData, 8, centroids);
 
-  FFN<MeanSquaredError<> > model;
-  model.Add<RBF<> >(trainData.n_rows, 8, centroids);
-  model.Add<Linear<> >(8, 3);
+  FFN<MeanSquaredError<>> model;
+  model.Add<RBF<>>(trainData.n_rows, 8, centroids);
+  model.Add<Linear<>>(8, 3);
 
   // RBFN neural net with MeanSquaredError.
   TestNetwork<>(model, trainData, trainLabels1, testData, testLabels, 10, 0.1);
@@ -131,9 +134,9 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   KMeans<> kmeans1;
   kmeans1.Cluster(dataset, 140, centroids1);
 
-  FFN<MeanSquaredError<> > model1;
-  model1.Add<RBF<> >(dataset.n_rows, 140, centroids1, 4.1);
-  model1.Add<Linear<> >(140, 2);
+  FFN<MeanSquaredError<>> model1;
+  model1.Add<RBF<>>(dataset.n_rows, 140, centroids1, 4.1);
+  model1.Add<Linear<>>(140, 2);
 
   // RBFN neural net with MeanSquaredError.
   TestNetwork<>(model1, dataset, labels1, dataset, labels, 10, 0.1);

From 1f88bc9630472daf01efaa3ef448a71335208e44 Mon Sep 17 00:00:00 2001
From: Heisenbuug <deathcoderx@gmail.com>
Date: Mon, 22 Feb 2021 20:32:12 +0530
Subject: [PATCH 188/253] Adding FAIL Messages

---
 .../tests/feedforward_network_2_test.cpp      | 35 ++++++-----
 src/mlpack/tests/feedforward_network_test.cpp | 45 +++++++++-----
 src/mlpack/tests/io_test.cpp                  | 18 ++++--
 src/mlpack/tests/kfn_test.cpp                 | 12 ++--
 src/mlpack/tests/knn_test.cpp                 |  6 +-
 src/mlpack/tests/krann_search_test.cpp        | 54 +++++++++++------
 src/mlpack/tests/ksinit_test.cpp              |  6 +-
 src/mlpack/tests/lars_test.cpp                | 30 ++++++----
 src/mlpack/tests/lin_alg_test.cpp             |  3 +-
 src/mlpack/tests/lmnn_test.cpp                | 12 ++--
 src/mlpack/tests/load_save_test.cpp           | 57 ++++++++++++------
 src/mlpack/tests/lrsdp_test.cpp               | 12 ++--
 src/mlpack/tests/lsh_test.cpp                 | 45 +++++++++-----
 src/mlpack/tests/matrix_completion_test.cpp   |  6 +-
 src/mlpack/tests/nbc_test.cpp                 | 60 ++++++++++++-------
 src/mlpack/tests/nystroem_method_test.cpp     |  3 +-
 src/mlpack/tests/one_hot_encoding_test.cpp    |  3 +-
 src/mlpack/tests/pca_test.cpp                 |  3 +-
 src/mlpack/tests/quic_svd_test.cpp            |  3 +-
 src/mlpack/tests/radical_test.cpp             |  6 +-
 src/mlpack/tests/random_forest_test.cpp       | 42 ++++++++-----
 src/mlpack/tests/svd_incremental_test.cpp     |  3 +-
 src/mlpack/tests/svdplusplus_test.cpp         |  6 +-
 23 files changed, 306 insertions(+), 164 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_2_test.cpp b/src/mlpack/tests/feedforward_network_2_test.cpp
index 104561cf03..3a57624d26 100644
--- a/src/mlpack/tests/feedforward_network_2_test.cpp
+++ b/src/mlpack/tests/feedforward_network_2_test.cpp
@@ -21,7 +21,7 @@
 #include <ensmallen.hpp>
 
 #include "catch.hpp"
-#include "serialization_catch.hpp"
+#include "serialization.hpp"
 #include "custom_layer.hpp"
 
 using namespace mlpack;
@@ -31,12 +31,12 @@ using namespace mlpack::kmeans;
 /**
  * Train and evaluate a model with the specified structure.
  */
-template <typename MatType = arma::mat, typename ModelType>
-void TestNetwork(ModelType &model,
-                 MatType &trainData,
-                 MatType &trainLabels,
-                 MatType &testData,
-                 MatType &testLabels,
+template<typename MatType = arma::mat, typename ModelType>
+void TestNetwork(ModelType& model,
+                 MatType& trainData,
+                 MatType& trainLabels,
+                 MatType& testData,
+                 MatType& testLabels,
                  const size_t maxEpochs,
                  const double classificationErrorThreshold)
 {
@@ -50,8 +50,7 @@ void TestNetwork(ModelType &model,
   for (size_t i = 0; i < predictionTemp.n_cols; ++i)
   {
     prediction(i) = arma::as_scalar(arma::find(
-                        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) +
-                    1;
+        arma::max(predictionTemp.col(i)) == predictionTemp.col(i), 1)) + 1;
   }
 
   size_t correct = arma::accu(prediction == testLabels);
@@ -67,7 +66,7 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   // Load the dataset.
   arma::mat trainData;
   if (!data::Load("thyroid_train.csv", trainData))
-    FAIL("Cannot load dataset thyroid_train.csv")
+    Fail("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -80,7 +79,7 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
 
   arma::mat testData;
   if (!data::Load("thyroid_test.csv", testData))
-    FAIL("Cannot load dataset thyroid_test.csv")
+    Fail("Cannot open thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -102,9 +101,9 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   KMeans<> kmeans;
   kmeans.Cluster(trainData, 8, centroids);
 
-  FFN<MeanSquaredError<>> model;
-  model.Add<RBF<>>(trainData.n_rows, 8, centroids);
-  model.Add<Linear<>>(8, 3);
+  FFN<MeanSquaredError<> > model;
+  model.Add<RBF<> >(trainData.n_rows, 8, centroids);
+  model.Add<Linear<> >(8, 3);
 
   // RBFN neural net with MeanSquaredError.
   TestNetwork<>(model, trainData, trainLabels1, testData, testLabels, 10, 0.1);
@@ -134,10 +133,10 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   KMeans<> kmeans1;
   kmeans1.Cluster(dataset, 140, centroids1);
 
-  FFN<MeanSquaredError<>> model1;
-  model1.Add<RBF<>>(dataset.n_rows, 140, centroids1, 4.1);
-  model1.Add<Linear<>>(140, 2);
+  FFN<MeanSquaredError<> > model1;
+  model1.Add<RBF<> >(dataset.n_rows, 140, centroids1, 4.1);
+  model1.Add<Linear<> >(140, 2);
 
   // RBFN neural net with MeanSquaredError.
   TestNetwork<>(model1, dataset, labels1, dataset, labels, 10, 0.1);
-}
+}
\ No newline at end of file
diff --git a/src/mlpack/tests/feedforward_network_test.cpp b/src/mlpack/tests/feedforward_network_test.cpp
index 7188f69f50..c7386261bf 100644
--- a/src/mlpack/tests/feedforward_network_test.cpp
+++ b/src/mlpack/tests/feedforward_network_test.cpp
@@ -107,7 +107,8 @@ TEST_CASE("CheckCopyMovingVanillaNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+  if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -160,13 +161,15 @@ TEST_CASE("FFVanillaNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -307,13 +310,15 @@ TEST_CASE("DropoutNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -408,13 +413,15 @@ TEST_CASE("DropConnectNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -497,13 +504,15 @@ TEST_CASE("FFSerializationTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+      FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -546,13 +555,15 @@ TEST_CASE("CustomLayerTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+      FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -625,13 +636,15 @@ TEST_CASE("FFNTrainReturnObjective", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+      FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -695,13 +708,15 @@ TEST_CASE("OptimizerTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-  data::Load("thyroid_train.csv", trainData, true);
+    if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
 
   arma::mat testData;
-  data::Load("thyroid_test.csv", testData, true);
+  if (!data::Load("thyroid_test.csv", testData))
+    FAIL("Cannot load dataset thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
diff --git a/src/mlpack/tests/io_test.cpp b/src/mlpack/tests/io_test.cpp
index fa363face9..26319a8d79 100644
--- a/src/mlpack/tests/io_test.cpp
+++ b/src/mlpack/tests/io_test.cpp
@@ -413,7 +413,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputColParamTest",
 
   // Now load the vector back and make sure it was saved correctly.
   arma::vec dataset2;
-  data::Load("test.csv", dataset2);
+  if (!data::Load("test.csv", dataset2))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_rows == dataset2.n_rows);
   for (size_t i = 0; i < dataset.n_elem; ++i)
@@ -461,7 +462,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputUnsignedColParamTest",
 
   // Now load the vector back and make sure it was saved correctly.
   arma::Col<size_t> dataset2;
-  data::Load("test.csv", dataset2);
+  if (!data::Load("test.csv", dataset2))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_rows == dataset2.n_rows);
   for (size_t i = 0; i < dataset.n_elem; ++i)
@@ -509,7 +511,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputRowParamTest",
 
   // Now load the row vector back and make sure it was saved correctly.
   arma::rowvec dataset2;
-  data::Load("test.csv", dataset2);
+  if (!data::Load("test.csv", dataset2))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_cols == dataset2.n_cols);
   for (size_t i = 0; i < dataset.n_elem; ++i)
@@ -556,7 +559,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputUnsignedRowParamTest", "[IOTest]")
 
   // Now load the row vector back and make sure it was saved correctly.
   arma::Row<size_t> dataset2;
-  data::Load("test.csv", dataset2);
+  if (!data::Load("test.csv", dataset2))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_cols == dataset2.n_cols);
   for (size_t i = 0; i < dataset.n_elem; ++i)
@@ -784,7 +788,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputMatrixParamTest",
 
   // Now load the matrix back and make sure it was saved correctly.
   arma::mat dataset2;
-  data::Load("test.csv", dataset2);
+  if (!data::Load("test.csv", dataset2))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_cols == dataset2.n_cols);
   REQUIRE(dataset.n_rows == dataset2.n_rows);
@@ -833,7 +838,8 @@ TEST_CASE_METHOD(IOTestDestroyer, "OutputMatrixNoTransposeParamTest",
 
   // Now load the matrix back and make sure it was saved correctly.
   arma::mat dataset2;
-  data::Load("test.csv", dataset2, true, false);
+  if (!data::Load("test.csv", dataset2, false, false))
+    FAIL("Cannot load dataset test.csv");
 
   REQUIRE(dataset.n_cols == dataset2.n_cols);
   REQUIRE(dataset.n_rows == dataset2.n_rows);
diff --git a/src/mlpack/tests/kfn_test.cpp b/src/mlpack/tests/kfn_test.cpp
index f3fefadb7a..1fb813b2e1 100644
--- a/src/mlpack/tests/kfn_test.cpp
+++ b/src/mlpack/tests/kfn_test.cpp
@@ -335,7 +335,7 @@ TEST_CASE("KFNDualTreeVsNaive1", "[KFNTest]")
 
   // Hard-coded filename: bad?
   if (!data::Load("test_data_3_1000.csv", dataset))
-    FAIL("Cannot load test dataset test_data_3_1000.csv!");
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KFN kfn(dataset);
 
@@ -369,7 +369,7 @@ TEST_CASE("KFNDualTreeVsNaive2", "[KFNTest]")
   // Hard-coded filename: bad?
   // Code duplication: also bad!
   if (!data::Load("test_data_3_1000.csv", dataset))
-    FAIL("Cannot load test dataset test_data_3_1000.csv!");
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KFN kfn(dataset);
 
@@ -403,7 +403,7 @@ TEST_CASE("KFNSingleTreeVsNaive", "[KFNTest]")
   // Hard-coded filename: bad!
   // Code duplication: also bad!
   if (!data::Load("test_data_3_1000.csv", dataset))
-    FAIL("Cannot load test dataset test_data_3_1000.csv!");
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KFN kfn(dataset, SINGLE_TREE_MODE);
 
@@ -466,7 +466,8 @@ TEST_CASE("KFNSingleCoverTreeTest", "[KFNTest]")
 TEST_CASE("KFNDualCoverTreeTest", "[KFNTest]")
 {
   arma::mat dataset;
-  data::Load("test_data_3_1000.csv", dataset);
+  if (!data::Load("test_data_3_1000.csv", dataset))
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KFN tree(dataset);
 
@@ -538,7 +539,8 @@ TEST_CASE("KFNSingleBallTreeTest", "[KFNTest]")
 TEST_CASE("KFNDualBallTreeTest", "[KFNTest]")
 {
   arma::mat dataset;
-  data::Load("test_data_3_1000.csv", dataset);
+  if (!data::Load("test_data_3_1000.csv", dataset))
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KFN tree(dataset);
 
diff --git a/src/mlpack/tests/knn_test.cpp b/src/mlpack/tests/knn_test.cpp
index 7e84700843..5f151eb4b6 100644
--- a/src/mlpack/tests/knn_test.cpp
+++ b/src/mlpack/tests/knn_test.cpp
@@ -794,7 +794,8 @@ TEST_CASE("KNNSingleCoverTreeTest", "[KNNTest]")
 TEST_CASE("KNNDualCoverTreeTest", "[KNNTest]")
 {
   arma::mat dataset;
-  data::Load("test_data_3_1000.csv", dataset);
+  if (!data::Load("test_data_3_1000.csv", dataset))
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KNN tree(dataset);
 
@@ -865,7 +866,8 @@ TEST_CASE("KNNSingleBallTreeTest", "[KNNTest]")
 TEST_CASE("KNNDualBallTreeTest", "[KNNTest]")
 {
   arma::mat dataset;
-  data::Load("test_data_3_1000.csv", dataset);
+  if (!data::Load("test_data_3_1000.csv", dataset))
+    FAIL("Cannot load test dataset test_data_3_1000.csv");
 
   KNN tree(dataset);
 
diff --git a/src/mlpack/tests/krann_search_test.cpp b/src/mlpack/tests/krann_search_test.cpp
index 4efa022776..5bc13eb952 100644
--- a/src/mlpack/tests/krann_search_test.cpp
+++ b/src/mlpack/tests/krann_search_test.cpp
@@ -35,13 +35,16 @@ TEST_CASE("NaiveGuaranteeTest", "[KRANNTest]")
   arma::mat refData;
   arma::mat queryData;
 
-  data::Load("rann_test_r_3_900.csv", refData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", refData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   RASearch<> rsRann(refData, true, false, 1.0);
 
   arma::mat qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+    if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 1000;
   arma::Col<size_t> numSuccessRounds(queryData.n_cols);
@@ -88,8 +91,10 @@ TEST_CASE("SingleTreeSearch", "[KRANNTest]")
   arma::mat refData;
   arma::mat queryData;
 
-  data::Load("rann_test_r_3_900.csv", refData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", refData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   // Search for 1 rank-approximate nearest-neighbors in the top 30% of the point
   // (rank error of 3).
@@ -100,7 +105,8 @@ TEST_CASE("SingleTreeSearch", "[KRANNTest]")
 
   // The relative ranks for the given query reference pair
   arma::Mat<size_t> qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 1000;
   arma::Col<size_t> numSuccessRounds(queryData.n_cols);
@@ -147,8 +153,10 @@ TEST_CASE("DualTreeSearch", "[KRANNTest]")
   arma::mat refData;
   arma::mat queryData;
 
-  data::Load("rann_test_r_3_900.csv", refData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", refData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   // Search for 1 rank-approximate nearest-neighbors in the top 30% of the point
   // (rank error of 3).
@@ -158,7 +166,8 @@ TEST_CASE("DualTreeSearch", "[KRANNTest]")
   RASearch<> tsdRann(refData, false, false, 1.0, 0.95, false, false, 5);
 
   arma::Mat<size_t> qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 1000;
   arma::Col<size_t> numSuccessRounds(queryData.n_cols);
@@ -274,8 +283,10 @@ TEST_CASE("SingleCoverTreeTest", "[KRANNTest]")
   arma::mat refData;
   arma::mat queryData;
 
-  data::Load("rann_test_r_3_900.csv", refData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", refData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   // Search for 1 rank-approximate nearest-neighbors in the top 30% of the point
   // (rank error of 3).
@@ -289,7 +300,8 @@ TEST_CASE("SingleCoverTreeTest", "[KRANNTest]")
 
   // The relative ranks for the given query reference pair.
   arma::Mat<size_t> qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 100;
   arma::Col<size_t> numSuccessRounds(queryData.n_cols);
@@ -335,8 +347,10 @@ TEST_CASE("DualCoverTreeTest", "[KRANNTest]")
   arma::mat refData;
   arma::mat queryData;
 
-  data::Load("rann_test_r_3_900.csv", refData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", refData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   // Search for 1 rank-approximate nearest-neighbors in the top 30% of the point
   // (rank error of 3).
@@ -354,7 +368,8 @@ TEST_CASE("DualCoverTreeTest", "[KRANNTest]")
   RACoverTreeSearch tsdRann(&refTree, false, 1.0, 0.95, false, false, 5);
 
   arma::Mat<size_t> qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 100;
   arma::Col<size_t> numSuccessRounds(queryData.n_cols);
@@ -623,8 +638,10 @@ TEST_CASE("RAModelTest", "[KRANNTest]")
   typedef RAModel<NearestNeighborSort> KNNModel;
 
   arma::mat queryData, referenceData;
-  data::Load("rann_test_r_3_900.csv", referenceData, true);
-  data::Load("rann_test_q_3_100.csv", queryData, true);
+  if (!data::Load("rann_test_r_3_900.csv", referenceData))
+    FAIL("Cannot load dataset rann_test_r_3_900.csv");
+  if (!data::Load("rann_test_q_3_100.csv", queryData))
+    FAIL("Cannot load dataset rann_test_q_3_100.csv");
 
   // Build all the possible models.
   KNNModel models[20];
@@ -650,7 +667,8 @@ TEST_CASE("RAModelTest", "[KRANNTest]")
   models[19] = KNNModel(KNNModel::TreeTypes::OCTREE, true);
 
   arma::Mat<size_t> qrRanks;
-  data::Load("rann_test_qr_ranks.csv", qrRanks, true, false); // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+    FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   for (size_t j = 0; j < 3; ++j)
   {
diff --git a/src/mlpack/tests/ksinit_test.cpp b/src/mlpack/tests/ksinit_test.cpp
index 11d6cdae40..930df617e4 100644
--- a/src/mlpack/tests/ksinit_test.cpp
+++ b/src/mlpack/tests/ksinit_test.cpp
@@ -230,8 +230,10 @@ TEST_CASE("IrisDataset", "[KSInitialization]")
 
   arma::mat dataset, labels;
 
-  data::Load("iris.csv", dataset, true);
-  data::Load("iris_labels.txt", labels, true);
+  if (!data::Load("iris.csv", dataset))
+    FAIL("Cannot load dataset iris.csv");
+  if (!data::Load("iris_labels.txt", labels))
+    FAIL("Cannot load dataset iris_labels.txt");
 
   dataset.insert_rows(dataset.n_rows, labels);
 
diff --git a/src/mlpack/tests/lars_test.cpp b/src/mlpack/tests/lars_test.cpp
index ef030343ae..bb3a2aa767 100644
--- a/src/mlpack/tests/lars_test.cpp
+++ b/src/mlpack/tests/lars_test.cpp
@@ -111,8 +111,10 @@ TEST_CASE("CholeskySingularityTest", "[LARSTest]")
   arma::mat X;
   arma::mat Y;
 
-  data::Load("lars_dependent_x.csv", X);
-  data::Load("lars_dependent_y.csv", Y);
+  if (!data::Load("lars_dependent_x.csv", X))
+    FAIL("Cannot load dataset lars_dependent_x.csv");
+  if (!data::Load("lars_dependent_y.csv", Y))
+    FAIL("Cannot load dataset lars_dependent_y.csv");
 
   arma::rowvec y = Y.row(0);
 
@@ -135,8 +137,10 @@ TEST_CASE("NoCholeskySingularityTest", "[LARSTest]")
   arma::mat X;
   arma::mat Y;
 
-  data::Load("lars_dependent_x.csv", X);
-  data::Load("lars_dependent_y.csv", Y);
+  if (!data::Load("lars_dependent_x.csv", X))
+    FAIL("Cannot load dataset lars_dependent_x.csv");
+  if (!data::Load("lars_dependent_y.csv", Y))
+    FAIL("Cannot load dataset lars_dependent_y.csv");
 
   arma::rowvec y = Y.row(0);
 
@@ -357,8 +361,10 @@ TEST_CASE("LARSTrainReturnCorrelation", "[LARSTest]")
   arma::mat X;
   arma::mat Y;
 
-  data::Load("lars_dependent_x.csv", X);
-  data::Load("lars_dependent_y.csv", Y);
+  if (!data::Load("lars_dependent_x.csv", X))
+    FAIL("Cannot load dataset lars_dependent_x.csv");
+  if (!data::Load("lars_dependent_y.csv", Y))
+    FAIL("Cannot load dataset lars_dependent_y.csv");
 
   arma::rowvec y = Y.row(0);
 
@@ -403,8 +409,10 @@ TEST_CASE("LARSTestComputeError", "[LARSTest]")
   arma::mat X;
   arma::mat Y;
 
-  data::Load("lars_dependent_x.csv", X);
-  data::Load("lars_dependent_y.csv", Y);
+  if (!data::Load("lars_dependent_x.csv", X))
+    FAIL("Cannot load dataset lars_dependent_x.csv");
+  if (!data::Load("lars_dependent_y.csv", Y))
+    FAIL("Cannot load dataset lars_dependent_y.csv");
 
   arma::rowvec y = Y.row(0);
 
@@ -427,8 +435,10 @@ TEST_CASE("LARSCopyConstructorTest", "[LARSTest]")
   arma::rowvec targets;
 
   // Load training input and predictions for testing.
-  data::Load("lars_dependent_x.csv", features);
-  data::Load("lars_dependent_y.csv", Y);
+  if (!data::Load("lars_dependent_x.csv", features))
+    FAIL("Cannot load dataset lars_dependent_x.csv");
+  if (!data::Load("lars_dependent_y.csv", Y))
+    FAIL("Cannot load dataset lars_dependent_y.csv");
   targets = Y.row(0);
 
   // Check if the copy is accessible even after deleting the pointer to the
diff --git a/src/mlpack/tests/lin_alg_test.cpp b/src/mlpack/tests/lin_alg_test.cpp
index a43821d75d..4b8af04b79 100644
--- a/src/mlpack/tests/lin_alg_test.cpp
+++ b/src/mlpack/tests/lin_alg_test.cpp
@@ -91,7 +91,8 @@ TEST_CASE("TestOrthogonalize", "[LinAlgTest]")
   // Generate a random matrix; then, orthogonalize it and test if it's
   // orthogonal.
   mat tmp, orth;
-  data::Load("fake.csv", tmp);
+  if (!data::Load("fake.csv", tmp))
+    FAIL("Cannot load dataset fake.csv");
   Orthogonalize(tmp, orth);
 
   // test orthogonality
diff --git a/src/mlpack/tests/lmnn_test.cpp b/src/mlpack/tests/lmnn_test.cpp
index b767f4a940..4a0ce99360 100644
--- a/src/mlpack/tests/lmnn_test.cpp
+++ b/src/mlpack/tests/lmnn_test.cpp
@@ -699,8 +699,10 @@ TEST_CASE("LMNNFunctionGradientTest3", "[LMNNTest]")
 {
   arma::mat dataset;
   arma::Row<size_t> labels;
-  data::Load("iris.csv", dataset);
-  data::Load("iris_labels.txt", labels);
+  if (!data::Load("iris.csv", dataset))
+    FAIL("Cannot load dataset iris.csv");
+  if (!data::Load("iris_labels.txt", labels))
+    FAIL("Cannot load dataset iris_labels.txt");
 
   LMNNFunction<> lmnnfn(dataset, labels, 1, 0.6, 1);
 
@@ -716,8 +718,10 @@ TEST_CASE("LMNNFunctionGradientTest4", "[LMNNTest]")
 {
   arma::mat dataset;
   arma::Row<size_t> labels;
-  data::Load("iris.csv", dataset);
-  data::Load("iris_labels.txt", labels);
+  if (!data::Load("iris.csv", dataset))
+    FAIL("Cannot load dataset iris.csv");
+  if (!data::Load("iris_labels.txt", labels))
+    FAIL("Cannot load dataset iris_labels.txt");
 
   LMNNFunction<> lmnnfn(dataset, labels, 1, 0.6, 1);
 
diff --git a/src/mlpack/tests/load_save_test.cpp b/src/mlpack/tests/load_save_test.cpp
index b9e8a839cf..bf7066c04f 100644
--- a/src/mlpack/tests/load_save_test.cpp
+++ b/src/mlpack/tests/load_save_test.cpp
@@ -1414,8 +1414,10 @@ TEST_CASE("RegularCSVDatasetInfoLoad", "[LoadSaveTest]")
   {
     arma::mat one, two;
     DatasetInfo info;
-    data::Load(testFiles[i], one);
-    data::Load(testFiles[i], two, info);
+    if (!data::Load(testFiles[i], one))
+      FAIL("Cannot load dataset");
+    if (!data::Load(testFiles[i], two, info);
+      FAIL("Cannot load dataset");
 
     // Check that the matrices contain the same information.
     REQUIRE(one.n_elem == two.n_elem);
@@ -1454,8 +1456,10 @@ TEST_CASE("NontransposedCSVDatasetInfoLoad", "[LoadSaveTest]")
   {
     arma::mat one, two;
     DatasetInfo info;
-    data::Load(testFiles[i], one, true, false); // No transpose.
-    data::Load(testFiles[i], two, info, true, false);
+    if (!data::Load(testFiles[i], one, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
+    if (!data::Load(testFiles[i], two, info, false, false))
+      FAIL("Cannot load dataset");
 
     // Check that the matrices contain the same information.
     REQUIRE(one.n_elem == two.n_elem);
@@ -1494,7 +1498,8 @@ TEST_CASE("CategoricalCSVLoadTest00", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 7);
   REQUIRE(matrix.n_rows == 3);
@@ -1551,7 +1556,8 @@ TEST_CASE("CategoricalCSVLoadTest01", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 4);
   REQUIRE(matrix.n_rows == 3);
@@ -1596,7 +1602,8 @@ TEST_CASE("CategoricalCSVLoadTest02", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 4);
   REQUIRE(matrix.n_rows == 3);
@@ -1640,7 +1647,8 @@ TEST_CASE("CategoricalCSVLoadTest03", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 4);
   REQUIRE(matrix.n_rows == 3);
@@ -1684,7 +1692,8 @@ TEST_CASE("CategoricalCSVLoadTest04", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 4);
   REQUIRE(matrix.n_rows == 3);
@@ -1731,7 +1740,8 @@ TEST_CASE("CategoricalNontransposedCSVLoadTest00", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true, false); // No transpose.
+  if (!data::Load("test.csv", matrix, info, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 3);
   REQUIRE(matrix.n_rows == 7);
@@ -1820,7 +1830,8 @@ TEST_CASE("CategoricalNontransposedCSVLoadTest01", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true, false); // No transpose.
+  if (!data::Load("test.csv", matrix, info, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 3);
   REQUIRE(matrix.n_rows == 4);
@@ -1865,7 +1876,8 @@ TEST_CASE("CategoricalNontransposedCSVLoadTest02", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true, false); // No transpose.
+  if (!data::Load("test.csv", matrix, info, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 3);
   REQUIRE(matrix.n_rows == 4);
@@ -1910,7 +1922,8 @@ TEST_CASE("CategoricalNontransposedCSVLoadTest03", "[LoadSaveTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info, true, false); // No transpose.
+  if (!data::Load("test.csv", matrix, info, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
 
   REQUIRE(matrix.n_cols == 3);
   REQUIRE(matrix.n_rows == 4);
@@ -1955,7 +1968,8 @@ TEST_CASE("CategoricalNontransposedCSVLoadTest04", "[LoadSaveTest]")
     // Load the test CSV.
     arma::umat matrix;
     DatasetInfo info;
-    data::Load("test.csv", matrix, info, true, false); // No transpose.
+    if (!data::Load("test.csv", matrix, info, false, false)) // No transpose.
+      FAIL("Cannot load dataset");
 
     REQUIRE(matrix.n_cols == 3);
     REQUIRE(matrix.n_rows == 4);
@@ -2003,7 +2017,8 @@ TEST_CASE("HarderKeonTest", "[LoadSaveTest]")
   // Load transposed.
   arma::mat dataset;
   data::DatasetInfo info;
-  data::Load("test.csv", dataset, info, true, true);
+  if (!data::Load("test.csv", dataset, info, false, true))
+    FAIL("Cannot load dataset");
 
   REQUIRE(dataset.n_rows == 5);
   REQUIRE(dataset.n_cols == 4);
@@ -2017,7 +2032,8 @@ TEST_CASE("HarderKeonTest", "[LoadSaveTest]")
 
   // Now load non-transposed.
   data::DatasetInfo ntInfo;
-  data::Load("test.csv", dataset, ntInfo, true, false);
+  if (!data::Load("test.csv", dataset, ntInfo, false, false))
+    FAIL("Cannot load dataset");
 
   REQUIRE(dataset.n_rows == 4);
   REQUIRE(dataset.n_cols == 5);
@@ -2052,7 +2068,8 @@ TEST_CASE("SimpleARFFTest", "[LoadSaveTest]")
 
   arma::mat dataset;
   DatasetInfo info;
-  data::Load("test.arff", dataset, info);
+  if (!data::Load("test.arff", dataset, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(info.Dimensionality() == 2);
   REQUIRE(info.Type(0) == Datatype::numeric);
@@ -2093,7 +2110,8 @@ TEST_CASE("SimpleARFFCategoricalTest", "[LoadSaveTest]")
 
   arma::mat dataset;
   DatasetInfo info;
-  data::Load("test.arff", dataset, info);
+  if (!data::Load("test.arff", dataset, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(info.Dimensionality() == 3);
 
@@ -2152,7 +2170,8 @@ TEST_CASE("HarderARFFTest", "[LoadSaveTest]")
 
   arma::mat dataset;
   DatasetInfo info;
-  data::Load("test.arff", dataset, info);
+  if (!data::Load("test.arff", dataset, info))
+    FAIL("Cannot load dataset");
 
   REQUIRE(info.Dimensionality() == 5);
 
diff --git a/src/mlpack/tests/lrsdp_test.cpp b/src/mlpack/tests/lrsdp_test.cpp
index f07b13ad7f..b2ac089997 100644
--- a/src/mlpack/tests/lrsdp_test.cpp
+++ b/src/mlpack/tests/lrsdp_test.cpp
@@ -95,7 +95,8 @@ BOOST_AUTO_TEST_CASE(Johnson844LovaszThetaSDP)
 {
   // Load the edges.
   arma::mat edges;
-  data::Load("johnson8-4-4.csv", edges, true);
+  if (!data::Load("johnson8-4-4.csv", edges))
+    FAIL("Cannot load dataset johnson8-4-4.csv");
 
   // The LRSDP itself and the initial point.
   arma::mat coordinates;
@@ -150,7 +151,8 @@ BOOST_AUTO_TEST_CASE(ErdosRenyiRandomGraphMaxCutSDP)
 {
   // Load the edges.
   arma::mat edges;
-  data::Load("erdosrenyi-n100.csv", edges, true);
+  if (!data::Load("erdosrenyi-n100.csv", edges)
+    FAIL("Cannot load dataset erdosrenyi-n100.csv");
 
   arma::sp_mat laplacian;
   CreateSparseGraphLaplacian(edges, laplacian);
@@ -221,8 +223,10 @@ BOOST_AUTO_TEST_CASE(GaussianMatrixSensingSDP)
   arma::mat Xorig, A;
 
   // read the unknown matrix X and the measurement matrices A_i in
-  data::Load("sensing_X.csv", Xorig, true, false);
-  data::Load("sensing_A.csv", A, true, false);
+  if (!data::Load("sensing_X.csv", Xorig, false, false))
+    FAIL("Cannot load dataset sensing_X.csv");
+  if (!data::Load("sensing_A.csv", A, false, false))
+    FAIL("Cannot load dataset sensing_A.csv");
 
   const size_t m = Xorig.n_rows;
   const size_t n = Xorig.n_cols;
diff --git a/src/mlpack/tests/lsh_test.cpp b/src/mlpack/tests/lsh_test.cpp
index c9583d9853..7eca5fbcc5 100644
--- a/src/mlpack/tests/lsh_test.cpp
+++ b/src/mlpack/tests/lsh_test.cpp
@@ -115,8 +115,10 @@ TEST_CASE("NumTablesTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Run classic knn on reference data.
   KNN knn(rdata);
@@ -187,8 +189,10 @@ TEST_CASE("HashWidthTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Run classic knn on reference data.
   KNN knn(rdata);
@@ -247,8 +251,10 @@ TEST_CASE("NumProjTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Run classic knn on reference data.
   KNN knn(rdata);
@@ -307,8 +313,10 @@ TEST_CASE("RecallTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Run classic knn on reference data.
   KNN knn(rdata);
@@ -502,8 +510,10 @@ TEST_CASE("MultiprobeTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Add a slight amount of noise to the dataset, so that we don't end up with
   // points that have the same distance (hopefully).
@@ -780,8 +790,10 @@ TEST_CASE("ParallelBichromatic", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Where to store neighbors and distances
   arma::Mat<size_t> sequentialNeighbors;
@@ -819,7 +831,8 @@ TEST_CASE("ParallelMonochromatic", "[LSHTest]")
   // Read iris training data as reference and query set.
   const string trainSet = "iris_train.csv";
   arma::mat rdata;
-  data::Load(trainSet, rdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
 
   // Where to store neighbors and distances
   arma::Mat<size_t> sequentialNeighbors;
@@ -936,8 +949,10 @@ TEST_CASE("SparseLSHTest", "[LSHTest]")
   const string testSet = "iris_test.csv";
   arma::mat rdata;
   arma::mat qdata;
-  data::Load(trainSet, rdata, true);
-  data::Load(testSet, qdata, true);
+  if (!data::Load(trainSet, rdata))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testSet, qdata))
+    FAIL("Cannot load dataset");
 
   // Run on dense data.
   LSHSearch<> denseLSH(
diff --git a/src/mlpack/tests/matrix_completion_test.cpp b/src/mlpack/tests/matrix_completion_test.cpp
index 104d169ef6..6fb3baff79 100644
--- a/src/mlpack/tests/matrix_completion_test.cpp
+++ b/src/mlpack/tests/matrix_completion_test.cpp
@@ -34,8 +34,10 @@ TEST_CASE("UniformMatrixCompletionSDP", "[MatrixCompletionTest]")
   arma::mat Xorig, values;
   arma::umat indices;
 
-  data::Load("completion_X.csv", Xorig, true, false);
-  data::Load("completion_indices.csv", indices, true, false);
+  if (!data::Load("completion_X.csv", Xorig, false, false))
+    FAIL("Cannot load dataset completion_X.csv");
+  if (!data::Load("completion_indices.csv", indices, false, false))
+    FAIL("Cannot load dataset completion_indices.csv");
 
   values.set_size(indices.n_cols);
   for (size_t i = 0; i < indices.n_cols; ++i)
diff --git a/src/mlpack/tests/nbc_test.cpp b/src/mlpack/tests/nbc_test.cpp
index ddc0487315..3b757d3b76 100644
--- a/src/mlpack/tests/nbc_test.cpp
+++ b/src/mlpack/tests/nbc_test.cpp
@@ -26,8 +26,10 @@ TEST_CASE("NaiveBayesClassifierTest", "[NBCTest]")
   size_t classes = 2;
 
   arma::mat trainData, trainRes, calcMat;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainResultFilename, trainRes, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainResultFilename, trainRes))
+    FAIL("Cannot load dataset");
 
   // Get the labels out.
   arma::Row<size_t> labels(trainData.n_cols);
@@ -66,9 +68,12 @@ TEST_CASE("NaiveBayesClassifierTest", "[NBCTest]")
   arma::mat testResProbs;
   arma::Row<size_t> calcVec;
   arma::mat calcProbs;
-  data::Load(testFilename, testData, true);
-  data::Load(testResultFilename, testRes, true);
-  data::Load(testResultProbsFilename, testResProbs, true);
+  if (!data::Load(testFilename, testData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testResultFilename, testRes))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testResultProbsFilename, testResProbs))
+    FAIL("Cannot load dataset");
 
   testData.shed_row(testData.n_rows - 1); // Remove the labels.
 
@@ -99,8 +104,10 @@ TEST_CASE("NaiveBayesClassifierIncrementalTest", "[NBCTest]")
   size_t classes = 2;
 
   arma::mat trainData, trainRes, calcMat;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainResultFilename, trainRes, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainResultFilename, trainRes))
+    FAIL("Cannot load dataset");
 
   // Get the labels out.
   arma::Row<size_t> labels(trainData.n_cols);
@@ -139,9 +146,12 @@ TEST_CASE("NaiveBayesClassifierIncrementalTest", "[NBCTest]")
   arma::mat testResProba;
   arma::Row<size_t> calcVec;
   arma::mat calcProbs;
-  data::Load(testFilename, testData, true);
-  data::Load(testResultFilename, testRes, true);
-  data::Load(testResultProbsFilename, testResProba, true);
+  if (!data::Load(testFilename, testData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testResultFilename, testRes))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testResultProbsFilename, testResProba))
+    FAIL("Cannot load dataset");
 
   testData.shed_row(testData.n_rows - 1); // Remove the labels.
 
@@ -170,8 +180,10 @@ TEST_CASE("SeparateTrainTest", "[NBCTest]")
   size_t classes = 2;
 
   arma::mat trainData, trainRes, calcMat;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainResultFilename, trainRes, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainResultFilename, trainRes))
+    FAIL("Cannot load dataset");
 
   // Get the labels out.
   arma::Row<size_t> labels(trainData.n_cols);
@@ -228,8 +240,10 @@ TEST_CASE("SeparateTrainIncrementalTest", "[NBCTest]")
   size_t classes = 2;
 
   arma::mat trainData, trainRes, calcMat;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainResultFilename, trainRes, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainResultFilename, trainRes))
+    FAIL("Cannot load dataset");
 
   // Get the labels out.
   arma::Row<size_t> labels(trainData.n_cols);
@@ -286,8 +300,10 @@ TEST_CASE("SeparateTrainIndividualIncrementalTest", "[NBCTest]")
   size_t classes = 2;
 
   arma::mat trainData, trainRes, calcMat;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainResultFilename, trainRes, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainResultFilename, trainRes))
+    FAIL("Cannot load dataset");
 
   // Get the labels out.
   arma::Row<size_t> labels(trainData.n_cols);
@@ -356,8 +372,10 @@ TEST_CASE("NaiveBayesClassifierHighDimensionsTest", "[NBCTest]")
   // Create variables for training and assign data to them.
   arma::mat trainData;
   arma::Row<size_t> trainLabels;
-  data::Load(trainFilename, trainData, true);
-  data::Load(trainLabelsFileName, trainLabels, true);
+  if (!data::Load(trainFilename, trainData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(trainLabelsFileName, trainLabels))
+    FAIL("Cannot load dataset");
 
   // Initialize and train a NBC model.
   NaiveBayesClassifier<> nbcTest(trainData, trainLabels, classes);
@@ -366,8 +384,10 @@ TEST_CASE("NaiveBayesClassifierHighDimensionsTest", "[NBCTest]")
   arma::mat testData, calcProbs;
   arma::Row<size_t> testLabels;
   arma::Row<size_t> calcVec;
-  data::Load(testFilename, testData, true);
-  data::Load(testLabelsFilename, testLabels, true);
+  if (!data::Load(testFilename, testData))
+    FAIL("Cannot load dataset");
+  if (!data::Load(testLabelsFilename, testLabels))
+    FAIL("Cannot load dataset");
 
   // Classify observations in the test dataset. To use Classify() method with
   // a parameter for probabilities of predictions, we pass 'calcProbs' to the
diff --git a/src/mlpack/tests/nystroem_method_test.cpp b/src/mlpack/tests/nystroem_method_test.cpp
index 1c99a7b7e6..32bf189d49 100644
--- a/src/mlpack/tests/nystroem_method_test.cpp
+++ b/src/mlpack/tests/nystroem_method_test.cpp
@@ -146,7 +146,8 @@ TEST_CASE("GermanTest", "[NystroemMethodTest]")
 {
   // Load the dataset.
   arma::mat dataset;
-  data::Load("german.csv", dataset, true);
+  if (!data::Load("german.csv", dataset))
+    FAIL("Cannot load dataset german.csv");
 
   // These are our tolerance bounds.
   double results[5] = { 32.0, 20.0, 15.0, 12.0, 9.0 };
diff --git a/src/mlpack/tests/one_hot_encoding_test.cpp b/src/mlpack/tests/one_hot_encoding_test.cpp
index a3b19363f6..1844539f0f 100644
--- a/src/mlpack/tests/one_hot_encoding_test.cpp
+++ b/src/mlpack/tests/one_hot_encoding_test.cpp
@@ -191,7 +191,8 @@ TEST_CASE("OneHotEncodingDatasetinfoTest", "[OneHotEncodingTest]")
   // Load the test CSV.
   arma::umat matrix;
   DatasetInfo info;
-  data::Load("test.csv", matrix, info);
+  if (!data::Load("test.csv", matrix, info))
+    FAIL("Cannot load dataset test.csv");
   arma::umat output;
   data::OneHotEncoding(matrix, output, info);
   REQUIRE(output.n_cols == 7);
diff --git a/src/mlpack/tests/pca_test.cpp b/src/mlpack/tests/pca_test.cpp
index 6ccefbbaeb..1d4a1657ed 100644
--- a/src/mlpack/tests/pca_test.cpp
+++ b/src/mlpack/tests/pca_test.cpp
@@ -240,7 +240,8 @@ TEST_CASE("RandomizedPCADimensionalityReductionTest", "[PCATest]")
 TEST_CASE("QUICPCADimensionalityReductionTest", "[PCATest]")
 {
   arma::mat data, data1;
-  data::Load("test_data_3_1000.csv", data);
+  if (!data::Load("test_data_3_1000.csv", data))
+    FAIL("Cannot load dataset test_data_3_1000.csv");
   data1 = data;
 
   arma::mat backupData(data);
diff --git a/src/mlpack/tests/quic_svd_test.cpp b/src/mlpack/tests/quic_svd_test.cpp
index 9ae2e33a79..16cbfa98af 100644
--- a/src/mlpack/tests/quic_svd_test.cpp
+++ b/src/mlpack/tests/quic_svd_test.cpp
@@ -24,7 +24,8 @@ TEST_CASE("QUICSVDReconstructionError", "[QUICSVDTest]")
 {
   // Load the dataset.
   arma::mat dataset;
-  data::Load("test_data_3_1000.csv", dataset);
+  if (!data::Load("test_data_3_1000.csv", dataset))
+    FAIL("Cannot load dataset test_data_3_1000.csv");
 
   // The QUIC-SVD procedure can fail---the Monte Carlo error calculation is
   // random.  Therefore we simply require at least one success.
diff --git a/src/mlpack/tests/radical_test.cpp b/src/mlpack/tests/radical_test.cpp
index feb687ee52..39b77a11f7 100644
--- a/src/mlpack/tests/radical_test.cpp
+++ b/src/mlpack/tests/radical_test.cpp
@@ -21,7 +21,8 @@ using namespace arma;
 TEST_CASE("Radical_Test_Radical3D", "[RadicalTest]")
 {
   mat matX;
-  data::Load("data_3d_mixed.txt", matX);
+  if (!data::Load("data_3d_mixed.txt", matX))
+    FAIL("Cannot load dataset data_3d_mixed.txt");
 
   Radical rad(0.175, 5, 100, matX.n_rows - 1);
 
@@ -39,7 +40,8 @@ TEST_CASE("Radical_Test_Radical3D", "[RadicalTest]")
   }
 
   mat matS;
-  data::Load("data_3d_ind.txt", matS);
+  if (!data::Load("data_3d_ind.txt", matS))
+    FAIL("Cannot load dataset data_3d_ind.txt");
   rad.DoRadical(matS, matY, matW);
 
   matYT = trans(matY);
diff --git a/src/mlpack/tests/random_forest_test.cpp b/src/mlpack/tests/random_forest_test.cpp
index b916ac446f..20397641e0 100644
--- a/src/mlpack/tests/random_forest_test.cpp
+++ b/src/mlpack/tests/random_forest_test.cpp
@@ -122,9 +122,11 @@ TEST_CASE("UnweightedNumericLearningTest", "[RandomForestTest]")
 {
   // Load the vc2 dataset.
   arma::mat dataset;
-  data::Load("vc2.csv", dataset);
+  if (!data::Load("vc2.csv", dataset))
+    FAIL("Cannot load dataset vc2.csv");
   arma::Row<size_t> labels;
-  data::Load("vc2_labels.txt", labels);
+  if (!data::Load("vc2_labels.txt", labels))
+    FAIL("Cannot load dataset vc2.csv");
 
   // Build a random forest and a decision tree.
   RandomForest<> rf(dataset, labels, 3, 20 /* 20 trees */, 1, 1e-7);
@@ -132,9 +134,11 @@ TEST_CASE("UnweightedNumericLearningTest", "[RandomForestTest]")
 
   // Get performance statistics on test data.
   arma::mat testDataset;
-  data::Load("vc2_test.csv", testDataset);
+  if (!data::Load("vc2_test.csv", testDataset))
+    FAIL("Cannot load dataset vc2_test.csv");
   arma::Row<size_t> testLabels;
-  data::Load("vc2_test_labels.txt", testLabels);
+  if (!data::Load("vc2_test_labels.txt", testLabels))
+    FAIL("Cannot load dataset vc2_test_labels.txt");
 
   arma::Row<size_t> rfPredictions;
   arma::Row<size_t> dtPredictions;
@@ -158,8 +162,10 @@ TEST_CASE("WeightedNumericLearningTest", "[RandomForestTest]")
 {
   arma::mat dataset;
   arma::Row<size_t> labels;
-  data::Load("vc2.csv", dataset);
-  data::Load("vc2_labels.txt", labels);
+  if (!data::Load("vc2.csv", dataset))
+    FAIL("Cannot load dataset vc2.csv");
+  if (!data::Load("vc2_labels.txt", labels))
+    FAIL("Cannot load dataset vc2_labels.txt");
 
   // Add some noise.
   arma::mat noise(dataset.n_rows, 1000, arma::fill::randu);
@@ -184,9 +190,11 @@ TEST_CASE("WeightedNumericLearningTest", "[RandomForestTest]")
 
   // Get performance statistics on test data.
   arma::mat testDataset;
-  data::Load("vc2_test.csv", testDataset);
+  if (!data::Load("vc2_test.csv", testDataset))
+    FAIL("Cannot load dataset vc2_test.csv");
   arma::Row<size_t> testLabels;
-  data::Load("vc2_test_labels.txt", testLabels);
+  if (!data::Load("vc2_test_labels.txt", testLabels))
+    FAIL("Cannot load dataset vc2_test_labels.txt");
 
   arma::Row<size_t> rfPredictions;
   arma::Row<size_t> dtPredictions;
@@ -304,9 +312,11 @@ TEST_CASE("LeafSizeDatasetTest", "[RandomForestTest]")
 {
   // Load the vc2 dataset.
   arma::mat dataset;
-  data::Load("vc2.csv", dataset);
+  if (!data::Load("vc2.csv", dataset))
+    FAIL("Cannot load dataset vc2.csv");
   arma::Row<size_t> labels;
-  data::Load("vc2_labels.txt", labels);
+  if (!data::Load("vc2_labels.txt", labels))
+    FAIL("Cannot load dataset vc2.csv");
 
   // Build a random forest with a leaf size equal to the number of points in the
   // dataset.
@@ -338,9 +348,11 @@ TEST_CASE("RandomForestSerializationTest", "[RandomForestTest]")
 {
   // Load the vc2 dataset.
   arma::mat dataset;
-  data::Load("vc2.csv", dataset);
+  if (!data::Load("vc2.csv", dataset))
+    FAIL("Cannot load dataset vc2.csv");
   arma::Row<size_t> labels;
-  data::Load("vc2_labels.txt", labels);
+  if (!data::Load("vc2_labels.txt", labels))
+    FAIL("Cannot load dataset vc2.csv");
 
   RandomForest<> rf(dataset, labels, 3, 10 /* 10 trees */, 1);
 
@@ -374,8 +386,10 @@ TEST_CASE("RandomForestNumericTrainReturnEntropy", "[RandomForestTest]")
 {
   arma::mat dataset;
   arma::Row<size_t> labels;
-  data::Load("vc2.csv", dataset);
-  data::Load("vc2_labels.txt", labels);
+  if (!data::Load("vc2.csv", dataset))
+    FAIL("Cannot load dataset vc2.csv");
+  if (!data::Load("vc2_labels.txt", labels))
+    FAIL("Cannot load dataset vc2_labels.txt");
 
   // Add some noise.
   arma::mat noise(dataset.n_rows, 1000, arma::fill::randu);
diff --git a/src/mlpack/tests/svd_incremental_test.cpp b/src/mlpack/tests/svd_incremental_test.cpp
index 433a86755f..56a55459d7 100644
--- a/src/mlpack/tests/svd_incremental_test.cpp
+++ b/src/mlpack/tests/svd_incremental_test.cpp
@@ -98,7 +98,8 @@ class SpecificRandomInitialization
 TEST_CASE("SVDIncompleteIncrementalRegularizationTest", "[SVDIncrementalTest]")
 {
   mat dataset;
-  data::Load("GroupLensSmall.csv", dataset);
+  if (!data::Load("GroupLensSmall.csv", dataset))
+    FAIL("Cannot load dataset GroupLensSmall.csv");
 
   // Generate list of locations for batch insert constructor for sparse
   // matrices.
diff --git a/src/mlpack/tests/svdplusplus_test.cpp b/src/mlpack/tests/svdplusplus_test.cpp
index dbf1417397..4ca13e55ad 100644
--- a/src/mlpack/tests/svdplusplus_test.cpp
+++ b/src/mlpack/tests/svdplusplus_test.cpp
@@ -255,7 +255,8 @@ TEST_CASE("SVDplusPlusOutputSizeTest", "[SVDPlusPlusTest]")
 {
   // Load small GroupLens dataset.
   arma::mat data;
-  data::Load("GroupLensSmall.csv", data);
+  if (!data::Load("GroupLensSmall.csv", data))
+    FAIL("Cannot load dataset GroupLensSmall.csv");
 
   // Define useful constants.
   const size_t numUsers = max(data.row(0)) + 1;
@@ -288,7 +289,8 @@ TEST_CASE("SVDPlusPlusCleanDataTest", "[SVDPlusPlusTest]")
 {
   // Load small GroupLens dataset.
   arma::mat data;
-  data::Load("GroupLensSmall.csv", data);
+  if (!data::Load("GroupLensSmall.csv", data))
+    FAIL("Cannot load dataset GroupLensSmall.csv");
 
   // Define useful constants.
   const size_t numUsers = max(data.row(0)) + 1;

From 1b79ef0678a5ed7acdd27eb9cebb5d5fdf1593b6 Mon Sep 17 00:00:00 2001
From: Gopi M Tatiraju <deathcoderx@gmail.com>
Date: Tue, 23 Feb 2021 00:08:27 +0530
Subject: [PATCH 189/253] Update load_save_test.cpp

---
 src/mlpack/tests/load_save_test.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/load_save_test.cpp b/src/mlpack/tests/load_save_test.cpp
index bf7066c04f..015ece667f 100644
--- a/src/mlpack/tests/load_save_test.cpp
+++ b/src/mlpack/tests/load_save_test.cpp
@@ -1415,7 +1415,7 @@ TEST_CASE("RegularCSVDatasetInfoLoad", "[LoadSaveTest]")
     arma::mat one, two;
     DatasetInfo info;
     if (!data::Load(testFiles[i], one))
-      FAIL("Cannot load dataset");
+      FAIL("Cannot load dataset")
     if (!data::Load(testFiles[i], two, info);
       FAIL("Cannot load dataset");
 

From a71a968f17aad63984c2050bca7826d0364b2de4 Mon Sep 17 00:00:00 2001
From: Gopi M Tatiraju <deathcoderx@gmail.com>
Date: Tue, 23 Feb 2021 00:09:24 +0530
Subject: [PATCH 190/253] Update load_save_test.cpp

---
 src/mlpack/tests/load_save_test.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/tests/load_save_test.cpp b/src/mlpack/tests/load_save_test.cpp
index 015ece667f..d4c5f6f58a 100644
--- a/src/mlpack/tests/load_save_test.cpp
+++ b/src/mlpack/tests/load_save_test.cpp
@@ -1415,8 +1415,8 @@ TEST_CASE("RegularCSVDatasetInfoLoad", "[LoadSaveTest]")
     arma::mat one, two;
     DatasetInfo info;
     if (!data::Load(testFiles[i], one))
-      FAIL("Cannot load dataset")
-    if (!data::Load(testFiles[i], two, info);
+      FAIL("Cannot load dataset");
+    if (!data::Load(testFiles[i], two, info)
       FAIL("Cannot load dataset");
 
     // Check that the matrices contain the same information.

From 656c29ba6d31ca237199d48f9f6a046123bf9e11 Mon Sep 17 00:00:00 2001
From: Gopi M Tatiraju <deathcoderx@gmail.com>
Date: Tue, 23 Feb 2021 01:35:31 +0530
Subject: [PATCH 191/253] Update load_save_test.cpp

---
 src/mlpack/tests/load_save_test.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/load_save_test.cpp b/src/mlpack/tests/load_save_test.cpp
index d4c5f6f58a..602533a84b 100644
--- a/src/mlpack/tests/load_save_test.cpp
+++ b/src/mlpack/tests/load_save_test.cpp
@@ -1416,7 +1416,7 @@ TEST_CASE("RegularCSVDatasetInfoLoad", "[LoadSaveTest]")
     DatasetInfo info;
     if (!data::Load(testFiles[i], one))
       FAIL("Cannot load dataset");
-    if (!data::Load(testFiles[i], two, info)
+    if (!data::Load(testFiles[i], two, info))
       FAIL("Cannot load dataset");
 
     // Check that the matrices contain the same information.

From 0180ca4f09b82aa875cfc82a59205d492ddb0d4f Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 23 Feb 2021 12:38:19 +0530
Subject: [PATCH 192/253]         Changed author name format

---
 src/mlpack/methods/ann/layer/isrlu.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu.hpp b/src/mlpack/methods/ann/layer/isrlu.hpp
index b0a786c6ba..fb4cd65947 100644
--- a/src/mlpack/methods/ann/layer/isrlu.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu.hpp
@@ -8,8 +8,8 @@
  *
  * @code
  * @article{
- *   author  = {Carlile, Brad and Delamarter, Guy and Kinney, Paul and Marti,
- *              Akiko and Whitney, Brian},
+ *   author  = {Carlile, Brad, Delamarter, Guy, Kinney, Paul, Marti,
+ *              Akiko, Whitney, Brian},
  *   title   = {Improving deep learning by inverse square root linear units (ISRLUs)},
  *   year    = {2017},
  *   url     = {https://arxiv.org/pdf/1710.09967.pdf}

From 5e695f99c8ea389fcf9b08080c51ce8b0ecc5ad9 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 23 Feb 2021 13:55:23 +0530
Subject: [PATCH 193/253] Removed  copying

---
 .../methods/ann/layer/pixel_shuffle_impl.hpp      | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 9edb09c2eb..89ae8b79d5 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -61,12 +61,10 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
   output.zeros(outputHeight * outputWidth * sizeOut, batchSize);
   for (size_t n = 0; n < batchSize; n++)
   {
-    arma::mat inputImage = input.col(n);
-    arma::mat outputImage = output.col(n);
-    arma::cube inputTemp(const_cast<arma::mat&>(inputImage).memptr(), height,
-        width, size, false, false);
-    arma::cube outputTemp(const_cast<arma::mat&>(outputImage).memptr(),
-        outputHeight, outputWidth, sizeOut, false, false);
+    arma::cube inputTemp(const_cast<arma::mat&>(input).memptr(), height,
+        width, size * batchSize, false, false);
+    arma::cube outputTemp(const_cast<arma::mat&>(output).memptr(),
+        outputHeight, outputWidth, sizeOut * batchSize, false, false);
 
     for (size_t c = 0; c < sizeOut ; c++)
     {
@@ -78,13 +76,12 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
           size_t width_index = w / upscaleFactor;
           size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
               (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
-          outputTemp(w, h, c) = inputTemp(width_index, height_index,
-              channel_index);
+          outputTemp(w, h, c + n * sizeOut) = inputTemp(width_index, height_index,
+              channel_index + n * size);
         }
       }
     }
 
-    output.col(n) = outputImage;
   }
 }
 

From 4eff650f9d90b236139117b4c6a69acfbb8f0329 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 23 Feb 2021 15:16:44 +0530
Subject: [PATCH 194/253]      Remove copying in backward function.

---
 .../methods/ann/layer/pixel_shuffle_impl.hpp   | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 89ae8b79d5..7bcf985f45 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -66,7 +66,7 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
     arma::cube outputTemp(const_cast<arma::mat&>(output).memptr(),
         outputHeight, outputWidth, sizeOut * batchSize, false, false);
 
-    for (size_t c = 0; c < sizeOut ; c++)
+    for (size_t c = 0; c < sizeOut; c++)
     {
       for (size_t h = 0; h < outputHeight; h++)
       {
@@ -93,14 +93,12 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
   g.zeros(arma::size(input));
   for (size_t n = 0; n < batchSize; n++)
   {
-    arma::mat gyImage = gy.col(n);
-    arma::mat gImage = g.col(n);
-    arma::cube gyTemp(const_cast<arma::mat&>(gyImage).memptr(), outputHeight,
-        outputWidth, sizeOut, false, false);
-    arma::cube gTemp(const_cast<arma::mat&>(gImage).memptr(), height, width,
-        size, false, false);
+    arma::cube gyTemp(const_cast<arma::mat&>(gy).memptr(), outputHeight,
+        outputWidth, sizeOut * batchSize, false, false);
+    arma::cube gTemp(const_cast<arma::mat&>(g).memptr(), height, width,
+        size * batchSize, false, false);
 
-    for (size_t c = 0; c < sizeOut ; c++)
+    for (size_t c = 0; c < sizeOut; c++)
     {
       for (size_t h = 0; h < outputHeight; h++)
       {
@@ -110,12 +108,12 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
           size_t width_index = w / upscaleFactor;
           size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
               (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
-          gTemp(width_index, height_index, channel_index) = gyTemp(w, h, c);
+          gTemp(width_index, height_index, channel_index + n * sizeOut) = gyTemp(w, h,
+              c + n * size);
         }
       }
     }
 
-    g.col(n) = gImage;
   }
 }
 

From 34ca85cad3cbf3dd60397b632f6cbc2368a79839 Mon Sep 17 00:00:00 2001
From: Gopi M Tatiraju <deathcoderx@gmail.com>
Date: Tue, 23 Feb 2021 16:00:09 +0530
Subject: [PATCH 195/253] Apply suggestions from code review

Co-authored-by: Anush Kini <33577829+Abilityguy@users.noreply.github.com>
---
 src/mlpack/tests/feedforward_network_test.cpp | 21 +++++++++----------
 src/mlpack/tests/krann_search_test.cpp        |  2 +-
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_test.cpp b/src/mlpack/tests/feedforward_network_test.cpp
index c7386261bf..629df89749 100644
--- a/src/mlpack/tests/feedforward_network_test.cpp
+++ b/src/mlpack/tests/feedforward_network_test.cpp
@@ -161,7 +161,7 @@ TEST_CASE("FFVanillaNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
+  if (!data::Load("thyroid_train.csv", trainData))
     FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
@@ -310,7 +310,7 @@ TEST_CASE("DropoutNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
+  if (!data::Load("thyroid_train.csv", trainData))
     FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
@@ -413,7 +413,7 @@ TEST_CASE("DropConnectNetworkTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
+  if (!data::Load("thyroid_train.csv", trainData))
     FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
@@ -504,8 +504,8 @@ TEST_CASE("FFSerializationTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
-      FAIL("Cannot open thyroid_train.csv");
+  if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -555,8 +555,8 @@ TEST_CASE("CustomLayerTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
-      FAIL("Cannot open thyroid_train.csv");
+  if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -636,8 +636,8 @@ TEST_CASE("FFNTrainReturnObjective", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
-      FAIL("Cannot open thyroid_train.csv");
+  if (!data::Load("thyroid_train.csv", trainData))
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -708,7 +708,7 @@ TEST_CASE("OptimizerTest", "[FeedForwardNetworkTest]")
 {
   // Load the dataset.
   arma::mat trainData;
-    if (!data::Load("thyroid_train.csv", trainData))
+  if (!data::Load("thyroid_train.csv", trainData))
     FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
@@ -730,4 +730,3 @@ TEST_CASE("OptimizerTest", "[FeedForwardNetworkTest]")
   ens::DE opt(200, 1000, 0.6, 0.8, 1e-5);
   model.Train(trainData, trainLabels, opt);
 }
-
diff --git a/src/mlpack/tests/krann_search_test.cpp b/src/mlpack/tests/krann_search_test.cpp
index 5bc13eb952..29aa5335ff 100644
--- a/src/mlpack/tests/krann_search_test.cpp
+++ b/src/mlpack/tests/krann_search_test.cpp
@@ -43,7 +43,7 @@ TEST_CASE("NaiveGuaranteeTest", "[KRANNTest]")
   RASearch<> rsRann(refData, true, false, 1.0);
 
   arma::mat qrRanks;
-    if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
+  if (!data::Load("rann_test_qr_ranks.csv", qrRanks, false, false)) // No transpose.
     FAIL("Cannot load dataset rann_test_qr_ranks.csv");
 
   size_t numRounds = 1000;

From 4f9eb2845c7d2f94886ead42119e2be2c97f8561 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 23 Feb 2021 16:47:45 +0530
Subject: [PATCH 196/253] Update pixel_shuffle_impl.hpp

---
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 7bcf985f45..c062c2a029 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -76,8 +76,8 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
           size_t width_index = w / upscaleFactor;
           size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
               (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
-          outputTemp(w, h, c + n * sizeOut) = inputTemp(width_index, height_index,
-              channel_index + n * size);
+          outputTemp(w, h, c + n * size) = inputTemp(width_index, height_index,
+              channel_index + n * sizeOut);
         }
       }
     }

From cd167d98ad75c45bb9ef72589807450a51ce57a4 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Tue, 23 Feb 2021 18:13:32 +0530
Subject: [PATCH 197/253] Update pixel_shuffle_impl.hpp

---
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index c062c2a029..7aa976e4d6 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -76,8 +76,8 @@ void PixelShuffle<InputDataType, OutputDataType>::Forward(
           size_t width_index = w / upscaleFactor;
           size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
               (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
-          outputTemp(w, h, c + n * size) = inputTemp(width_index, height_index,
-              channel_index + n * sizeOut);
+          outputTemp(w, h, c + n * sizeOut) = inputTemp(width_index, height_index,
+              channel_index + n * size);
         }
       }
     }
@@ -108,8 +108,8 @@ void PixelShuffle<InputDataType, OutputDataType>::Backward(
           size_t width_index = w / upscaleFactor;
           size_t channel_index = (upscaleFactor * (h % upscaleFactor)) +
               (w % upscaleFactor) + (c * std::pow(upscaleFactor, 2));
-          gTemp(width_index, height_index, channel_index + n * sizeOut) = gyTemp(w, h,
-              c + n * size);
+          gTemp(width_index, height_index, channel_index + n * size) = gyTemp(w, h,
+              c + n * sizeOut);
         }
       }
     }

From b1cb6255e68328164f0452a70c5b45ab648225a9 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Wed, 24 Feb 2021 11:00:31 +0530
Subject: [PATCH 198/253] changed  authors name

Co-authored-by: Ryan Birmingham <birm@rbirm.us>
---
 src/mlpack/methods/ann/layer/isrlu.hpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/methods/ann/layer/isrlu.hpp b/src/mlpack/methods/ann/layer/isrlu.hpp
index fb4cd65947..b0a786c6ba 100644
--- a/src/mlpack/methods/ann/layer/isrlu.hpp
+++ b/src/mlpack/methods/ann/layer/isrlu.hpp
@@ -8,8 +8,8 @@
  *
  * @code
  * @article{
- *   author  = {Carlile, Brad, Delamarter, Guy, Kinney, Paul, Marti,
- *              Akiko, Whitney, Brian},
+ *   author  = {Carlile, Brad and Delamarter, Guy and Kinney, Paul and Marti,
+ *              Akiko and Whitney, Brian},
  *   title   = {Improving deep learning by inverse square root linear units (ISRLUs)},
  *   year    = {2017},
  *   url     = {https://arxiv.org/pdf/1710.09967.pdf}

From 95e756dbb4f5e400dd58e2d7ba71a1088915be14 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Thu, 25 Feb 2021 18:15:22 +0530
Subject: [PATCH 199/253] Adding co-author

---
 src/mlpack/methods/ann/layer/pixel_shuffle.hpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
index 48d89c2fe2..f425d7c508 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle.hpp
@@ -1,6 +1,7 @@
 /**
  * @file methods/ann/layer/pixel_shuffle.hpp
  * @author Anjishnu Mukherjee
+ * @author Abhinav Anand
  *
  * Definition of the PixelShuffle class.
  *

From 6e040a48aebb4ec213e069473e81798c1a418a09 Mon Sep 17 00:00:00 2001
From: abh2k <41710346+abh2k@users.noreply.github.com>
Date: Thu, 25 Feb 2021 18:16:42 +0530
Subject: [PATCH 200/253]       Adding co-author

---
 src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
index 7aa976e4d6..f56f708981 100644
--- a/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
+++ b/src/mlpack/methods/ann/layer/pixel_shuffle_impl.hpp
@@ -1,6 +1,7 @@
 /**
  * @file methods/ann/layer/pixel_shuffle_impl.hpp
  * @author Anjishnu Mukherjee
+ * @author Abhinav Anand
  *
  * Implementation of the PixelShuffle class.
  *

From 73bb3515ce29fb165606431f6d55a9f2aacea4ee Mon Sep 17 00:00:00 2001
From: Anush Kini <33577829+Abilityguy@users.noreply.github.com>
Date: Fri, 26 Feb 2021 16:53:17 +0530
Subject: [PATCH 201/253] Some review changes implemented.

Changes implemented for the following reviews in 2746:

1. Using ```cols``` and ```subvec``` to avoid the for loop.
2. Changed instances of ```arma::row``` to ```arma::Row```.
3. Logic added where ```order``` is initialised only when ```shuffleData``` is true.
4. input fields made ```const```.
5. Removed extra new line where the line was less than 80 characters long.
6. Spacing fix (Refer line 566 in changed file).
---
 src/mlpack/core/data/split_data.hpp | 151 +++++++++++++++++-----------
 1 file changed, 93 insertions(+), 58 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index f4a75d871b..370128dfc6 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -143,7 +143,7 @@ void StratifiedSplit(const arma::Mat<T>& input,
  * @endcode
  *
  * @tparam T Type of the elements of the input matrix.
- * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::row,
+ * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::Row,
  *       arma::Cube or arma::SpMat.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
@@ -170,28 +170,39 @@ void Split(const arma::Mat<T>& input,
   const size_t trainSize = input.n_cols - testSize;
   trainData.set_size(input.n_rows, trainSize);
   testData.set_size(input.n_rows, testSize);
+  trainLabel.set_size(1, trainSize);
+  testLabel.set_size(1, testSize);
 
-  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
-      input.n_cols);
   if (shuffleData)
-    order = arma::shuffle(order);
-
-  if (trainSize > 0)
   {
-    trainLabel.set_size(1, trainSize);
-    trainData = input.cols(order.subvec(0, trainSize - 1));
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0, input.n_cols - 1,
+        input.n_cols));
 
-    for (size_t i = 0; i < trainSize; ++i)
-      trainLabel(0, i) = inputLabel(0, order(i));
+    if (trainSize > 0)
+    {
+      trainData = input.cols(order.subvec(0, trainSize - 1));
+      trainLabel = inputLabel.cols(order.subvec(0, trainSize - 1));
+    }
+
+    if (trainSize < input.n_cols)
+    {
+      testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
+      testLabel = inputLabel.cols(order.subvec(trainSize, input.n_cols - 1));
+    }
   }
-
-  if (trainSize < input.n_cols)
+  else
   {
-    testLabel.set_size(1, testSize);
-    testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
+    if (trainSize > 0)
+    {
+      trainData = input.cols(0, trainSize - 1);
+      trainLabel = inputLabel.cols(0, trainSize - 1);
+    }
 
-    for (size_t i = trainSize; i < input.n_cols; ++i)
-      testLabel(0, i - trainSize) = inputLabel(0, order(i));
+    if (trainSize < input.n_cols)
+    {
+      testData = input.cols(trainSize, input.n_cols - 1);
+      testLabel = inputLabel.cols(trainSize, inputLabel.n_cols - 1);
+    }
   }
 }
 
@@ -265,7 +276,7 @@ void Split(const arma::Mat<T>& input,
  * @endcode
  *
  * @tparam T Type of the elements of the input matrix.
- * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::row,
+ * @tparam LabelsType Type of input labels. It can be arma::Mat, arma::Row,
  *       arma::Cube or arma::SpMat.
  * @param input Input dataset to split.
  * @param inputLabel Input labels to split.
@@ -362,8 +373,7 @@ Split(const arma::Mat<T>& input,
  *
  * // Split the dataset into a training and test set, with 30% of the data being
  * // held out for the test set.
- * Split(input, label, trainData,
- *                testData, trainLabel, testLabel, 0.3);
+ * Split(input, label, trainData, testData, trainLabel, testLabel, 0.3);
  * @endcode
  *
  * @param input Input dataset to split.
@@ -380,46 +390,56 @@ template <typename FieldType,
           typename = std::enable_if_t<
               arma::is_Col<typename FieldType::object_type>::value ||
               arma::is_Mat_only<typename FieldType::object_type>::value>>
-void Split(FieldType& input,
-           arma::field<arma::vec>& inputLabel,
+void Split(const FieldType& input,
+           const arma::field<arma::vec>& inputLabel,
            FieldType& trainData,
-           arma::field<arma::vec>& trainLabels,
+           arma::field<arma::vec>& trainLabel,
            FieldType& testData,
-           arma::field<arma::vec>& testLabels,
+           arma::field<arma::vec>& testLabel,
            const double testRatio,
            const bool shuffleData = true)
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
-
-  trainData.set_size(1, trainSize);
-  testData.set_size(1, testSize);
-
-  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
-      input.n_cols);
+  trainLabel.set_size(1, trainSize);
+  testLabel.set_size(1, testSize);
 
   if (shuffleData)
-    order = arma::shuffle(order);
-
-  if (trainSize > 0)
   {
-    trainLabels.set_size(1, trainSize);
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
 
-    for (size_t i = 0; i < trainSize; ++i)
-      trainData[i] = input(0, order(i));
+    if (trainSize > 0)
+    {
+      trainData = input.cols(order.subvec(0, trainSize - 1));
 
-    for (size_t i = 0; i < trainSize; ++i)
-      trainLabels(0, i) = inputLabel(0, order(i));
+      for (size_t i = 0; i < trainSize; ++i)
+        trainLabel(0, i) = inputLabel(0, order(i));
+    }
+
+    if (trainSize < input.n_cols)
+    {
+      testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
+
+      for (size_t i = trainSize; i < input.n_cols; ++i)
+        testLabel(0, i - trainSize) = inputLabel(0, order(i));
+    }
   }
-
-  if (testSize <= input.n_cols)
+  else
   {
-    for (size_t i = trainSize; i < input.n_cols - 1; ++i)
-     testData[i - trainSize] = input(0, order(i));
+    if (trainSize > 0)
+    {
+      trainData = input.cols(0, trainSize - 1);
+      for (size_t i = 0; i < trainSize; ++i)
+        trainLabel(0, i) = inputLabel(0, i);
+    }
 
-    testLabels.set_size(1, testSize);
-    for (size_t i = trainSize; i < input.n_cols; ++i)
-      testLabels(0, i - trainSize) = inputLabel(0, order(i));
+    if (trainSize < input.n_cols)
+    {
+      testData = input.cols(trainSize, input.n_cols - 1);
+      for (size_t i = trainSize; i < input.n_cols; ++i)
+        testLabel(0, i - trainSize) = inputLabel(0, i);
+    }
   }
 }
 
@@ -467,21 +487,36 @@ void Split(const FieldType& input,
   trainData.set_size(1, trainSize);
   testData.set_size(1, testSize);
 
-  arma::uvec order = arma::linspace<arma::uvec>(0, input.n_cols - 1,
-      input.n_cols);
   if (shuffleData)
-    order = arma::shuffle(order);
-
-  if (trainSize > 0)
   {
-    for (size_t i = 0; i < trainSize; i++)
-       trainData[i] = input(0, order(i));
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+
+    if (trainSize > 0)
+    {
+      for (size_t i = 0; i < trainSize; i++)
+        trainData[i] = input(0, order(i));
+    }
+
+    if (trainSize < input.n_cols)
+    {
+      for (size_t i = trainSize; i < input.n_cols - 1; ++i)
+         testData[i - trainSize] = input(0, order(i));
+    }
   }
-
-  if (testSize <= input.n_cols)
+  else
   {
-    for (size_t i = trainSize; i < input.n_cols - 1; ++i)
-       testData[i - trainSize] = input(0, order(i));
+    if (trainSize > 0)
+    {
+      for (size_t i = 0; i < trainSize; i++)
+        trainData[i] = input(0, i);
+    }
+
+    if (trainSize < input.n_cols)
+    {
+      for (size_t i = trainSize; i < input.n_cols - 1; ++i)
+         testData[i - trainSize] = input(0, i);
+    }
   }
 }
 
@@ -517,8 +552,8 @@ template <class FieldType,
               arma::is_Col<typename FieldType::object_type>::value ||
               arma::is_Mat_only<typename FieldType::object_type>::value>>
 std::tuple<FieldType, FieldType, FieldType, FieldType>
-Split(FieldType& input,
-      arma::field<arma::vec>& inputLabel,
+Split(const FieldType& input,
+      const arma::field<arma::vec>& inputLabel,
       const double testRatio,
       const bool shuffleData = true)
 {
@@ -528,7 +563,7 @@ Split(FieldType& input,
   arma::field<arma::vec> testLabel;
 
   Split(input, inputLabel, trainData, testData, trainLabel, testLabel,
-    testRatio, shuffleData);
+      testRatio, shuffleData);
 
   return std::make_tuple(std::move(trainData),
                          std::move(testData),

From e837763302237357b0b0fc2eadfb1ce9dfc6a4ff Mon Sep 17 00:00:00 2001
From: Anush Kini <33577829+Abilityguy@users.noreply.github.com>
Date: Fri, 26 Feb 2021 17:02:22 +0530
Subject: [PATCH 202/253] Review changes made to test suite

1. Restored blank lines that were removed in a previous commit.
2. Edited test ```SplitMatrixLabeledDataResultMat``` to ```SplitMatrixLabeledData``` and made changes to fix this failing test.
---
 src/mlpack/tests/split_data_test.cpp | 97 ++++++++++++++++------------
 1 file changed, 54 insertions(+), 43 deletions(-)

diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 74862469ba..1419756e5b 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -121,29 +121,6 @@ TEST_CASE("SplitDataResultMat", "[SplitDataTest]")
   CheckMatrices(input, concat);
 }
 
-TEST_CASE("SplitDataResultField", "[SplitDataTest]")
-{
-  field<mat> input(1, 2);
-
-  mat matA(2, 10);
-  mat matB(2, 10);
-
-  size_t count = 0; // Counter for unique sequential values.
-  matA.imbue([&count]() { return ++count; });
-  matB.imbue([&count]() { return ++count; });
-
-  input(0, 0) = matA;
-  input(0, 1) = matB;
-
-  const auto value = Split(input, 0.5, false);
-  REQUIRE(std::get<0>(value).n_cols == 1); // Train data.
-  REQUIRE(std::get<1>(value).n_cols == 1); // Test data.
-
-  field<mat> concat = {std::get<0>(value)(0), std::get<1>(value)(0)};
-  // Order matters here.
-  CheckFields(input, concat);
-}
-
 TEST_CASE("ZeroRatioSplitData", "[SplitDataTest]")
 {
   mat input(2, 10);
@@ -198,26 +175,6 @@ TEST_CASE("SplitLabeledDataResultMat", "[SplitDataTest]")
   CheckDuplication(std::get<2>(value), std::get<3>(value));
 }
 
-TEST_CASE("SplitMatrixLabeledDataResultMat", "[SplitDataTest]")
-{
-  mat input(2, 10);
-  input.randu();
-
-  const mat labels(2, 10, fill::randu);
-
-  const auto value = Split(input, labels, 0.2);
-  REQUIRE(std::get<0>(value).n_cols == 8);
-  REQUIRE(std::get<1>(value).n_cols == 2);
-  REQUIRE(std::get<2>(value).n_cols == 8);
-  REQUIRE(std::get<3>(value).n_cols == 2);
-
-  mat input_concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
-  mat labels_concat = arma::join_rows(std::get<2>(value), std::get<3>(value));
-  // Order matters here.
-  CheckMatrices(input, input_concat);
-  CheckMatrices(labels, labels_concat);
-}
-
 /**
  * The same test as above, but on a larger dataset.
  */
@@ -334,28 +291,34 @@ TEST_CASE("StratifiedSplitLargerDataResultTest", "[SplitDataTest]")
 {
   mat input(3, 480);
   input.randu();
+
   // 256 0s, 128 1s, 64 2s and 32 3s.
   Row<size_t> zero_label(256);
   Row<size_t> one_label(128);
   Row<size_t> two_label(64);
   Row<size_t> three_label(32);
+
   zero_label.fill(0);
   one_label.fill(1);
   two_label.fill(2);
   three_label.fill(3);
+
   Row<size_t> labels = arma::join_rows(zero_label, one_label);
   labels = arma::join_rows(labels, two_label);
   labels = arma::join_rows(labels, three_label);
   const double test_ratio = 0.3;
+
   const auto value = Split(input, labels, test_ratio, false, true);
   REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 0)).n_rows == 180);
   REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 1)).n_rows == 90);
   REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 2)).n_rows == 45);
   REQUIRE(static_cast<uvec>(find(std::get<2>(value) == 3)).n_rows == 23);
+
   REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 0)).n_rows == 76);
   REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 1)).n_rows == 38);
   REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 2)).n_rows == 19);
   REQUIRE(static_cast<uvec>(find(std::get<3>(value) == 3)).n_rows == 9);
+
   mat concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
   CheckMatEqual(input, concat);
 }
@@ -376,3 +339,51 @@ TEST_CASE("StratifiedSplitRunTimeErrorTest", "[SplitDataTest]")
   REQUIRE_THROWS_AS(Split(input, labels, test_ratio, false, true),
       std::runtime_error);
 }
+
+/*
+ * Split with input of type field<>.
+ */
+TEST_CASE("SplitDataResultField", "[SplitDataTest]")
+{
+  field<mat> input(1, 2);
+
+  mat matA(2, 10);
+  mat matB(2, 10);
+
+  size_t count = 0; // Counter for unique sequential values.
+  matA.imbue([&count]() { return ++count; });
+  matB.imbue([&count]() { return ++count; });
+
+  input(0, 0) = matA;
+  input(0, 1) = matB;
+
+  const auto value = Split(input, 0.5, false);
+  REQUIRE(std::get<0>(value).n_cols == 1); // Train data.
+  REQUIRE(std::get<1>(value).n_cols == 1); // Test data.
+
+  field<mat> concat = {std::get<0>(value)(0), std::get<1>(value)(0)};
+  // Order matters here.
+  CheckFields(input, concat);
+}
+
+/**
+ * Test for Split() with labels of type arma::Mat with shuffleData = False.
+ */
+TEST_CASE("SplitMatrixLabeledData", "[SplitDataTest]")
+{
+  const mat input(2, 10, fill::randu);
+  const mat labels(2, 10, fill::randu);
+
+  const auto value = Split(input, labels, 0.2, false);
+  REQUIRE(std::get<0>(value).n_cols == 8);
+  REQUIRE(std::get<1>(value).n_cols == 2);
+  REQUIRE(std::get<2>(value).n_cols == 8);
+  REQUIRE(std::get<3>(value).n_cols == 2);
+
+  mat input_concat = arma::join_rows(std::get<0>(value), std::get<1>(value));
+  mat labels_concat = arma::join_rows(std::get<2>(value), std::get<3>(value));
+
+  // Order matters here.
+  CheckMatrices(input, input_concat);
+  CheckMatrices(labels, labels_concat);
+}

From c74ef9cc22a345a4a44b27bcf4c4c6fc62239b3d Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Sat, 27 Feb 2021 18:13:01 +0530
Subject: [PATCH 203/253] order is init in Stratified Split only when
 shuffleData is true

---
 src/mlpack/core/data/split_data.hpp | 67 ++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 24 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 370128dfc6..1c7b6578fe 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -23,7 +23,7 @@ namespace data {
  * It is recommended to have the input labels between the range [0, n) where n
  * is the number of different labels. The NormalizeLabels() function in
  * mlpack::data can be used for this.
- * Expects labels to be of type arma::Row<>.
+ * Expects labels to be of type arma::Row<> or arma::Col<>.
  * Throws a runtime error if this is not the case.
  * Example usage below. This overload places the stratified dataset into the
  * four output parameters given (trainData, testData, trainLabel,
@@ -65,7 +65,9 @@ void StratifiedSplit(const arma::Mat<T>& input,
                      const double testRatio,
                      const bool shuffleData = true)
 {
-  if (!arma::is_Row<LabelsType>::value)
+  const bool typeCheck = (arma::is_Row<LabelsType>::value)
+      || (arma::is_Col<LabelsType>::value);
+  if (!typeCheck)
     throw std::runtime_error("data::Split(): when stratified sampling is done, "
         "labels must have type `arma::Row<>`!");
   size_t trainIdx = 0;
@@ -79,18 +81,8 @@ void StratifiedSplit(const arma::Mat<T>& input,
   labelCounts.zeros(maxLabel+1);
   testLabelCounts.zeros(maxLabel+1);
 
-  arma::uvec order =
-      arma::linspace<arma::uvec>(0, input.n_cols - 1, input.n_cols);
-
-  if (shuffleData)
-  {
-    order = arma::shuffle(order);
-  }
-
   for (typename LabelsType::elem_type label : inputLabel)
-  {
     ++labelCounts[label];
-  }
 
   for (arma::uword labelCount : labelCounts)
   {
@@ -103,21 +95,47 @@ void StratifiedSplit(const arma::Mat<T>& input,
   trainLabel.set_size(trainSize);
   testLabel.set_size(testSize);
 
-  for (arma::uword i : order)
+  if (shuffleData)
   {
-    typename LabelsType::elem_type label = inputLabel[i];
-    if (testLabelCounts[label] < floor(labelCounts[label] * testRatio))
+    arma::uvec order = arma::shuffle(
+        arma::linspace<arma::uvec>(0, input.n_cols - 1, input.n_cols));
+
+    for (arma::uword i : order)
     {
-      testLabelCounts[label] += 1;
-      testData.col(testIdx) = input.col(i);
-      testLabel[testIdx] = inputLabel[i];
-      testIdx += 1;
+      typename LabelsType::elem_type label = inputLabel[i];
+      if (testLabelCounts[label] < floor(labelCounts[label] * testRatio))
+      {
+        testLabelCounts[label] += 1;
+        testData.col(testIdx) = input.col(i);
+        testLabel[testIdx] = inputLabel[i];
+        testIdx += 1;
+      }
+      else
+      {
+        trainData.col(trainIdx) = input.col(i);
+        trainLabel[trainIdx] = inputLabel[i];
+        trainIdx += 1;
+      }
     }
-    else
+  }
+  else
+  {
+    for (arma::uword i = 0; i < input.n_cols; i++)
     {
-      trainData.col(trainIdx) = input.col(i);
-      trainLabel[trainIdx] = inputLabel[i];
-      trainIdx += 1;
+      typename LabelsType::elem_type label = inputLabel[i];
+      if (testLabelCounts[label] < floor(labelCounts[label] * testRatio))
+      {
+        testLabelCounts[label] += 1;
+        testData.col(testIdx) = input.col(i);
+        testLabel[testIdx] = inputLabel[i];
+        testIdx += 1;
+      }
+      else
+      {
+        trainData.col(trainIdx) = input.col(i);
+        trainLabel[trainIdx] = inputLabel[i];
+        trainIdx += 1;
+      }
     }
   }
 }
@@ -285,7 +303,8 @@ void Split(const arma::Mat<T>& input,
  *     sample is visited in linear order. (Default true).
  * @param stratifyData If true, the train and test splits are stratified
  *     so that the ratio of each class in the training and test sets is the same
- *     as in the original dataset. Expects labels to be of type arma::Row<>.
+ *     as in the original dataset. Expects labels to be of type arma::Row<> or
+ *     arma::Col<>.
  * @return std::tuple containing trainData (arma::Mat<T>), testData
  *      (arma::Mat<T>), trainLabel (arma::Row<U>), and testLabel (arma::Row<U>).
  */

From 26e311ac7286bb808b7a063e83db1578ec0184b2 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Sat, 27 Feb 2021 20:41:54 +0530
Subject: [PATCH 204/253] Added test with label of type field and other review
 fixes

---
 src/mlpack/core/data/split_data.hpp  | 38 +++++++++++++++++-----------
 src/mlpack/tests/split_data_test.cpp | 36 +++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 1c7b6578fe..da4c240ca2 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -420,8 +420,11 @@ void Split(const FieldType& input,
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
-  trainLabel.set_size(1, trainSize);
-  testLabel.set_size(1, testSize);
+
+  trainData.set_size(1, trainSize);
+  testData.set_size(1, testSize);
+  trainLabel.set_size(trainSize);
+  testLabel.set_size(testSize);
 
   if (shuffleData)
   {
@@ -430,34 +433,39 @@ void Split(const FieldType& input,
 
     if (trainSize > 0)
     {
-      trainData = input.cols(order.subvec(0, trainSize - 1));
-
       for (size_t i = 0; i < trainSize; ++i)
-        trainLabel(0, i) = inputLabel(0, order(i));
+      {
+        trainData[i] = input(0, order(i));
+        trainLabel[i] = inputLabel(0, order(i));
+      }
     }
-
     if (trainSize < input.n_cols)
     {
-      testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
-
       for (size_t i = trainSize; i < input.n_cols; ++i)
-        testLabel(0, i - trainSize) = inputLabel(0, order(i));
+      {
+        testData[i - trainSize] = input(0, order(i));
+        testLabel[i - trainSize] = inputLabel(0, order(i));
+      }
     }
   }
   else
   {
     if (trainSize > 0)
     {
-      trainData = input.cols(0, trainSize - 1);
       for (size_t i = 0; i < trainSize; ++i)
-        trainLabel(0, i) = inputLabel(0, i);
+      {
+        trainData[i] = input(0, i);
+        trainLabel[i] = inputLabel(0, i);
+      }
     }
 
     if (trainSize < input.n_cols)
     {
-      testData = input.cols(trainSize, input.n_cols - 1);
       for (size_t i = trainSize; i < input.n_cols; ++i)
-        testLabel(0, i - trainSize) = inputLabel(0, i);
+      {
+        testData[i - trainSize] = input(0, i);
+        testLabel[i - trainSize] = inputLabel(0, i);
+      }
     }
   }
 }
@@ -570,7 +578,7 @@ template <class FieldType,
           class = std::enable_if_t<
               arma::is_Col<typename FieldType::object_type>::value ||
               arma::is_Mat_only<typename FieldType::object_type>::value>>
-std::tuple<FieldType, FieldType, FieldType, FieldType>
+std::tuple<FieldType, FieldType, arma::field<arma::vec>, arma::field<arma::vec>>
 Split(const FieldType& input,
       const arma::field<arma::vec>& inputLabel,
       const double testRatio,
@@ -581,7 +589,7 @@ Split(const FieldType& input,
   arma::field<arma::vec> trainLabel;
   arma::field<arma::vec> testLabel;
 
-  Split(input, inputLabel, trainData, testData, trainLabel, testLabel,
+  Split(input, inputLabel, trainData, trainLabel, testData, testLabel,
       testRatio, shuffleData);
 
   return std::make_tuple(std::move(trainData),
diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 1419756e5b..8d2b5e470e 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -341,7 +341,7 @@ TEST_CASE("StratifiedSplitRunTimeErrorTest", "[SplitDataTest]")
 }
 
 /*
- * Split with input of type field<>.
+ * Split with input of type field<mat>.
  */
 TEST_CASE("SplitDataResultField", "[SplitDataTest]")
 {
@@ -387,3 +387,37 @@ TEST_CASE("SplitMatrixLabeledData", "[SplitDataTest]")
   CheckMatrices(input, input_concat);
   CheckMatrices(labels, labels_concat);
 }
+
+/*
+ * Split with input of type field<mat> and label of type field<vec>.
+ */
+TEST_CASE("SplitLabeledDataResultField", "[SplitDataTest]")
+{
+  field<mat> input(1, 2);
+  field<vec> label(1, 2);
+
+  mat matA(2, 10, fill::randu);
+  mat matB(2, 10, fill::randu);
+
+  vec vecA(10, fill::randu);
+  vec vecB(10, fill::randu);
+
+  input(0, 0) = matA;
+  input(0, 1) = matB;
+
+  label(0, 0) = vecA;
+  label(0, 1) = vecB;
+
+  const auto value = Split(input, label, 0.5, false);
+  REQUIRE(std::get<0>(value).n_cols == 1); // Train data.
+  REQUIRE(std::get<1>(value).n_cols == 1); // Test data.
+  REQUIRE(std::get<2>(value).n_cols == 1); // Train label.
+  REQUIRE(std::get<3>(value).n_cols == 1); // Test label.
+
+  field<mat> input_concat = {std::get<0>(value)(0), std::get<1>(value)(0)};
+  field<vec> label_concat = {std::get<2>(value)(0), std::get<3>(value)(0)};
+
+  // Order matters here.
+  CheckFields(input, input_concat);
+  CheckFields(label, label_concat);
+}

From 332bbd4ea27cf3f397e8fbae41b724b7f193082d Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Sun, 12 Apr 2020 23:32:58 +0530
Subject: [PATCH 205/253] CheckSameSize() added

---
 src/mlpack/core/util/CMakeLists.txt |  1 +
 src/mlpack/core/util/facilities.hpp | 71 +++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)
 create mode 100644 src/mlpack/core/util/facilities.hpp

diff --git a/src/mlpack/core/util/CMakeLists.txt b/src/mlpack/core/util/CMakeLists.txt
index 19ddff3293..4872652826 100644
--- a/src/mlpack/core/util/CMakeLists.txt
+++ b/src/mlpack/core/util/CMakeLists.txt
@@ -33,6 +33,7 @@ set(SOURCES
   to_lower.hpp
   version.hpp
   version.cpp
+  facilities.hpp
 )
 
 # add directory name to sources
diff --git a/src/mlpack/core/util/facilities.hpp b/src/mlpack/core/util/facilities.hpp
new file mode 100644
index 0000000000..dee4cd7ee8
--- /dev/null
+++ b/src/mlpack/core/util/facilities.hpp
@@ -0,0 +1,71 @@
+/**
+ * @file facilities.hpp
+ * @author Kirill Mishchenko
+ * @author Bisakh Mondal
+ *
+ * Utility that is used for checking same size &  same dimensionality between
+ * data & response.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_UTIL_FACILITIES_HPP
+#define MLPACK_UTIL_FACILITIES_HPP
+
+#include <mlpack/core.hpp>
+
+namespace mlpack {
+namespace util {
+
+/**
+  * Check for if the given data points & labels have same size.
+  *
+  * @param data data.
+  * @param labels Labels.
+  * @param callerDescription A description of the caller that can be used for
+  *     error generation.
+  * @param mode For nature of comparision(default "CE").
+  *   types of mode:
+  *     "CE" equivalent to (data.n_cols, labels.n_elem).
+  *     "CC" equivalent to (data.n_cols, labels.n_cols).
+  */
+template<typename DataType, typename LabelsType>
+inline void CheckSameSizes(const DataType& data,
+                          const LabelsType& labels,
+                          const std::string& callerDescription,
+                          const std::string& mode = "CE")
+{
+  if (mode == "CE")
+  {
+    if (data.n_cols != labels.n_elem)
+    {
+      std::ostringstream oss;
+      oss << callerDescription << ": number of points (" << data.n_cols << ") "
+          << "does not match number of labels (" << labels.n_elem << ")!"
+          << std::endl;
+      throw std::invalid_argument(oss.str());
+    }
+  }
+  else if (mode == "CC")
+  {
+    if (data.n_cols != labels.n_cols)
+    {
+      std::ostringstream oss;
+      oss << callerDescription << ": number of points (" << data.n_cols << ") "
+          << "does not match number of responses (" << labels.n_cols << ")!"
+          << std::endl;
+      throw std::invalid_argument(oss.str());
+    }
+  }
+  else
+    //For development purpose, not intended for user.
+    Log::Fatal << "Ensure Providing Correct mode!!" << std::endl;
+ 
+}
+
+} // namespace util
+} // namespace mlpack
+
+#endif

From 5a328bae3f6069e83bd09d8a947dc23b500297c1 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 02:05:52 +0530
Subject: [PATCH 206/253] CheckSameDimensionality() added

---
 src/mlpack/core/util/facilities.hpp | 56 +++++++++++++++++++++++++----
 1 file changed, 50 insertions(+), 6 deletions(-)

diff --git a/src/mlpack/core/util/facilities.hpp b/src/mlpack/core/util/facilities.hpp
index dee4cd7ee8..b466634eb2 100644
--- a/src/mlpack/core/util/facilities.hpp
+++ b/src/mlpack/core/util/facilities.hpp
@@ -3,8 +3,7 @@
  * @author Kirill Mishchenko
  * @author Bisakh Mondal
  *
- * Utility that is used for checking same size &  same dimensionality between
- * data & response.
+ * Utility for checking same size &  same dimensionality.
  *
  * mlpack is free software; you may redistribute it and/or modify it under the
  * terms of the 3-clause BSD license.  You should have received a copy of the
@@ -33,9 +32,9 @@ namespace util {
   */
 template<typename DataType, typename LabelsType>
 inline void CheckSameSizes(const DataType& data,
-                          const LabelsType& labels,
-                          const std::string& callerDescription,
-                          const std::string& mode = "CE")
+                           const LabelsType& labels,
+                           const std::string& callerDescription,
+                           const std::string& mode = "CE")
 {
   if (mode == "CE")
   {
@@ -59,13 +58,58 @@ inline void CheckSameSizes(const DataType& data,
       throw std::invalid_argument(oss.str());
     }
   }
+  else
+    //For development purpose, not intended for user.
+    Log::Fatal << "Ensure Providing Correct mode." << std::endl;
+
+}
+
+/**
+  * Check for if the given dataset dimension matches with the model's.
+  *
+  * @param data dataset.
+  * @param dimension Dimension of the model.
+  * @param callerDescription A description of the caller that can be used for
+  *     error generation.
+  * @param mode For nature of comparision(default "R").
+  *   types of mode:
+  *     "R" for comparision with number of rows of the dataset.
+  *     "C" for comparision with number of columns of the dataset.
+  */
+template<typename DataType>
+inline void CheckSameDimentionality(const DataType& data,
+                                    const size_t& dimension,
+                                    const std::string& callerDescription,
+                                    const std::string& mode = "R")
+{
+  if (mode == "R")
+  {
+    if (data.n_rows != dimension)
+    {
+      std::ostringstream oss;
+      oss << callerDescription << ": dataset has " << data.n_rows
+          << " dimensions, but model has " << dimension << " dimensions!";
+      throw std::invalid_argument(oss.str());
+    }
+  }
+  else if (mode == "C")
+  {
+    if (data.n_cols != dimension)
+    {
+      std::ostringstream oss;
+      oss << callerDescription << ": dataset has " << data.n_cols
+          << " dimensions, but model has " << dimension << " dimensions!";
+      throw std::invalid_argument(oss.str());
+    }
+  }
   else
     //For development purpose, not intended for user.
     Log::Fatal << "Ensure Providing Correct mode!!" << std::endl;
- 
+
 }
 
 } // namespace util
 } // namespace mlpack
 
 #endif
+

From 1dd543b5518bdab70c415f5844e30e97624fbb20 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 02:06:45 +0530
Subject: [PATCH 207/253] Added header file to core.hpp

---
 src/mlpack/core.hpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/mlpack/core.hpp b/src/mlpack/core.hpp
index b4645d2b09..7c73678163 100644
--- a/src/mlpack/core.hpp
+++ b/src/mlpack/core.hpp
@@ -89,6 +89,8 @@
 #include <mlpack/core/dists/gamma_distribution.hpp>
 #include <mlpack/core/dists/diagonal_gaussian_distribution.hpp>
 #include <mlpack/core/data/confusion_matrix.hpp>
+#include <mlpack/core/data/one_hot_encoding.hpp>
+#include <mlpack/core/util/facilities.hpp>
 
 // mlpack::backtrace only for linux
 #ifdef HAS_BFD_DL

From ed6bb2af15079661cb34ec709e98427e12d8522c Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 02:07:28 +0530
Subject: [PATCH 208/253] Tests added

---
 src/mlpack/tests/facilities_test.cpp | 55 +++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 2 deletions(-)

diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
index 65b754bb4e..5d95734fca 100644
--- a/src/mlpack/tests/facilities_test.cpp
+++ b/src/mlpack/tests/facilities_test.cpp
@@ -1,8 +1,9 @@
 /**
  * @file facilities_test.cpp
  * @author Khizir Siddiqui
- *
- * Test file for facilities in metrics.
+ * @author Bisakh Mondal
+ * 
+ * Test file for Utility facilities.
  *
  * mlpack is free software; you may redistribute it and/or modify it under the
  * terms of the 3-clause BSD license.  You should have received a copy of the
@@ -14,11 +15,15 @@
 #include <mlpack/core/cv/metrics/facilities.hpp>
 #include <mlpack/core/metrics/lmetric.hpp>
 #include <mlpack/core/data/load.hpp>
+#include <boost/test/unit_test.hpp>
 
 #include "catch.hpp"
 
 using namespace mlpack;
 using namespace mlpack::cv;
+using namespace mlpack::util;
+
+BOOST_AUTO_TEST_SUITE(FacilityTest);
 
 /**
  * The unequal sizes for data and labels show throw an error.
@@ -54,3 +59,49 @@ TEST_CASE("PairwiseDistanceTest", "[FacilitiesTest]")
   REQUIRE(dist(1, 0) == Approx(1.41421).epsilon(1e-5));
   REQUIRE(dist(2, 0) == 3);
 }
+
+
+/**
+ * Test that CheckSameSizes() works in different cases.
+ */
+BOOST_AUTO_TEST_CASE(CheckSizeTest)
+{
+  arma::mat data = arma::randu<arma::mat>(20,30);
+  arma::colvec firstLabels = arma::randu<arma::colvec>(20);
+  arma::colvec secondLabels = arma::randu<arma::colvec>(30);
+  arma::mat thirdLabels = arma::randu<arma::mat>(20,30);
+
+  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking","CC"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking","AB"),
+      std::runtime_error);
+
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data,secondLabels,"TestChecking"));
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data,thirdLabels,"TestChecking",
+      "CC"));
+
+}
+
+
+/**
+ * Test that CheckSameDimensionality() works in different cases.
+ */
+BOOST_AUTO_TEST_CASE(CheckDimensioinality)
+{
+  arma::mat dataset = arma::randu<arma::mat>(20,30);
+
+  BOOST_REQUIRE_NO_THROW(CheckSameDimentionality(dataset,20,"TestingDim"));
+  BOOST_REQUIRE_NO_THROW(CheckSameDimentionality(dataset,30,"TestingDim",
+      "C"));
+
+  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 100, "TestingDim"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 50, "TestingDim", "C"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 20, "TestingDim", "A"),
+      std::runtime_error);
+}
+
+BOOST_AUTO_TEST_SUITE_END();

From 2e0e08edbf6694df6f2db09a12493736b0405b98 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 04:04:50 +0530
Subject: [PATCH 209/253] Old updated

---
 src/mlpack/core/cv/metrics/CMakeLists.txt     | 1 -
 src/mlpack/core/cv/metrics/accuracy_impl.hpp  | 4 +---
 src/mlpack/core/cv/metrics/f1_impl.hpp        | 7 +++----
 src/mlpack/core/cv/metrics/precision_impl.hpp | 7 +++----
 src/mlpack/core/cv/metrics/recall_impl.hpp    | 7 +++----
 5 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/src/mlpack/core/cv/metrics/CMakeLists.txt b/src/mlpack/core/cv/metrics/CMakeLists.txt
index b9edacaf9a..e2322e673c 100644
--- a/src/mlpack/core/cv/metrics/CMakeLists.txt
+++ b/src/mlpack/core/cv/metrics/CMakeLists.txt
@@ -6,7 +6,6 @@ set(SOURCES
   average_strategy.hpp
   f1.hpp
   f1_impl.hpp
-  facilities.hpp
   mse.hpp
   mse_impl.hpp
   precision.hpp
diff --git a/src/mlpack/core/cv/metrics/accuracy_impl.hpp b/src/mlpack/core/cv/metrics/accuracy_impl.hpp
index 91f3dc1c3e..b6f08332af 100644
--- a/src/mlpack/core/cv/metrics/accuracy_impl.hpp
+++ b/src/mlpack/core/cv/metrics/accuracy_impl.hpp
@@ -12,8 +12,6 @@
 #ifndef MLPACK_CORE_CV_METRICS_ACCURACY_IMPL_HPP
 #define MLPACK_CORE_CV_METRICS_ACCURACY_IMPL_HPP
 
-#include <mlpack/core/cv/metrics/facilities.hpp>
-
 namespace mlpack {
 namespace cv {
 
@@ -22,7 +20,7 @@ double Accuracy::Evaluate(MLAlgorithm& model,
                           const DataType& data,
                           const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Accuracy::Evaluate()");
+  util::CheckSameSizes(data, labels, "Accuracy::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
diff --git a/src/mlpack/core/cv/metrics/f1_impl.hpp b/src/mlpack/core/cv/metrics/f1_impl.hpp
index 6e89754941..5af0558a68 100644
--- a/src/mlpack/core/cv/metrics/f1_impl.hpp
+++ b/src/mlpack/core/cv/metrics/f1_impl.hpp
@@ -13,7 +13,6 @@
 #define MLPACK_CORE_CV_METRICS_F1_IMPL_HPP
 
 #include <mlpack/core/cv/metrics/accuracy.hpp>
-#include <mlpack/core/cv/metrics/facilities.hpp>
 
 namespace mlpack {
 namespace cv {
@@ -33,7 +32,7 @@ double F1<AS, PC>::Evaluate(MLAlgorithm& model,
                             const DataType& data,
                             const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "F1<Binary>::Evaluate()");
+  util::CheckSameSizes(data, labels, "F1<Binary>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
@@ -56,7 +55,7 @@ double F1<AS, PC>::Evaluate(MLAlgorithm& model,
                             const DataType& data,
                             const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "F1<Micro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "F1<Micro>::Evaluate()");
 
   // Microaveraged F1 is really the same as microaveraged precision and
   // microaveraged recall, which are in turn the same as accuracy.
@@ -70,7 +69,7 @@ double F1<AS, PC>::Evaluate(MLAlgorithm& model,
                             const DataType& data,
                             const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "F1<Macro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "F1<Macro>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
diff --git a/src/mlpack/core/cv/metrics/precision_impl.hpp b/src/mlpack/core/cv/metrics/precision_impl.hpp
index b8831fe132..25afd43454 100644
--- a/src/mlpack/core/cv/metrics/precision_impl.hpp
+++ b/src/mlpack/core/cv/metrics/precision_impl.hpp
@@ -13,7 +13,6 @@
 #define MLPACK_CORE_CV_METRICS_PRECISION_IMPL_HPP
 
 #include <mlpack/core/cv/metrics/accuracy.hpp>
-#include <mlpack/core/cv/metrics/facilities.hpp>
 
 namespace mlpack {
 namespace cv {
@@ -33,7 +32,7 @@ double Precision<AS, PC>::Evaluate(MLAlgorithm& model,
                                    const DataType& data,
                                    const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Precision<Binary>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Precision<Binary>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
@@ -51,7 +50,7 @@ double Precision<AS, PC>::Evaluate(MLAlgorithm& model,
                                    const DataType& data,
                                    const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Precision<Micro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Precision<Micro>::Evaluate()");
 
   // Microaveraged precision turns out to be just accuracy.
   return Accuracy::Evaluate(model, data, labels);
@@ -64,7 +63,7 @@ double Precision<AS, PC>::Evaluate(MLAlgorithm& model,
                                    const DataType& data,
                                    const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Precision<Macro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Precision<Macro>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
diff --git a/src/mlpack/core/cv/metrics/recall_impl.hpp b/src/mlpack/core/cv/metrics/recall_impl.hpp
index 5ff7bd7400..bbfbe7071d 100644
--- a/src/mlpack/core/cv/metrics/recall_impl.hpp
+++ b/src/mlpack/core/cv/metrics/recall_impl.hpp
@@ -13,7 +13,6 @@
 #define MLPACK_CORE_CV_METRICS_RECALL_IMPL_HPP
 
 #include <mlpack/core/cv/metrics/accuracy.hpp>
-#include <mlpack/core/cv/metrics/facilities.hpp>
 
 namespace mlpack {
 namespace cv {
@@ -33,7 +32,7 @@ double Recall<AS, PC>::Evaluate(MLAlgorithm& model,
                                 const DataType& data,
                                 const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Recall<Binary>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Recall<Binary>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);
@@ -51,7 +50,7 @@ double Recall<AS, PC>::Evaluate(MLAlgorithm& model,
                                 const DataType& data,
                                 const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Recall<Micro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Recall<Micro>::Evaluate()");
 
   // Microaveraged recall is really the same as accuracy.
   return Accuracy::Evaluate(model, data, labels);
@@ -64,7 +63,7 @@ double Recall<AS, PC>::Evaluate(MLAlgorithm& model,
                                 const DataType& data,
                                 const arma::Row<size_t>& labels)
 {
-  AssertSizes(data, labels, "Recall<Macro>::Evaluate()");
+  util::CheckSameSizes(data, labels, "Recall<Macro>::Evaluate()");
 
   arma::Row<size_t> predictedLabels;
   model.Classify(data, predictedLabels);

From e8cba43562a1013f9c74d192935f28ded8738d3f Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 04:08:04 +0530
Subject: [PATCH 210/253] unnecessary file removed

---
 src/mlpack/core/cv/metrics/facilities.hpp | 71 -----------------------
 1 file changed, 71 deletions(-)
 delete mode 100644 src/mlpack/core/cv/metrics/facilities.hpp

diff --git a/src/mlpack/core/cv/metrics/facilities.hpp b/src/mlpack/core/cv/metrics/facilities.hpp
deleted file mode 100644
index c7b9b4b70e..0000000000
--- a/src/mlpack/core/cv/metrics/facilities.hpp
+++ /dev/null
@@ -1,71 +0,0 @@
-/**
- * @file core/cv/metrics/facilities.hpp
- * @author Kirill Mishchenko
- * @author Khizir Siddiqui
- *
- * Functionality that is used more than in one metric.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-#ifndef MLPACK_CORE_CV_METRICS_FACILITIES_HPP
-#define MLPACK_CORE_CV_METRICS_FACILITIES_HPP
-
-#include <mlpack/core.hpp>
-#include <mlpack/core/metrics/lmetric.hpp>
-
-namespace mlpack {
-namespace cv {
-
-/**
-  * Assert there is the same number of the given data points and labels.
-  *
-  * @param data Column-major data.
-  * @param labels Labels.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  */
-template<typename DataType>
-void AssertSizes(const DataType& data,
-                 const arma::Row<size_t>& labels,
-                 const std::string& callerDescription)
-{
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << callerDescription << ": number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
-}
-
-/**
-  * Pairwise distance of the given data.
-  *
-  * @param data Column-major matrix.
-  * @param metric Distance metric to be used.
-  */
-template<typename DataType, typename Metric>
-DataType PairwiseDistances(const DataType& data,
-                           const Metric& metric)
-{
-  DataType distances = DataType(data.n_cols, data.n_cols, arma::fill::none);
-  for (size_t i = 0; i < data.n_cols; i++)
-  {
-    for (size_t j = 0; j < i; j++)
-    {
-      distances(i, j) = metric.Evaluate(data.col(i), data.col(j));
-      distances(j, i) = distances(i, j);
-    }
-  }
-  distances.diag().zeros();
-  return distances;
-}
-
-} // namespace cv
-} // namespace mlpack
-
-#endif

From 72e000f09bdd7d509b3f621c259836a15e188752 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 09:41:30 +0530
Subject: [PATCH 211/253] spelling error corrected

---
 src/mlpack/core/util/facilities.hpp  |  2 +-
 src/mlpack/tests/facilities_test.cpp | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/core/util/facilities.hpp b/src/mlpack/core/util/facilities.hpp
index b466634eb2..5a7d22069e 100644
--- a/src/mlpack/core/util/facilities.hpp
+++ b/src/mlpack/core/util/facilities.hpp
@@ -77,7 +77,7 @@ inline void CheckSameSizes(const DataType& data,
   *     "C" for comparision with number of columns of the dataset.
   */
 template<typename DataType>
-inline void CheckSameDimentionality(const DataType& data,
+inline void CheckSameDimensionality(const DataType& data,
                                     const size_t& dimension,
                                     const std::string& callerDescription,
                                     const std::string& mode = "R")
diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
index 5d95734fca..4b1042fe72 100644
--- a/src/mlpack/tests/facilities_test.cpp
+++ b/src/mlpack/tests/facilities_test.cpp
@@ -88,19 +88,19 @@ BOOST_AUTO_TEST_CASE(CheckSizeTest)
 /**
  * Test that CheckSameDimensionality() works in different cases.
  */
-BOOST_AUTO_TEST_CASE(CheckDimensioinality)
+BOOST_AUTO_TEST_CASE(CheckDimensionality)
 {
   arma::mat dataset = arma::randu<arma::mat>(20,30);
 
-  BOOST_REQUIRE_NO_THROW(CheckSameDimentionality(dataset,20,"TestingDim"));
-  BOOST_REQUIRE_NO_THROW(CheckSameDimentionality(dataset,30,"TestingDim",
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset,20,"TestingDim"));
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset,30,"TestingDim",
       "C"));
 
-  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 100, "TestingDim"),
+  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 100, "TestingDim"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 50, "TestingDim", "C"),
+  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 50, "TestingDim", "C"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameDimentionality(dataset, 20, "TestingDim", "A"),
+  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 20, "TestingDim", "A"),
       std::runtime_error);
 }
 

From f02fe11fbc7f7a430de879f281c13be7894d925e Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Mon, 13 Apr 2020 10:19:15 +0530
Subject: [PATCH 212/253] style issue fixed

---
 src/mlpack/core/util/facilities.hpp  |  6 ++----
 src/mlpack/tests/facilities_test.cpp | 21 ++++++++++-----------
 2 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/src/mlpack/core/util/facilities.hpp b/src/mlpack/core/util/facilities.hpp
index 5a7d22069e..bd9605b460 100644
--- a/src/mlpack/core/util/facilities.hpp
+++ b/src/mlpack/core/util/facilities.hpp
@@ -59,9 +59,8 @@ inline void CheckSameSizes(const DataType& data,
     }
   }
   else
-    //For development purpose, not intended for user.
+    // For development purpose, not intended for user.
     Log::Fatal << "Ensure Providing Correct mode." << std::endl;
-
 }
 
 /**
@@ -103,9 +102,8 @@ inline void CheckSameDimensionality(const DataType& data,
     }
   }
   else
-    //For development purpose, not intended for user.
+    // For development purpose, not intended for user.
     Log::Fatal << "Ensure Providing Correct mode!!" << std::endl;
-
 }
 
 } // namespace util
diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
index 4b1042fe72..11ee5c68b1 100644
--- a/src/mlpack/tests/facilities_test.cpp
+++ b/src/mlpack/tests/facilities_test.cpp
@@ -66,22 +66,21 @@ TEST_CASE("PairwiseDistanceTest", "[FacilitiesTest]")
  */
 BOOST_AUTO_TEST_CASE(CheckSizeTest)
 {
-  arma::mat data = arma::randu<arma::mat>(20,30);
+  arma::mat data = arma::randu<arma::mat>(20, 30);
   arma::colvec firstLabels = arma::randu<arma::colvec>(20);
   arma::colvec secondLabels = arma::randu<arma::colvec>(30);
-  arma::mat thirdLabels = arma::randu<arma::mat>(20,30);
+  arma::mat thirdLabels = arma::randu<arma::mat>(20, 30);
 
-  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking"),
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking","CC"),
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "CC"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data,firstLabels,"TestChecking","AB"),
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "AB"),
       std::runtime_error);
 
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data,secondLabels,"TestChecking"));
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data,thirdLabels,"TestChecking",
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, secondLabels, "TestChecking"));
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, thirdLabels, "TestChecking",
       "CC"));
-
 }
 
 
@@ -90,10 +89,10 @@ BOOST_AUTO_TEST_CASE(CheckSizeTest)
  */
 BOOST_AUTO_TEST_CASE(CheckDimensionality)
 {
-  arma::mat dataset = arma::randu<arma::mat>(20,30);
+  arma::mat dataset = arma::randu<arma::mat>(20, 30);
 
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset,20,"TestingDim"));
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset,30,"TestingDim",
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, 20, "TestingDim"));
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, 30, "TestingDim",
       "C"));
 
   BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 100, "TestingDim"),

From bd8710d53483493407200defeaa6c7e368512df6 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Tue, 28 Apr 2020 21:49:36 +0530
Subject: [PATCH 213/253] Size Check Suite added

---
 src/mlpack/core/util/size_checks.hpp  | 108 ++++++++++++++++++++++++++
 src/mlpack/tests/size_checks_test.cpp |  62 +++++++++++++++
 2 files changed, 170 insertions(+)
 create mode 100644 src/mlpack/core/util/size_checks.hpp
 create mode 100644 src/mlpack/tests/size_checks_test.cpp

diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
new file mode 100644
index 0000000000..7a02a2ee5e
--- /dev/null
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -0,0 +1,108 @@
+/**
+ * @file size_checks.hpp
+ * @author Kirill Mishchenko
+ * @author Bisakh Mondal
+ *
+ * Utility for checking same size &  same dimensionality.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_UTIL_SIZE_CHECKS_HPP
+#define MLPACK_UTIL_SIZE_CHECKS_HPP
+
+#include <mlpack/core.hpp>
+
+namespace mlpack {
+namespace util {
+
+/**
+  * Check for if the given data points & labels have same size.
+  *
+  * @param data data.
+  * @param labels Labels.
+  * @param callerDescription A description of the caller that can be used for
+  *     error generation.
+  * @param mode For nature of comparision(default "CE").
+  *   types of mode:
+  *     "CE" equivalent to (data.n_cols, labels.n_elem).
+  *     "CC" equivalent to (data.n_cols, labels.n_cols).
+  * @param addInfo  An additional information about labels that can be used for
+  *	precise error generation. Default is "labels". Another e.g. weights
+  */
+template<typename DataType, typename LabelsType>
+inline void CheckSameSizes(const DataType& data,
+                           const LabelsType& labels,
+                           const std::string& callerDescription,
+                           const std::string& mode = "CE",
+                           const std::string& addInfo = "labels")
+{
+  if (mode != "CE" && mode != "CC")
+    // For development purpose, not intended for user.
+    Log::Fatal << "Ensure Providing Correct mode." << std::endl;
+
+  const size_t size1 = data.n_cols;
+  const size_t size2 = mode == "CE" ? labels.n_elem : labels.n_cols;
+
+  if (size1 != size2)
+  {
+    std::ostringstream oss;
+    oss << callerDescription << ": number of points (" << size1 << ") "
+        << "does not match number of " << addInfo << " (" << size2 << ")!"
+        << std::endl;
+    throw std::invalid_argument(oss.str());
+  }
+}
+
+/**
+  * Check for if the given dataset dimension matches with the model's.
+  *
+  * @param data dataset.
+  * @param dimension Dimension of the model.
+  * @param callerDescription A description of the caller that can be used for
+  *     error generation.
+  * @param addInfo  An additional information about data that can be used for
+  *	precise error generation. Default is "dataset". Another e.g. weights.
+  */
+template<typename DataType, typename DimType>
+inline void CheckSameDimensionality(const DataType& data,
+                                    const DimType& dimension,
+                                    const std::string& callerDescription,
+                                    const std::string& addInfo = "dataset")
+{
+  if (data.n_rows != dimension.n_rows)
+  {
+    std::ostringstream oss;
+    oss << callerDescription << ": dimensionality of " << addInfo << " ("
+        << data.n_rows << ") is not equal to the dimensionality of the model"
+        " (" << dimension.n_rows << ")!";
+
+    throw std::invalid_argument(oss.str());
+  }
+}
+
+// An overload of CheckSameDimensionality() where second param is unsigned
+//    long int.
+template<typename DataType>
+inline void CheckSameDimensionality(const DataType& data,
+                                    const size_t& dimension,
+                                    const std::string& callerDescription,
+                                    const std::string& addInfo = "dataset")
+{
+  if (data.n_rows != dimension)
+  {
+    std::ostringstream oss;
+    oss << callerDescription << ": dimensionality of " << addInfo << " ("
+        << data.n_rows << ") is not equal to the dimensionality of the model"
+        " (" << dimension << ")!";
+    throw std::invalid_argument(oss.str());
+  }
+}
+
+} // namespace util
+} // namespace mlpack
+
+#endif
+
diff --git a/src/mlpack/tests/size_checks_test.cpp b/src/mlpack/tests/size_checks_test.cpp
new file mode 100644
index 0000000000..44539036b9
--- /dev/null
+++ b/src/mlpack/tests/size_checks_test.cpp
@@ -0,0 +1,62 @@
+/**
+ * @file size_checks_test.cpp
+ * @author Bisakh Mondal
+ * 
+ * Test file for Utility size_checks.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include <mlpack/core.hpp>
+#include <boost/test/unit_test.hpp>
+
+using namespace mlpack;
+using namespace mlpack::util;
+BOOST_AUTO_TEST_SUITE(SizeCheckTest);
+
+/**
+ * Test that CheckSameSizes() works in different cases.
+ */
+BOOST_AUTO_TEST_CASE(CheckSizeTest)
+{
+  arma::mat data = arma::randu<arma::mat>(20, 30);
+  arma::colvec firstLabels = arma::randu<arma::colvec>(20);
+  arma::colvec secondLabels = arma::randu<arma::colvec>(30);
+  arma::mat thirdLabels = arma::randu<arma::mat>(20, 30);
+
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "CC"),
+      std::invalid_argument);
+  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "AB"),
+      std::runtime_error);
+
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, secondLabels, "TestChecking"));
+  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, thirdLabels, "TestChecking",
+      "CC"));
+}
+
+/**
+ * Test that CheckSameDimensionality() works in different cases.
+ */
+BOOST_AUTO_TEST_CASE(CheckDimensionality)
+{
+  arma::mat dataset = arma::randu<arma::mat>(20, 30);
+  arma::colvec refSet = arma::randu<arma::colvec>(20);
+  arma::colvec refSet2 = arma::randu<arma::colvec>(40);
+
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, (size_t) 20,
+      "TestingDim"));
+  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, (size_t) 100,
+      "TestingDim"), std::invalid_argument);
+
+  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, refSet2, "TestingDim"),
+      std::invalid_argument);
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, refSet, "TestingDim"
+      ));
+}
+
+BOOST_AUTO_TEST_SUITE_END();
+

From d4f0cad156307409924d3952d312507418f7042f Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Tue, 28 Apr 2020 21:59:52 +0530
Subject: [PATCH 214/253] updated implementations

---
 src/mlpack/core.hpp                           |   2 +-
 src/mlpack/core/cv/cv_base_impl.hpp           |  10 +-
 src/mlpack/core/cv/metrics/mse_impl.hpp       |   9 +-
 src/mlpack/core/cv/metrics/r2_score_impl.hpp  |  10 +-
 src/mlpack/core/util/CMakeLists.txt           |   2 +-
 src/mlpack/core/util/facilities.hpp           | 113 ------------------
 src/mlpack/core/util/size_checks.hpp          |   2 +-
 .../decision_tree/decision_tree_impl.hpp      |  60 +++++-----
 .../methods/linear_svm/linear_svm_impl.hpp    |   8 +-
 src/mlpack/methods/lsh/lsh_search_impl.hpp    |  10 +-
 .../range_search/range_search_impl.hpp        |  10 +-
 .../softmax_regression/softmax_regression.cpp |  10 +-
 src/mlpack/tests/CMakeLists.txt               |   4 +-
 src/mlpack/tests/facilities_test.cpp          | 106 ----------------
 14 files changed, 46 insertions(+), 310 deletions(-)
 delete mode 100644 src/mlpack/core/util/facilities.hpp
 delete mode 100644 src/mlpack/tests/facilities_test.cpp

diff --git a/src/mlpack/core.hpp b/src/mlpack/core.hpp
index 7c73678163..c4522ba05f 100644
--- a/src/mlpack/core.hpp
+++ b/src/mlpack/core.hpp
@@ -90,7 +90,7 @@
 #include <mlpack/core/dists/diagonal_gaussian_distribution.hpp>
 #include <mlpack/core/data/confusion_matrix.hpp>
 #include <mlpack/core/data/one_hot_encoding.hpp>
-#include <mlpack/core/util/facilities.hpp>
+#include <mlpack/core/util/size_checks.hpp>
 
 // mlpack::backtrace only for linux
 #ifdef HAS_BFD_DL
diff --git a/src/mlpack/core/cv/cv_base_impl.hpp b/src/mlpack/core/cv/cv_base_impl.hpp
index a7017d770a..fc819603db 100644
--- a/src/mlpack/core/cv/cv_base_impl.hpp
+++ b/src/mlpack/core/cv/cv_base_impl.hpp
@@ -106,14 +106,8 @@ void CVBase<MLAlgorithm,
             WeightsType>::AssertDataConsistency(const MatType& xs,
                                                 const PredictionsType& ys)
 {
-  if (xs.n_cols != ys.n_cols)
-  {
-    std::ostringstream oss;
-    oss << "CVBase::AssertDataConsistency(): number of data points ("
-        << xs.n_cols << ") does not match number of predictions (" << ys.n_cols
-        << ")!" << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameSizes(xs, ys, "CVBase::AssertDataConsistency()", "CC",
+      "predictions");
 }
 
 template<typename MLAlgorithm,
diff --git a/src/mlpack/core/cv/metrics/mse_impl.hpp b/src/mlpack/core/cv/metrics/mse_impl.hpp
index 79a26476aa..a55a0e7ed0 100644
--- a/src/mlpack/core/cv/metrics/mse_impl.hpp
+++ b/src/mlpack/core/cv/metrics/mse_impl.hpp
@@ -20,14 +20,7 @@ double MSE::Evaluate(MLAlgorithm& model,
                      const DataType& data,
                      const ResponsesType& responses)
 {
-  if (data.n_cols != responses.n_cols)
-  {
-    std::ostringstream oss;
-    oss << "MSE::Evaluate(): number of points (" << data.n_cols << ") "
-        << "does not match number of responses (" << responses.n_cols << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameSizes(data, responses, "MSE::Evaluate()", "CC", "responses");
 
   ResponsesType predictedResponses;
   model.Predict(data, predictedResponses);
diff --git a/src/mlpack/core/cv/metrics/r2_score_impl.hpp b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
index 2859a17f9d..dad46216eb 100644
--- a/src/mlpack/core/cv/metrics/r2_score_impl.hpp
+++ b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
@@ -21,14 +21,8 @@ double R2Score<AdjustedR2>::Evaluate(MLAlgorithm& model,
                                      const DataType& data,
                                      const ResponsesType& responses)
 {
-  if (data.n_cols != responses.n_cols)
-  {
-    std::ostringstream oss;
-    oss << "R2Score::Evaluate(): number of points (" << data.n_cols << ") "
-        << "does not match number of responses (" << responses.n_cols << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameSizes(data, responses, "R2Score::Evaluate()", "CC",
+      "responses");
 
   ResponsesType predictedResponses;
   // Taking Predicted Output from the model.
diff --git a/src/mlpack/core/util/CMakeLists.txt b/src/mlpack/core/util/CMakeLists.txt
index 4872652826..ef21ff91ca 100644
--- a/src/mlpack/core/util/CMakeLists.txt
+++ b/src/mlpack/core/util/CMakeLists.txt
@@ -26,6 +26,7 @@ set(SOURCES
   prefixedoutstream_impl.hpp
   program_doc.hpp
   program_doc.cpp
+  size_checks.hpp
   sfinae_utility.hpp
   singletons.cpp
   timers.hpp
@@ -33,7 +34,6 @@ set(SOURCES
   to_lower.hpp
   version.hpp
   version.cpp
-  facilities.hpp
 )
 
 # add directory name to sources
diff --git a/src/mlpack/core/util/facilities.hpp b/src/mlpack/core/util/facilities.hpp
deleted file mode 100644
index bd9605b460..0000000000
--- a/src/mlpack/core/util/facilities.hpp
+++ /dev/null
@@ -1,113 +0,0 @@
-/**
- * @file facilities.hpp
- * @author Kirill Mishchenko
- * @author Bisakh Mondal
- *
- * Utility for checking same size &  same dimensionality.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-#ifndef MLPACK_UTIL_FACILITIES_HPP
-#define MLPACK_UTIL_FACILITIES_HPP
-
-#include <mlpack/core.hpp>
-
-namespace mlpack {
-namespace util {
-
-/**
-  * Check for if the given data points & labels have same size.
-  *
-  * @param data data.
-  * @param labels Labels.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  * @param mode For nature of comparision(default "CE").
-  *   types of mode:
-  *     "CE" equivalent to (data.n_cols, labels.n_elem).
-  *     "CC" equivalent to (data.n_cols, labels.n_cols).
-  */
-template<typename DataType, typename LabelsType>
-inline void CheckSameSizes(const DataType& data,
-                           const LabelsType& labels,
-                           const std::string& callerDescription,
-                           const std::string& mode = "CE")
-{
-  if (mode == "CE")
-  {
-    if (data.n_cols != labels.n_elem)
-    {
-      std::ostringstream oss;
-      oss << callerDescription << ": number of points (" << data.n_cols << ") "
-          << "does not match number of labels (" << labels.n_elem << ")!"
-          << std::endl;
-      throw std::invalid_argument(oss.str());
-    }
-  }
-  else if (mode == "CC")
-  {
-    if (data.n_cols != labels.n_cols)
-    {
-      std::ostringstream oss;
-      oss << callerDescription << ": number of points (" << data.n_cols << ") "
-          << "does not match number of responses (" << labels.n_cols << ")!"
-          << std::endl;
-      throw std::invalid_argument(oss.str());
-    }
-  }
-  else
-    // For development purpose, not intended for user.
-    Log::Fatal << "Ensure Providing Correct mode." << std::endl;
-}
-
-/**
-  * Check for if the given dataset dimension matches with the model's.
-  *
-  * @param data dataset.
-  * @param dimension Dimension of the model.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  * @param mode For nature of comparision(default "R").
-  *   types of mode:
-  *     "R" for comparision with number of rows of the dataset.
-  *     "C" for comparision with number of columns of the dataset.
-  */
-template<typename DataType>
-inline void CheckSameDimensionality(const DataType& data,
-                                    const size_t& dimension,
-                                    const std::string& callerDescription,
-                                    const std::string& mode = "R")
-{
-  if (mode == "R")
-  {
-    if (data.n_rows != dimension)
-    {
-      std::ostringstream oss;
-      oss << callerDescription << ": dataset has " << data.n_rows
-          << " dimensions, but model has " << dimension << " dimensions!";
-      throw std::invalid_argument(oss.str());
-    }
-  }
-  else if (mode == "C")
-  {
-    if (data.n_cols != dimension)
-    {
-      std::ostringstream oss;
-      oss << callerDescription << ": dataset has " << data.n_cols
-          << " dimensions, but model has " << dimension << " dimensions!";
-      throw std::invalid_argument(oss.str());
-    }
-  }
-  else
-    // For development purpose, not intended for user.
-    Log::Fatal << "Ensure Providing Correct mode!!" << std::endl;
-}
-
-} // namespace util
-} // namespace mlpack
-
-#endif
-
diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
index 7a02a2ee5e..318de15567 100644
--- a/src/mlpack/core/util/size_checks.hpp
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -3,7 +3,7 @@
  * @author Kirill Mishchenko
  * @author Bisakh Mondal
  *
- * Utility for checking same size &  same dimensionality.
+ * Utility for checking same size & same dimensionality.
  *
  * mlpack is free software; you may redistribute it and/or modify it under the
  * terms of the 3-clause BSD license.  You should have received a copy of the
diff --git a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
index 1646608d0b..8967e88f1b 100644
--- a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
+++ b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
@@ -469,14 +469,7 @@ double DecisionTree<FitnessFunction,
     DimensionSelectionType dimensionSelector)
 {
   // Sanity check on data.
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
   using TrueLabelsType = typename std::decay<LabelsType>::type;
@@ -518,14 +511,15 @@ double DecisionTree<FitnessFunction,
     DimensionSelectionType dimensionSelector)
 {
   // Sanity check on data.
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  // if (data.n_cols != labels.n_elem)
+  // {
+  //   std::ostringstream oss;
+  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
+  //       << "does not match number of labels (" << labels.n_elem << ")!"
+  //       << std::endl;
+  //   throw std::invalid_argument(oss.str());
+  // }
+  util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
   using TrueLabelsType = typename std::decay<LabelsType>::type;
@@ -573,14 +567,15 @@ double DecisionTree<FitnessFunction,
         WeightsType>::type>::value>*)
 {
   // Sanity check on data.
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  // if (data.n_cols != labels.n_elem)
+  // {
+  //   std::ostringstream oss;
+  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
+  //       << "does not match number of labels (" << labels.n_elem << ")!"
+  //       << std::endl;
+  //   throw std::invalid_argument(oss.str());
+  // }
+  util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
   using TrueLabelsType = typename std::decay<LabelsType>::type;
@@ -628,14 +623,15 @@ double DecisionTree<FitnessFunction,
         WeightsType>::type>::value>*)
 {
   // Sanity check on data.
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  // if (data.n_cols != labels.n_elem)
+  // {
+  //   std::ostringstream oss;
+  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
+  //       << "does not match number of labels (" << labels.n_elem << ")!"
+  //       << std::endl;
+  //   throw std::invalid_argument(oss.str());
+  // }
+  util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
   using TrueLabelsType = typename std::decay<LabelsType>::type;
diff --git a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
index 243ba772ce..69f0887f9d 100644
--- a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
+++ b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
@@ -173,13 +173,7 @@ void LinearSVM<MatType>::Classify(
     const MatType& data,
     arma::mat& scores) const
 {
-  if (data.n_rows != FeatureSize())
-  {
-    std::ostringstream oss;
-    oss << "LinearSVM::Classify(): dataset has " << data.n_rows
-        << " dimensions, but model has " << FeatureSize() << " dimensions!";
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameDimensionality(data, FeatureSize(), "LinearSVM::Classify()");
 
   if (fitIntercept)
   {
diff --git a/src/mlpack/methods/lsh/lsh_search_impl.hpp b/src/mlpack/methods/lsh/lsh_search_impl.hpp
index c3838bd4b6..6c3aeb8259 100644
--- a/src/mlpack/methods/lsh/lsh_search_impl.hpp
+++ b/src/mlpack/methods/lsh/lsh_search_impl.hpp
@@ -865,14 +865,8 @@ void LSHSearch<SortPolicy, MatType>::Search(
     const size_t T)
 {
   // Ensure the dimensionality of the query set is correct.
-  if (querySet.n_rows != referenceSet.n_rows)
-  {
-    std::ostringstream oss;
-    oss << "LSHSearch::Search(): dimensionality of query set ("
-        << querySet.n_rows << ") is not equal to the dimensionality the model "
-        << "was trained on (" << referenceSet.n_rows << ")!" << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameDimensionality(querySet, referenceSet, "LSHSearch::Search()",
+      "query set");
 
   if (k > referenceSet.n_cols)
   {
diff --git a/src/mlpack/methods/range_search/range_search_impl.hpp b/src/mlpack/methods/range_search/range_search_impl.hpp
index 03f90b3057..cce20339a3 100644
--- a/src/mlpack/methods/range_search/range_search_impl.hpp
+++ b/src/mlpack/methods/range_search/range_search_impl.hpp
@@ -312,14 +312,8 @@ void RangeSearch<MetricType, MatType, TreeType>::Search(
     std::vector<std::vector<size_t>>& neighbors,
     std::vector<std::vector<double>>& distances)
 {
-  if (querySet.n_rows != referenceSet->n_rows)
-  {
-    std::ostringstream oss;
-    oss << "RangeSearch::Search(): dimensionalities of query set ("
-        << querySet.n_rows << ") and reference set (" << referenceSet->n_rows
-        << ") do not match!";
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameDimensionality(querySet, *referenceSet,
+      "RangeSearch::Search()", "query set");
 
   // If there are no points, there is no search to be done.
   if (referenceSet->n_cols == 0)
diff --git a/src/mlpack/methods/softmax_regression/softmax_regression.cpp b/src/mlpack/methods/softmax_regression/softmax_regression.cpp
index ae39513df6..b269c07690 100644
--- a/src/mlpack/methods/softmax_regression/softmax_regression.cpp
+++ b/src/mlpack/methods/softmax_regression/softmax_regression.cpp
@@ -11,6 +11,7 @@
  */
 
 #include "softmax_regression.hpp"
+#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace regression {
@@ -91,13 +92,8 @@ void SoftmaxRegression::Classify(const arma::mat& dataset,
                                  arma::mat& probabilities)
     const
 {
-  if (dataset.n_rows != FeatureSize())
-  {
-    std::ostringstream oss;
-    oss << "SoftmaxRegression::Classify(): dataset has " << dataset.n_rows
-        << " dimensions, but model has " << FeatureSize() << " dimensions!";
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameDimensionality(dataset, FeatureSize(),
+      "SoftmaxRegression::Classify()");
 
   // Calculate the probabilities for each test input.
   arma::mat hypothesis;
diff --git a/src/mlpack/tests/CMakeLists.txt b/src/mlpack/tests/CMakeLists.txt
index e6dd629266..a384be6825 100644
--- a/src/mlpack/tests/CMakeLists.txt
+++ b/src/mlpack/tests/CMakeLists.txt
@@ -30,8 +30,7 @@ add_executable(mlpack_test
   det_test.cpp
   distribution_test.cpp
   drusilla_select_test.cpp
-  emst_test.cpp
-  facilities_test.cpp
+  emst_test.cpp 
   fastmks_test.cpp
   feedforward_network_test.cpp
   gan_test.cpp
@@ -98,6 +97,7 @@ add_executable(mlpack_test
   reward_clipping_test.cpp
   rl_components_test.cpp
   scaling_test.cpp
+  size_checks_test.cpp
   serialization.cpp
   serialization.hpp
   serialization_test.cpp
diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
deleted file mode 100644
index 11ee5c68b1..0000000000
--- a/src/mlpack/tests/facilities_test.cpp
+++ /dev/null
@@ -1,106 +0,0 @@
-/**
- * @file facilities_test.cpp
- * @author Khizir Siddiqui
- * @author Bisakh Mondal
- * 
- * Test file for Utility facilities.
- *
- * mlpack is free software; you may redistribute it and/or modify it under the
- * terms of the 3-clause BSD license.  You should have received a copy of the
- * 3-clause BSD license along with mlpack.  If not, see
- * http://www.opensource.org/licenses/BSD-3-Clause for more information.
- */
-
-#include <mlpack/core.hpp>
-#include <mlpack/core/cv/metrics/facilities.hpp>
-#include <mlpack/core/metrics/lmetric.hpp>
-#include <mlpack/core/data/load.hpp>
-#include <boost/test/unit_test.hpp>
-
-#include "catch.hpp"
-
-using namespace mlpack;
-using namespace mlpack::cv;
-using namespace mlpack::util;
-
-BOOST_AUTO_TEST_SUITE(FacilityTest);
-
-/**
- * The unequal sizes for data and labels show throw an error.
- */
-TEST_CASE("AssertSizesTest", "[FacilitiesTest]")
-{
-  // Load the dataset.
-  arma::mat dataset;
-  if (!data::Load("iris_train.csv", dataset))
-    FAIL("Cannot load test dataset iris_train.csv!");
-  // Load the labels.
-  arma::Row<size_t> labels;
-  if (!data::Load("iris_test_labels.csv", labels))
-    FAIL("Cannot load test dataset iris_test_labels.csv!");
-
-  REQUIRE_THROWS_AS(
-    AssertSizes(dataset, labels, "test"), std::invalid_argument);
-}
-
-
-/**
- * Pairwise distances.
- */
-TEST_CASE("PairwiseDistanceTest", "[FacilitiesTest]")
-{
-  arma::mat X;
-  X = { { 0, 1, 1, 0, 0 },
-        { 0, 1, 2, 0, 0 },
-        { 1, 1, 3, 2, 0 } };
-  metric::EuclideanDistance metric;
-  arma::mat dist = PairwiseDistances(X, metric);
-  REQUIRE(dist(0, 0) == 0);
-  REQUIRE(dist(1, 0) == Approx(1.41421).epsilon(1e-5));
-  REQUIRE(dist(2, 0) == 3);
-}
-
-
-/**
- * Test that CheckSameSizes() works in different cases.
- */
-BOOST_AUTO_TEST_CASE(CheckSizeTest)
-{
-  arma::mat data = arma::randu<arma::mat>(20, 30);
-  arma::colvec firstLabels = arma::randu<arma::colvec>(20);
-  arma::colvec secondLabels = arma::randu<arma::colvec>(30);
-  arma::mat thirdLabels = arma::randu<arma::mat>(20, 30);
-
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking"),
-      std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "CC"),
-      std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "AB"),
-      std::runtime_error);
-
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, secondLabels, "TestChecking"));
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, thirdLabels, "TestChecking",
-      "CC"));
-}
-
-
-/**
- * Test that CheckSameDimensionality() works in different cases.
- */
-BOOST_AUTO_TEST_CASE(CheckDimensionality)
-{
-  arma::mat dataset = arma::randu<arma::mat>(20, 30);
-
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, 20, "TestingDim"));
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, 30, "TestingDim",
-      "C"));
-
-  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 100, "TestingDim"),
-      std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 50, "TestingDim", "C"),
-      std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, 20, "TestingDim", "A"),
-      std::runtime_error);
-}
-
-BOOST_AUTO_TEST_SUITE_END();

From e6e41199a007fb882d4fda8023e83515417fe7fd Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Tue, 28 Apr 2020 22:07:37 +0530
Subject: [PATCH 215/253] Deletion of Commented out code Done.

---
 .../decision_tree/decision_tree_impl.hpp      | 24 -------------------
 src/mlpack/tests/size_checks_test.cpp         |  4 ++--
 2 files changed, 2 insertions(+), 26 deletions(-)

diff --git a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
index 8967e88f1b..b99075f5b2 100644
--- a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
+++ b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
@@ -511,14 +511,6 @@ double DecisionTree<FitnessFunction,
     DimensionSelectionType dimensionSelector)
 {
   // Sanity check on data.
-  // if (data.n_cols != labels.n_elem)
-  // {
-  //   std::ostringstream oss;
-  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-  //       << "does not match number of labels (" << labels.n_elem << ")!"
-  //       << std::endl;
-  //   throw std::invalid_argument(oss.str());
-  // }
   util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
@@ -567,14 +559,6 @@ double DecisionTree<FitnessFunction,
         WeightsType>::type>::value>*)
 {
   // Sanity check on data.
-  // if (data.n_cols != labels.n_elem)
-  // {
-  //   std::ostringstream oss;
-  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-  //       << "does not match number of labels (" << labels.n_elem << ")!"
-  //       << std::endl;
-  //   throw std::invalid_argument(oss.str());
-  // }
   util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
@@ -623,14 +607,6 @@ double DecisionTree<FitnessFunction,
         WeightsType>::type>::value>*)
 {
   // Sanity check on data.
-  // if (data.n_cols != labels.n_elem)
-  // {
-  //   std::ostringstream oss;
-  //   oss << "DecisionTree::Train(): number of points (" << data.n_cols << ") "
-  //       << "does not match number of labels (" << labels.n_elem << ")!"
-  //       << std::endl;
-  //   throw std::invalid_argument(oss.str());
-  // }
   util::CheckSameSizes(data, labels, "DecisionTree::Train()");
 
   using TrueMatType = typename std::decay<MatType>::type;
diff --git a/src/mlpack/tests/size_checks_test.cpp b/src/mlpack/tests/size_checks_test.cpp
index 44539036b9..d5ca71e6a8 100644
--- a/src/mlpack/tests/size_checks_test.cpp
+++ b/src/mlpack/tests/size_checks_test.cpp
@@ -54,8 +54,8 @@ BOOST_AUTO_TEST_CASE(CheckDimensionality)
 
   BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, refSet2, "TestingDim"),
       std::invalid_argument);
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, refSet, "TestingDim"
-      ));
+  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, refSet,
+      "TestingDim"));
 }
 
 BOOST_AUTO_TEST_SUITE_END();

From 7e463525253bcd29fc347821cf78e9b080113595 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Wed, 29 Apr 2020 15:54:43 +0530
Subject: [PATCH 216/253] Updated

---
 src/mlpack/core/cv/cv_base_impl.hpp                     | 2 ++
 src/mlpack/methods/decision_tree/decision_tree_impl.hpp | 1 +
 src/mlpack/methods/linear_svm/linear_svm_impl.hpp       | 1 +
 src/mlpack/methods/lsh/lsh_search_impl.hpp              | 1 +
 src/mlpack/methods/range_search/range_search_impl.hpp   | 1 +
 5 files changed, 6 insertions(+)

diff --git a/src/mlpack/core/cv/cv_base_impl.hpp b/src/mlpack/core/cv/cv_base_impl.hpp
index fc819603db..e5df5d8bca 100644
--- a/src/mlpack/core/cv/cv_base_impl.hpp
+++ b/src/mlpack/core/cv/cv_base_impl.hpp
@@ -12,6 +12,8 @@
 #ifndef MLPACK_CORE_CV_CV_BASE_IMPL_HPP
 #define MLPACK_CORE_CV_CV_BASE_IMPL_HPP
 
+#include <mlpack/core.hpp>
+
 namespace mlpack {
 namespace cv {
 
diff --git a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
index b99075f5b2..171675a84b 100644
--- a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
+++ b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
@@ -13,6 +13,7 @@
 #define MLPACK_METHODS_DECISION_TREE_DECISION_TREE_IMPL_HPP
 
 #include "decision_tree.hpp"
+#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace tree {
diff --git a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
index 69f0887f9d..db7275eff8 100644
--- a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
+++ b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
@@ -14,6 +14,7 @@
 
 // In case it hasn't been included yet.
 #include "linear_svm.hpp"
+#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace svm {
diff --git a/src/mlpack/methods/lsh/lsh_search_impl.hpp b/src/mlpack/methods/lsh/lsh_search_impl.hpp
index 6c3aeb8259..0eb69d850b 100644
--- a/src/mlpack/methods/lsh/lsh_search_impl.hpp
+++ b/src/mlpack/methods/lsh/lsh_search_impl.hpp
@@ -14,6 +14,7 @@
 
 #include <mlpack/prereqs.hpp>
 #include <mlpack/core/math/random.hpp>
+#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace neighbor {
diff --git a/src/mlpack/methods/range_search/range_search_impl.hpp b/src/mlpack/methods/range_search/range_search_impl.hpp
index cce20339a3..0a8162301b 100644
--- a/src/mlpack/methods/range_search/range_search_impl.hpp
+++ b/src/mlpack/methods/range_search/range_search_impl.hpp
@@ -17,6 +17,7 @@
 
 // The rules for traversal.
 #include "range_search_rules.hpp"
+#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace range {

From 30299c0f039c64615576cc9edc6786fc03449e32 Mon Sep 17 00:00:00 2001
From: Bisakh <bisakhmondal00@gmail.com>
Date: Wed, 24 Feb 2021 20:36:11 +0530
Subject: [PATCH 217/253] Two new utility APIs introduced

---
 src/mlpack/core.hpp                           |  1 -
 src/mlpack/core/cv/cv_base_impl.hpp           | 14 +---
 src/mlpack/core/cv/metrics/CMakeLists.txt     |  1 +
 src/mlpack/core/cv/metrics/accuracy.hpp       |  1 +
 src/mlpack/core/cv/metrics/facilities.hpp     | 73 +++++++++++++++++++
 src/mlpack/core/cv/metrics/mse_impl.hpp       |  2 +-
 src/mlpack/core/cv/metrics/r2_score_impl.hpp  |  2 +-
 src/mlpack/core/util/size_checks.hpp          | 47 +++++++-----
 .../decision_tree/decision_tree_impl.hpp      |  1 -
 .../methods/linear_svm/linear_svm_impl.hpp    |  1 -
 src/mlpack/methods/lsh/lsh_search_impl.hpp    |  1 -
 .../range_search/range_search_impl.hpp        |  1 -
 .../softmax_regression/softmax_regression.cpp |  1 -
 src/mlpack/prereqs.hpp                        |  3 +
 src/mlpack/tests/CMakeLists.txt               |  3 +-
 src/mlpack/tests/facilities_test.cpp          | 56 ++++++++++++++
 src/mlpack/tests/size_checks_test.cpp         | 34 ++++-----
 17 files changed, 184 insertions(+), 58 deletions(-)
 create mode 100644 src/mlpack/core/cv/metrics/facilities.hpp
 create mode 100644 src/mlpack/tests/facilities_test.cpp

diff --git a/src/mlpack/core.hpp b/src/mlpack/core.hpp
index c4522ba05f..34cf60dd09 100644
--- a/src/mlpack/core.hpp
+++ b/src/mlpack/core.hpp
@@ -90,7 +90,6 @@
 #include <mlpack/core/dists/diagonal_gaussian_distribution.hpp>
 #include <mlpack/core/data/confusion_matrix.hpp>
 #include <mlpack/core/data/one_hot_encoding.hpp>
-#include <mlpack/core/util/size_checks.hpp>
 
 // mlpack::backtrace only for linux
 #ifdef HAS_BFD_DL
diff --git a/src/mlpack/core/cv/cv_base_impl.hpp b/src/mlpack/core/cv/cv_base_impl.hpp
index e5df5d8bca..0da9f8f4fa 100644
--- a/src/mlpack/core/cv/cv_base_impl.hpp
+++ b/src/mlpack/core/cv/cv_base_impl.hpp
@@ -12,7 +12,7 @@
 #ifndef MLPACK_CORE_CV_CV_BASE_IMPL_HPP
 #define MLPACK_CORE_CV_CV_BASE_IMPL_HPP
 
-#include <mlpack/core.hpp>
+#include <mlpack/prereqs.hpp>
 
 namespace mlpack {
 namespace cv {
@@ -108,7 +108,7 @@ void CVBase<MLAlgorithm,
             WeightsType>::AssertDataConsistency(const MatType& xs,
                                                 const PredictionsType& ys)
 {
-  util::CheckSameSizes(xs, ys, "CVBase::AssertDataConsistency()", "CC",
+  util::CheckSameSizes(xs, (size_t) ys.n_cols, "CVBase::AssertDataConsistency()",
       "predictions");
 }
 
@@ -125,14 +125,8 @@ void CVBase<MLAlgorithm,
   static_assert(MIE::SupportsWeights,
       "The given MLAlgorithm does not support weighted learning");
 
-  if (weights.n_elem != xs.n_cols)
-  {
-    std::ostringstream oss;
-    oss << "CVBase::AssertWeightsConsistency(): number of weights ("
-        << weights.n_elem << ") does not match number of data points ("
-        << xs.n_cols << ")!" << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
+  util::CheckSameSizes(xs, weights, "CVBase::AssertWeightsConsistency()",
+      "weights");
 }
 
 template<typename MLAlgorithm,
diff --git a/src/mlpack/core/cv/metrics/CMakeLists.txt b/src/mlpack/core/cv/metrics/CMakeLists.txt
index e2322e673c..b9edacaf9a 100644
--- a/src/mlpack/core/cv/metrics/CMakeLists.txt
+++ b/src/mlpack/core/cv/metrics/CMakeLists.txt
@@ -6,6 +6,7 @@ set(SOURCES
   average_strategy.hpp
   f1.hpp
   f1_impl.hpp
+  facilities.hpp
   mse.hpp
   mse_impl.hpp
   precision.hpp
diff --git a/src/mlpack/core/cv/metrics/accuracy.hpp b/src/mlpack/core/cv/metrics/accuracy.hpp
index 4fc3600167..481e06a7bb 100644
--- a/src/mlpack/core/cv/metrics/accuracy.hpp
+++ b/src/mlpack/core/cv/metrics/accuracy.hpp
@@ -13,6 +13,7 @@
 #define MLPACK_CORE_CV_METRICS_ACCURACY_HPP
 
 #include <mlpack/core.hpp>
+#include <mlpack/prereqs.hpp>
 
 namespace mlpack {
 namespace cv {
diff --git a/src/mlpack/core/cv/metrics/facilities.hpp b/src/mlpack/core/cv/metrics/facilities.hpp
new file mode 100644
index 0000000000..4cd2a8f36e
--- /dev/null
+++ b/src/mlpack/core/cv/metrics/facilities.hpp
@@ -0,0 +1,73 @@
+/**
+ * @file core/cv/metrics/facilities.hpp
+ * @author Kirill Mishchenko
+ * @author Khizir Siddiqui
+ *
+ * Functionality that is used more than in one metric.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#ifndef MLPACK_CORE_CV_METRICS_FACILITIES_HPP
+#define MLPACK_CORE_CV_METRICS_FACILITIES_HPP
+
+#include <mlpack/core.hpp>
+#include <mlpack/core/metrics/lmetric.hpp>
+
+namespace mlpack {
+namespace cv {
+
+/**
+  * Assert there is the same number of the given data points and labels.
+  *
+  * @param data Column-major data.
+  * @param labels Labels.
+  * @param callerDescription A description of the caller that can be used for
+  *     error generation.
+  * @deprecated Check the new versions, util::CheckSameSizes &
+  * util::CheckSameDimensionality.
+  */
+template<typename DataType>
+void AssertSizes(const DataType& data,
+                 const arma::Row<size_t>& labels,
+                 const std::string& callerDescription)
+{
+  if (data.n_cols != labels.n_elem)
+  {
+    std::ostringstream oss;
+    oss << callerDescription << ": number of points (" << data.n_cols << ") "
+        << "does not match number of labels (" << labels.n_elem << ")!"
+        << std::endl;
+    throw std::invalid_argument(oss.str());
+  }
+}
+
+/**
+  * Pairwise distance of the given data.
+  *
+  * @param data Column-major matrix.
+  * @param metric Distance metric to be used.
+  */
+template<typename DataType, typename Metric>
+DataType PairwiseDistances(const DataType& data,
+                           const Metric& metric)
+{
+  DataType distances = DataType(data.n_cols, data.n_cols, arma::fill::none);
+  for (size_t i = 0; i < data.n_cols; i++)
+  {
+    for (size_t j = 0; j < i; j++)
+    {
+      distances(i, j) = metric.Evaluate(data.col(i), data.col(j));
+      distances(j, i) = distances(i, j);
+    }
+  }
+  distances.diag().zeros();
+  return distances;
+}
+
+} // namespace cv
+} // namespace mlpack
+
+#endif
diff --git a/src/mlpack/core/cv/metrics/mse_impl.hpp b/src/mlpack/core/cv/metrics/mse_impl.hpp
index a55a0e7ed0..d4eb83cd97 100644
--- a/src/mlpack/core/cv/metrics/mse_impl.hpp
+++ b/src/mlpack/core/cv/metrics/mse_impl.hpp
@@ -20,7 +20,7 @@ double MSE::Evaluate(MLAlgorithm& model,
                      const DataType& data,
                      const ResponsesType& responses)
 {
-  util::CheckSameSizes(data, responses, "MSE::Evaluate()", "CC", "responses");
+  util::CheckSameSizes(data,(size_t) responses.n_cols, "MSE::Evaluate()", "responses");
 
   ResponsesType predictedResponses;
   model.Predict(data, predictedResponses);
diff --git a/src/mlpack/core/cv/metrics/r2_score_impl.hpp b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
index dad46216eb..bb3d491447 100644
--- a/src/mlpack/core/cv/metrics/r2_score_impl.hpp
+++ b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
@@ -21,7 +21,7 @@ double R2Score<AdjustedR2>::Evaluate(MLAlgorithm& model,
                                      const DataType& data,
                                      const ResponsesType& responses)
 {
-  util::CheckSameSizes(data, responses, "R2Score::Evaluate()", "CC",
+  util::CheckSameSizes(data,(size_t) responses.n_cols, "R2Score::Evaluate()",
       "responses");
 
   ResponsesType predictedResponses;
diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
index 318de15567..ee06e29214 100644
--- a/src/mlpack/core/util/size_checks.hpp
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -25,37 +25,45 @@ namespace util {
   * @param labels Labels.
   * @param callerDescription A description of the caller that can be used for
   *     error generation.
-  * @param mode For nature of comparision(default "CE").
-  *   types of mode:
-  *     "CE" equivalent to (data.n_cols, labels.n_elem).
-  *     "CC" equivalent to (data.n_cols, labels.n_cols).
-  * @param addInfo  An additional information about labels that can be used for
+  * @param addInfo  Additional information about labels that can be used for
   *	precise error generation. Default is "labels". Another e.g. weights
   */
 template<typename DataType, typename LabelsType>
 inline void CheckSameSizes(const DataType& data,
-                           const LabelsType& labels,
+                           const LabelsType& label,
                            const std::string& callerDescription,
-                           const std::string& mode = "CE",
                            const std::string& addInfo = "labels")
 {
-  if (mode != "CE" && mode != "CC")
-    // For development purpose, not intended for user.
-    Log::Fatal << "Ensure Providing Correct mode." << std::endl;
-
-  const size_t size1 = data.n_cols;
-  const size_t size2 = mode == "CE" ? labels.n_elem : labels.n_cols;
-
-  if (size1 != size2)
+  if (data.n_cols != label.n_elem)
   {
     std::ostringstream oss;
-    oss << callerDescription << ": number of points (" << size1 << ") "
-        << "does not match number of " << addInfo << " (" << size2 << ")!"
+    oss << callerDescription << ": number of points (" << data.n_cols << ") "
+        << "does not match number of " << addInfo << " (" << label.n_elem << ")!"
         << std::endl;
     throw std::invalid_argument(oss.str());
   }
 }
 
+/** An overload of CheckSameSizes() where the size to be checked is known
+ * previously. The second parameter is of type unsigned int.
+ */
+template<typename DataType>
+inline void CheckSameSizes(const DataType& data,
+                           const size_t& size,
+                           const std::string& callerDescription,
+                           const std::string& addInfo = "labels")
+{
+  if (data.n_cols != size)
+  {
+    std::ostringstream oss;
+    oss << callerDescription << ": number of points (" << data.n_cols << ") "
+        << "does not match number of " << addInfo << " (" << size << ")!"
+        << std::endl;
+    throw std::invalid_argument(oss.str());
+  }
+}
+
+
 /**
   * Check for if the given dataset dimension matches with the model's.
   *
@@ -83,8 +91,9 @@ inline void CheckSameDimensionality(const DataType& data,
   }
 }
 
-// An overload of CheckSameDimensionality() where second param is unsigned
-//    long int.
+/** An overload of CheckSameDimensionality() where the dimension to be checked
+ * is known second param is unsigned long int.
+ */
 template<typename DataType>
 inline void CheckSameDimensionality(const DataType& data,
                                     const size_t& dimension,
diff --git a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
index 171675a84b..b99075f5b2 100644
--- a/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
+++ b/src/mlpack/methods/decision_tree/decision_tree_impl.hpp
@@ -13,7 +13,6 @@
 #define MLPACK_METHODS_DECISION_TREE_DECISION_TREE_IMPL_HPP
 
 #include "decision_tree.hpp"
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace tree {
diff --git a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
index db7275eff8..69f0887f9d 100644
--- a/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
+++ b/src/mlpack/methods/linear_svm/linear_svm_impl.hpp
@@ -14,7 +14,6 @@
 
 // In case it hasn't been included yet.
 #include "linear_svm.hpp"
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace svm {
diff --git a/src/mlpack/methods/lsh/lsh_search_impl.hpp b/src/mlpack/methods/lsh/lsh_search_impl.hpp
index 0eb69d850b..6c3aeb8259 100644
--- a/src/mlpack/methods/lsh/lsh_search_impl.hpp
+++ b/src/mlpack/methods/lsh/lsh_search_impl.hpp
@@ -14,7 +14,6 @@
 
 #include <mlpack/prereqs.hpp>
 #include <mlpack/core/math/random.hpp>
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace neighbor {
diff --git a/src/mlpack/methods/range_search/range_search_impl.hpp b/src/mlpack/methods/range_search/range_search_impl.hpp
index 0a8162301b..cce20339a3 100644
--- a/src/mlpack/methods/range_search/range_search_impl.hpp
+++ b/src/mlpack/methods/range_search/range_search_impl.hpp
@@ -17,7 +17,6 @@
 
 // The rules for traversal.
 #include "range_search_rules.hpp"
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace range {
diff --git a/src/mlpack/methods/softmax_regression/softmax_regression.cpp b/src/mlpack/methods/softmax_regression/softmax_regression.cpp
index b269c07690..567241b35a 100644
--- a/src/mlpack/methods/softmax_regression/softmax_regression.cpp
+++ b/src/mlpack/methods/softmax_regression/softmax_regression.cpp
@@ -11,7 +11,6 @@
  */
 
 #include "softmax_regression.hpp"
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace regression {
diff --git a/src/mlpack/prereqs.hpp b/src/mlpack/prereqs.hpp
index 4ec1031235..5eb9ee6fd7 100644
--- a/src/mlpack/prereqs.hpp
+++ b/src/mlpack/prereqs.hpp
@@ -140,4 +140,7 @@ or upgrade Boost to 1.59 or newer.
 // We need to be able to mark functions deprecated.
 #include <mlpack/core/util/deprecated.hpp>
 
+// Include ready to use utility function for better workflow.
+#include <mlpack/core/util/size_checks.hpp>
+
 #endif
diff --git a/src/mlpack/tests/CMakeLists.txt b/src/mlpack/tests/CMakeLists.txt
index a384be6825..cf9628eea3 100644
--- a/src/mlpack/tests/CMakeLists.txt
+++ b/src/mlpack/tests/CMakeLists.txt
@@ -30,7 +30,8 @@ add_executable(mlpack_test
   det_test.cpp
   distribution_test.cpp
   drusilla_select_test.cpp
-  emst_test.cpp 
+  emst_test.cpp
+  facilities_test.cpp
   fastmks_test.cpp
   feedforward_network_test.cpp
   gan_test.cpp
diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
new file mode 100644
index 0000000000..65b754bb4e
--- /dev/null
+++ b/src/mlpack/tests/facilities_test.cpp
@@ -0,0 +1,56 @@
+/**
+ * @file facilities_test.cpp
+ * @author Khizir Siddiqui
+ *
+ * Test file for facilities in metrics.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+
+#include <mlpack/core.hpp>
+#include <mlpack/core/cv/metrics/facilities.hpp>
+#include <mlpack/core/metrics/lmetric.hpp>
+#include <mlpack/core/data/load.hpp>
+
+#include "catch.hpp"
+
+using namespace mlpack;
+using namespace mlpack::cv;
+
+/**
+ * The unequal sizes for data and labels show throw an error.
+ */
+TEST_CASE("AssertSizesTest", "[FacilitiesTest]")
+{
+  // Load the dataset.
+  arma::mat dataset;
+  if (!data::Load("iris_train.csv", dataset))
+    FAIL("Cannot load test dataset iris_train.csv!");
+  // Load the labels.
+  arma::Row<size_t> labels;
+  if (!data::Load("iris_test_labels.csv", labels))
+    FAIL("Cannot load test dataset iris_test_labels.csv!");
+
+  REQUIRE_THROWS_AS(
+    AssertSizes(dataset, labels, "test"), std::invalid_argument);
+}
+
+
+/**
+ * Pairwise distances.
+ */
+TEST_CASE("PairwiseDistanceTest", "[FacilitiesTest]")
+{
+  arma::mat X;
+  X = { { 0, 1, 1, 0, 0 },
+        { 0, 1, 2, 0, 0 },
+        { 1, 1, 3, 2, 0 } };
+  metric::EuclideanDistance metric;
+  arma::mat dist = PairwiseDistances(X, metric);
+  REQUIRE(dist(0, 0) == 0);
+  REQUIRE(dist(1, 0) == Approx(1.41421).epsilon(1e-5));
+  REQUIRE(dist(2, 0) == 3);
+}
diff --git a/src/mlpack/tests/size_checks_test.cpp b/src/mlpack/tests/size_checks_test.cpp
index d5ca71e6a8..d5c7f22e46 100644
--- a/src/mlpack/tests/size_checks_test.cpp
+++ b/src/mlpack/tests/size_checks_test.cpp
@@ -9,54 +9,48 @@
  * 3-clause BSD license along with mlpack.  If not, see
  * http://www.opensource.org/licenses/BSD-3-Clause for more information.
  */
-#include <mlpack/core.hpp>
-#include <boost/test/unit_test.hpp>
+#include <mlpack/prereqs.hpp>
+#include "catch.hpp"
 
 using namespace mlpack;
 using namespace mlpack::util;
-BOOST_AUTO_TEST_SUITE(SizeCheckTest);
 
 /**
  * Test that CheckSameSizes() works in different cases.
  */
-BOOST_AUTO_TEST_CASE(CheckSizeTest)
+TEST_CASE("CheckSizeTest", "[SizeCheckTest]")
 {
   arma::mat data = arma::randu<arma::mat>(20, 30);
   arma::colvec firstLabels = arma::randu<arma::colvec>(20);
   arma::colvec secondLabels = arma::randu<arma::colvec>(30);
-  arma::mat thirdLabels = arma::randu<arma::mat>(20, 30);
+  arma::mat thirdLabels = arma::randu<arma::mat>(40, 30);
 
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking"),
+  REQUIRE_THROWS_AS(CheckSameSizes(data, firstLabels, "TestChecking"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "CC"),
+  REQUIRE_THROWS_AS(CheckSameSizes(data, (size_t) 20, "TestChecking"),
       std::invalid_argument);
-  BOOST_REQUIRE_THROW(CheckSameSizes(data, firstLabels, "TestChecking", "AB"),
-      std::runtime_error);
 
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, secondLabels, "TestChecking"));
-  BOOST_REQUIRE_NO_THROW(CheckSameSizes(data, thirdLabels, "TestChecking",
-      "CC"));
+  REQUIRE_NOTHROW(CheckSameSizes(data, secondLabels, "TestChecking"));
+  REQUIRE_NOTHROW(CheckSameSizes(data, (size_t) 30, "TestChecking"));
+  REQUIRE_NOTHROW(CheckSameSizes(data, (size_t) thirdLabels.n_cols, "TestChecking"));
 }
 
 /**
  * Test that CheckSameDimensionality() works in different cases.
  */
-BOOST_AUTO_TEST_CASE(CheckDimensionality)
+TEST_CASE("CheckDimensionality", "[SizeCheckTest]")
 {
   arma::mat dataset = arma::randu<arma::mat>(20, 30);
   arma::colvec refSet = arma::randu<arma::colvec>(20);
   arma::colvec refSet2 = arma::randu<arma::colvec>(40);
 
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, (size_t) 20,
+  REQUIRE_NOTHROW(CheckSameDimensionality(dataset, (size_t) 20,
       "TestingDim"));
-  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, (size_t) 100,
+  REQUIRE_THROWS_AS(CheckSameDimensionality(dataset, (size_t) 100,
       "TestingDim"), std::invalid_argument);
 
-  BOOST_REQUIRE_THROW(CheckSameDimensionality(dataset, refSet2, "TestingDim"),
+  REQUIRE_THROWS_AS(CheckSameDimensionality(dataset, refSet2, "TestingDim"),
       std::invalid_argument);
-  BOOST_REQUIRE_NO_THROW(CheckSameDimensionality(dataset, refSet,
+  REQUIRE_NOTHROW(CheckSameDimensionality(dataset, refSet,
       "TestingDim"));
 }
-
-BOOST_AUTO_TEST_SUITE_END();
-

From de67fb4faae8f7e31c3fd38daf4f9b7428f428af Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Wed, 24 Feb 2021 20:39:50 +0530
Subject: [PATCH 218/253] Grammar fix as suggested by @rcurtin

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/util/size_checks.hpp | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
index ee06e29214..1ef5555749 100644
--- a/src/mlpack/core/util/size_checks.hpp
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -71,7 +71,7 @@ inline void CheckSameSizes(const DataType& data,
   * @param dimension Dimension of the model.
   * @param callerDescription A description of the caller that can be used for
   *     error generation.
-  * @param addInfo  An additional information about data that can be used for
+  * @param addInfo Additional information about data that can be used for
   *	precise error generation. Default is "dataset". Another e.g. weights.
   */
 template<typename DataType, typename DimType>
@@ -114,4 +114,3 @@ inline void CheckSameDimensionality(const DataType& data,
 } // namespace mlpack
 
 #endif
-

From c474e30378cfed52f5c03d664e69a0a03a8b8c0a Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Sat, 27 Feb 2021 21:49:20 +0530
Subject: [PATCH 219/253] Applying suggestions from code review by @rcurtin

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/cv/metrics/mse_impl.hpp      |  3 +-
 src/mlpack/core/cv/metrics/r2_score_impl.hpp |  2 +-
 src/mlpack/core/util/size_checks.hpp         | 42 ++++++++++----------
 src/mlpack/prereqs.hpp                       |  2 +-
 4 files changed, 26 insertions(+), 23 deletions(-)

diff --git a/src/mlpack/core/cv/metrics/mse_impl.hpp b/src/mlpack/core/cv/metrics/mse_impl.hpp
index d4eb83cd97..d2fdcf8e74 100644
--- a/src/mlpack/core/cv/metrics/mse_impl.hpp
+++ b/src/mlpack/core/cv/metrics/mse_impl.hpp
@@ -20,7 +20,8 @@ double MSE::Evaluate(MLAlgorithm& model,
                      const DataType& data,
                      const ResponsesType& responses)
 {
-  util::CheckSameSizes(data,(size_t) responses.n_cols, "MSE::Evaluate()", "responses");
+  util::CheckSameSizes(data, (size_t) responses.n_cols, "MSE::Evaluate()",
+      "responses");
 
   ResponsesType predictedResponses;
   model.Predict(data, predictedResponses);
diff --git a/src/mlpack/core/cv/metrics/r2_score_impl.hpp b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
index bb3d491447..00eb9a1448 100644
--- a/src/mlpack/core/cv/metrics/r2_score_impl.hpp
+++ b/src/mlpack/core/cv/metrics/r2_score_impl.hpp
@@ -21,7 +21,7 @@ double R2Score<AdjustedR2>::Evaluate(MLAlgorithm& model,
                                      const DataType& data,
                                      const ResponsesType& responses)
 {
-  util::CheckSameSizes(data,(size_t) responses.n_cols, "R2Score::Evaluate()",
+  util::CheckSameSizes(data, (size_t) responses.n_cols, "R2Score::Evaluate()",
       "responses");
 
   ResponsesType predictedResponses;
diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
index 1ef5555749..933655f475 100644
--- a/src/mlpack/core/util/size_checks.hpp
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -19,15 +19,15 @@ namespace mlpack {
 namespace util {
 
 /**
-  * Check for if the given data points & labels have same size.
-  *
-  * @param data data.
-  * @param labels Labels.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  * @param addInfo  Additional information about labels that can be used for
-  *	precise error generation. Default is "labels". Another e.g. weights
-  */
+ * Check for if the given data points & labels have same size.
+ *
+ * @param data data.
+ * @param labels Labels.
+ * @param callerDescription A description of the caller that can be used for
+ *     error generation.
+ * @param addInfo Name to use for labels for precise error generation. Default
+ *     is "labels"; for example, "weights" could also be used.
+ */
 template<typename DataType, typename LabelsType>
 inline void CheckSameSizes(const DataType& data,
                            const LabelsType& label,
@@ -44,7 +44,8 @@ inline void CheckSameSizes(const DataType& data,
   }
 }
 
-/** An overload of CheckSameSizes() where the size to be checked is known
+/**
+ * An overload of CheckSameSizes() where the size to be checked is known
  * previously. The second parameter is of type unsigned int.
  */
 template<typename DataType>
@@ -65,15 +66,15 @@ inline void CheckSameSizes(const DataType& data,
 
 
 /**
-  * Check for if the given dataset dimension matches with the model's.
-  *
-  * @param data dataset.
-  * @param dimension Dimension of the model.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  * @param addInfo Additional information about data that can be used for
-  *	precise error generation. Default is "dataset". Another e.g. weights.
-  */
+ * Check for if the given dataset dimension matches with the model's.
+ *
+ * @param data dataset.
+ * @param dimension Dimension of the model.
+ * @param callerDescription A description of the caller that can be used for
+ *     error generation.
+ * @param addInfo Name to use for dataset for precise error generation. Default
+ *     is "dataset"; for example, "weights" could also be used.
+ */
 template<typename DataType, typename DimType>
 inline void CheckSameDimensionality(const DataType& data,
                                     const DimType& dimension,
@@ -91,7 +92,8 @@ inline void CheckSameDimensionality(const DataType& data,
   }
 }
 
-/** An overload of CheckSameDimensionality() where the dimension to be checked
+/**
+ * An overload of CheckSameDimensionality() where the dimension to be checked
  * is known second param is unsigned long int.
  */
 template<typename DataType>
diff --git a/src/mlpack/prereqs.hpp b/src/mlpack/prereqs.hpp
index 5eb9ee6fd7..1d049d711c 100644
--- a/src/mlpack/prereqs.hpp
+++ b/src/mlpack/prereqs.hpp
@@ -140,7 +140,7 @@ or upgrade Boost to 1.59 or newer.
 // We need to be able to mark functions deprecated.
 #include <mlpack/core/util/deprecated.hpp>
 
-// Include ready to use utility function for better workflow.
+// Include ready to use utility function to check sizes of datasets.
 #include <mlpack/core/util/size_checks.hpp>
 
 #endif

From 970588c5daa9f15173c833be60558d5b8561e6f2 Mon Sep 17 00:00:00 2001
From: Bisakh <bisakhmondal00@gmail.com>
Date: Sat, 27 Feb 2021 22:46:50 +0530
Subject: [PATCH 220/253] AssertSizes api has been replaced by CheckSameSizes

---
 src/mlpack/core/cv/metrics/facilities.hpp     | 25 -------------------
 .../core/cv/metrics/silhouette_score_impl.hpp |  6 ++---
 src/mlpack/tests/facilities_test.cpp          | 19 --------------
 3 files changed, 3 insertions(+), 47 deletions(-)

diff --git a/src/mlpack/core/cv/metrics/facilities.hpp b/src/mlpack/core/cv/metrics/facilities.hpp
index 4cd2a8f36e..fdd5b1216a 100644
--- a/src/mlpack/core/cv/metrics/facilities.hpp
+++ b/src/mlpack/core/cv/metrics/facilities.hpp
@@ -19,31 +19,6 @@
 namespace mlpack {
 namespace cv {
 
-/**
-  * Assert there is the same number of the given data points and labels.
-  *
-  * @param data Column-major data.
-  * @param labels Labels.
-  * @param callerDescription A description of the caller that can be used for
-  *     error generation.
-  * @deprecated Check the new versions, util::CheckSameSizes &
-  * util::CheckSameDimensionality.
-  */
-template<typename DataType>
-void AssertSizes(const DataType& data,
-                 const arma::Row<size_t>& labels,
-                 const std::string& callerDescription)
-{
-  if (data.n_cols != labels.n_elem)
-  {
-    std::ostringstream oss;
-    oss << callerDescription << ": number of points (" << data.n_cols << ") "
-        << "does not match number of labels (" << labels.n_elem << ")!"
-        << std::endl;
-    throw std::invalid_argument(oss.str());
-  }
-}
-
 /**
   * Pairwise distance of the given data.
   *
diff --git a/src/mlpack/core/cv/metrics/silhouette_score_impl.hpp b/src/mlpack/core/cv/metrics/silhouette_score_impl.hpp
index 89041f736e..b271f0d6df 100644
--- a/src/mlpack/core/cv/metrics/silhouette_score_impl.hpp
+++ b/src/mlpack/core/cv/metrics/silhouette_score_impl.hpp
@@ -22,7 +22,7 @@ double SilhouetteScore::Overall(const DataType& X,
                                 const arma::Row<size_t>& labels,
                                 const Metric& metric)
 {
-  AssertSizes(X, labels, "SilhouetteScore::Overall()");
+  util::CheckSameSizes(X, labels, "SilhouetteScore::Overall()");
   return arma::mean(SamplesScore(X, labels, metric));
 }
 
@@ -30,7 +30,7 @@ template<typename DataType>
 arma::rowvec SilhouetteScore::SamplesScore(const DataType& distances,
                                            const arma::Row<size_t>& labels)
 {
-  AssertSizes(distances, labels, "SilhouetteScore::SamplesScore()");
+  util::CheckSameSizes(distances, labels, "SilhouetteScore::SamplesScore()");
 
   // Stores the silhouette scores of individual samples.
   arma::rowvec sampleScores(distances.n_rows);
@@ -76,7 +76,7 @@ arma::rowvec SilhouetteScore::SamplesScore(const DataType& X,
                                            const arma::Row<size_t>& labels,
                                            const Metric& metric)
 {
-  AssertSizes(X, labels, "SilhouetteScore::SamplesScore()");
+  util::CheckSameSizes(X, labels, "SilhouetteScore::SamplesScore()");
   DataType distances = PairwiseDistances(X, metric);
   return SamplesScore(distances, labels);
 }
diff --git a/src/mlpack/tests/facilities_test.cpp b/src/mlpack/tests/facilities_test.cpp
index 65b754bb4e..d4bcec3c3b 100644
--- a/src/mlpack/tests/facilities_test.cpp
+++ b/src/mlpack/tests/facilities_test.cpp
@@ -20,25 +20,6 @@
 using namespace mlpack;
 using namespace mlpack::cv;
 
-/**
- * The unequal sizes for data and labels show throw an error.
- */
-TEST_CASE("AssertSizesTest", "[FacilitiesTest]")
-{
-  // Load the dataset.
-  arma::mat dataset;
-  if (!data::Load("iris_train.csv", dataset))
-    FAIL("Cannot load test dataset iris_train.csv!");
-  // Load the labels.
-  arma::Row<size_t> labels;
-  if (!data::Load("iris_test_labels.csv", labels))
-    FAIL("Cannot load test dataset iris_test_labels.csv!");
-
-  REQUIRE_THROWS_AS(
-    AssertSizes(dataset, labels, "test"), std::invalid_argument);
-}
-
-
 /**
  * Pairwise distances.
  */

From cdede9018bdf5f22735b11b3815c9a01662ea03d Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 27 Feb 2021 15:59:50 -0500
Subject: [PATCH 221/253] Make sure feedforward_network_2_test.cpp gets
 compiled and run.

---
 src/mlpack/tests/CMakeLists.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/mlpack/tests/CMakeLists.txt b/src/mlpack/tests/CMakeLists.txt
index e6dd629266..e94c73e0d3 100644
--- a/src/mlpack/tests/CMakeLists.txt
+++ b/src/mlpack/tests/CMakeLists.txt
@@ -34,6 +34,7 @@ add_executable(mlpack_test
   facilities_test.cpp
   fastmks_test.cpp
   feedforward_network_test.cpp
+  feedforward_network_2_test.cpp
   gan_test.cpp
   gmm_test.cpp
   hmm_test.cpp

From bf238ed213d2d09dfeae40c506f57402d6e04293 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 27 Feb 2021 16:09:13 -0500
Subject: [PATCH 222/253] Don't take a second argument for ToLower().

---
 src/mlpack/core/util/to_lower.hpp                            | 5 +++--
 src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp     | 3 +--
 src/mlpack/methods/ann/layer/convolution_impl.hpp            | 3 +--
 src/mlpack/methods/ann/layer/transposed_convolution_impl.hpp | 3 +--
 4 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/src/mlpack/core/util/to_lower.hpp b/src/mlpack/core/util/to_lower.hpp
index 866b160ffd..98f46de9b5 100644
--- a/src/mlpack/core/util/to_lower.hpp
+++ b/src/mlpack/core/util/to_lower.hpp
@@ -19,12 +19,13 @@ namespace util {
  * Convert a string to lowercase letters.
  *
  * @param input The string to convert.
- * @param output The string to be converted.
  */
-inline void ToLower(const std::string& input, std::string& output)
+inline std::string ToLower(const std::string& input)
 {
+  std::string output;
   std::transform(input.begin(), input.end(), output.begin(),
       [](unsigned char c){ return std::tolower(c); });
+  return output;
 }
 
 } // namespace util
diff --git a/src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp b/src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp
index cfb200e3ec..2377ddee00 100644
--- a/src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp
+++ b/src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp
@@ -125,8 +125,7 @@ AtrousConvolution<
   weights.set_size(WeightSize(), 1);
 
   // Transform paddingType to lowercase.
-  std::string paddingTypeLow = paddingType;
-  util::ToLower(paddingType, paddingTypeLow);
+  const std::string paddingTypeLow = util::ToLower(paddingType);
 
   size_t padWLeft = std::get<0>(padW);
   size_t padWRight = std::get<1>(padW);
diff --git a/src/mlpack/methods/ann/layer/convolution_impl.hpp b/src/mlpack/methods/ann/layer/convolution_impl.hpp
index 5018593279..7e6cebf184 100644
--- a/src/mlpack/methods/ann/layer/convolution_impl.hpp
+++ b/src/mlpack/methods/ann/layer/convolution_impl.hpp
@@ -120,8 +120,7 @@ Convolution<
   weights.set_size(WeightSize(), 1);
 
   // Transform paddingType to lowercase.
-  std::string paddingTypeLow = paddingType;
-  util::ToLower(paddingType, paddingTypeLow);
+  const std::string paddingTypeLow = util::ToLower(paddingType);
 
   if (paddingTypeLow == "valid")
   {
diff --git a/src/mlpack/methods/ann/layer/transposed_convolution_impl.hpp b/src/mlpack/methods/ann/layer/transposed_convolution_impl.hpp
index 47cf2cd6c8..d932acb6a7 100644
--- a/src/mlpack/methods/ann/layer/transposed_convolution_impl.hpp
+++ b/src/mlpack/methods/ann/layer/transposed_convolution_impl.hpp
@@ -126,8 +126,7 @@ TransposedConvolution<
 {
   weights.set_size(WeightSize(), 1);
   // Transform paddingType to lowercase.
-  std::string paddingTypeLow = paddingType;
-  util::ToLower(paddingType, paddingTypeLow);
+  const std::string paddingTypeLow = util::ToLower(paddingType);
 
   if (paddingTypeLow == "valid")
   {

From 355e6db33a2b187e9b06aa780a725aadc267320b Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 27 Feb 2021 16:50:39 -0500
Subject: [PATCH 223/253] Oops, use std::back_inserter().

---
 src/mlpack/core/util/to_lower.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/util/to_lower.hpp b/src/mlpack/core/util/to_lower.hpp
index 98f46de9b5..f427449baf 100644
--- a/src/mlpack/core/util/to_lower.hpp
+++ b/src/mlpack/core/util/to_lower.hpp
@@ -23,7 +23,7 @@ namespace util {
 inline std::string ToLower(const std::string& input)
 {
   std::string output;
-  std::transform(input.begin(), input.end(), output.begin(),
+  std::transform(input.begin(), input.end(), std::back_inserter(output),
       [](unsigned char c){ return std::tolower(c); });
   return output;
 }

From 12333a6b8b797807e658a5d513ead0e4148c0266 Mon Sep 17 00:00:00 2001
From: Bisakh Mondal <bisakhmondal00@gmail.com>
Date: Sun, 28 Feb 2021 05:46:51 +0530
Subject: [PATCH 224/253] Update src/mlpack/core/util/size_checks.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/util/size_checks.hpp | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/mlpack/core/util/size_checks.hpp b/src/mlpack/core/util/size_checks.hpp
index 933655f475..ab81a9b355 100644
--- a/src/mlpack/core/util/size_checks.hpp
+++ b/src/mlpack/core/util/size_checks.hpp
@@ -13,7 +13,6 @@
 #ifndef MLPACK_UTIL_SIZE_CHECKS_HPP
 #define MLPACK_UTIL_SIZE_CHECKS_HPP
 
-#include <mlpack/core.hpp>
 
 namespace mlpack {
 namespace util {

From 6800e5a05885b15fadaf905cdce2ad156a866f65 Mon Sep 17 00:00:00 2001
From: Gopi M Tatiraju <deathcoderx@gmail.com>
Date: Mon, 1 Mar 2021 15:34:06 +0530
Subject: [PATCH 225/253] Apply suggestions from code review

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/tests/feedforward_network_2_test.cpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/tests/feedforward_network_2_test.cpp b/src/mlpack/tests/feedforward_network_2_test.cpp
index 3a57624d26..90ba3c3fbd 100644
--- a/src/mlpack/tests/feedforward_network_2_test.cpp
+++ b/src/mlpack/tests/feedforward_network_2_test.cpp
@@ -66,7 +66,7 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
   // Load the dataset.
   arma::mat trainData;
   if (!data::Load("thyroid_train.csv", trainData))
-    Fail("Cannot open thyroid_train.csv");
+    FAIL("Cannot open thyroid_train.csv");
 
   arma::mat trainLabels = trainData.row(trainData.n_rows - 1);
   trainData.shed_row(trainData.n_rows - 1);
@@ -79,7 +79,7 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
 
   arma::mat testData;
   if (!data::Load("thyroid_test.csv", testData))
-    Fail("Cannot open thyroid_test.csv");
+    FAIL("Cannot open thyroid_test.csv");
 
   arma::mat testLabels = testData.row(testData.n_rows - 1);
   testData.shed_row(testData.n_rows - 1);
@@ -139,4 +139,4 @@ TEST_CASE("RBFNetworkTest", "[FeedForwardNetworkTest]")
 
   // RBFN neural net with MeanSquaredError.
   TestNetwork<>(model1, dataset, labels1, dataset, labels, 10, 0.1);
-}
\ No newline at end of file
+}

From f33f003c3e9d9ea0d8906706e47be92dd9f98c58 Mon Sep 17 00:00:00 2001
From: onikolskyy <onikolskyy@gmail.com>
Date: Mon, 1 Mar 2021 15:03:08 +0100
Subject: [PATCH 226/253] fix default values of cmake config for bindings in
 docs

---
 doc/guide/build.hpp | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/doc/guide/build.hpp b/doc/guide/build.hpp
index d889652e81..9996f5132d 100644
--- a/doc/guide/build.hpp
+++ b/doc/guide/build.hpp
@@ -175,9 +175,13 @@ The full list of options mlpack allows:
        (i.e. \c mlpack_knn, \c mlpack_kfn, \c mlpack_logistic_regression, etc.)
        (default ON)
  - BUILD_PYTHON_BINDINGS=(ON/OFF): compile the bindings for Python, if the
-       necessary Python libraries are available (default ON except on Windows)
+       necessary Python libraries are available (default OFF)
+ - BUILD_R_BINDINGS=(ON/OFF): compile the bindings for R, if R is found
+       (default OFF)
+ - BUILD_GO_BINDINGS=(ON/OFF): compile Go bindings, if Go and the necessary Go
+       and Gonum exist. (default OFF)
  - BUILD_JULIA_BINDINGS=(ON/OFF): compile Julia bindings, if Julia is found
-       (default ON)
+       (default OFF)
  - BUILD_SHARED_LIBS=(ON/OFF): compile shared libraries as opposed to
        static libraries (default ON)
  - TEST_VERBOSE=(ON/OFF): run test cases in \c mlpack_test with verbose output

From 89163f648332d7c8a1d7137ea4c17bb01e5b3274 Mon Sep 17 00:00:00 2001
From: RishabhGarg108 <rishabhgarg108@gmail.com>
Date: Tue, 2 Mar 2021 13:01:13 +0530
Subject: [PATCH 227/253] Templated labels for field labels

---
 src/mlpack/core/data/split_data.hpp | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index da4c240ca2..61f9860f54 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -405,16 +405,16 @@ Split(const arma::Mat<T>& input,
  * @param shuffleData If true, the sample order is shuffled; otherwise, each
  *       sample is visited in linear order. (Default true.)
  */
-template <typename FieldType,
+template <typename FieldType, typename T,
           typename = std::enable_if_t<
               arma::is_Col<typename FieldType::object_type>::value ||
               arma::is_Mat_only<typename FieldType::object_type>::value>>
 void Split(const FieldType& input,
-           const arma::field<arma::vec>& inputLabel,
+           const arma::field<T>& inputLabel,
            FieldType& trainData,
-           arma::field<arma::vec>& trainLabel,
+           arma::field<T>& trainLabel,
            FieldType& testData,
-           arma::field<arma::vec>& testLabel,
+           arma::field<T>& testLabel,
            const double testRatio,
            const bool shuffleData = true)
 {
@@ -574,20 +574,20 @@ void Split(const FieldType& input,
  *      (FieldType), trainLabel (arma::field<arma::vec>), and
  *                   testLabel (arma::field<arma::vec>).
  */
-template <class FieldType,
+template <class FieldType, typename T,
           class = std::enable_if_t<
               arma::is_Col<typename FieldType::object_type>::value ||
               arma::is_Mat_only<typename FieldType::object_type>::value>>
-std::tuple<FieldType, FieldType, arma::field<arma::vec>, arma::field<arma::vec>>
+std::tuple<FieldType, FieldType, arma::field<T>, arma::field<T>>
 Split(const FieldType& input,
-      const arma::field<arma::vec>& inputLabel,
+      const arma::field<T>& inputLabel,
       const double testRatio,
       const bool shuffleData = true)
 {
   FieldType trainData;
   FieldType testData;
-  arma::field<arma::vec> trainLabel;
-  arma::field<arma::vec> testLabel;
+  arma::field<T> trainLabel;
+  arma::field<T> testLabel;
 
   Split(input, inputLabel, trainData, trainLabel, testData, testLabel,
       testRatio, shuffleData);

From 9bffdb6d6e15e82d8b14ad3489909aa7c7b6657f Mon Sep 17 00:00:00 2001
From: Tru Hoang <trugiahoang@gmail.com>
Date: Tue, 2 Mar 2021 13:51:51 -0800
Subject: [PATCH 228/253] Add CMake linking for OpenMP

. Fixes build error for macOS 10.15 Catalina (#2412)

* Update CMakeLists for macOS Catalina build

* The XCode switch is probably not necessary with the new version.

* Test OpenMP on macOS 10.15.

* Update CMakeLists.txt

Add guard condition for OpenMP_CXX_LIBRARIES for compatible CMake versions

Co-authored-by: Ryan Birmingham <birm@rbirm.us>

* Update CMakeLists.txt

Add endif()

Co-authored-by: Ryan Birmingham <birm@rbirm.us>

* export OMP_NUM_THREADS in CI script

* Empty commit to set up deployments

* Use macOS latest image.

* Add name to list of contributors

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
Co-authored-by: Ryan Birmingham <birm@rbirm.us>
---
 .ci/macos-steps.yaml | 4 ++--
 CMakeLists.txt       | 3 +++
 COPYRIGHT.txt        | 1 +
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/.ci/macos-steps.yaml b/.ci/macos-steps.yaml
index 85e92fe3b3..ce3c7796f5 100644
--- a/.ci/macos-steps.yaml
+++ b/.ci/macos-steps.yaml
@@ -14,7 +14,7 @@ steps:
     set -e
     sudo xcode-select --switch /Applications/Xcode_12.2.app/Contents/Developer
     unset BOOST_ROOT
-    brew install openblas armadillo boost cereal
+    brew install libomp openblas armadillo boost cereal
 
     if [ "$(binding)" == "python" ]; then
       pip install --upgrade pip
@@ -65,4 +65,4 @@ steps:
   inputs:
     pathtoPublish: 'build/Testing/'
     artifactName: 'Tests'
-  displayName: 'Publish artifacts test results'
+  displayName: 'Publish artifacts test results'
\ No newline at end of file
diff --git a/CMakeLists.txt b/CMakeLists.txt
index e0be77df06..2ecd13769c 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -467,6 +467,9 @@ if (OPENMP_FOUND)
   add_definitions(-DHAS_OPENMP)
   set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
+  if(OpenMP_CXX_FOUND)
+    set(MLPACK_LIBRARIES ${MLPACK_LIBRARIES} ${OpenMP_CXX_LIBRARIES})
+  endif ()
 else ()
   # Disable warnings for all the unknown OpenMP pragmas.
   if (NOT MSVC)
diff --git a/COPYRIGHT.txt b/COPYRIGHT.txt
index d2d177da71..a3c8f90f38 100644
--- a/COPYRIGHT.txt
+++ b/COPYRIGHT.txt
@@ -141,6 +141,7 @@ Copyright:
   Copyright 2020, Alex Nguyen <alexvn.edu@gmail.com>
   Copyright 2020, Gaurav Ghati <gauravghatii@gmail.com>
   Copyright 2020, Anmolpreet Singh <anmol323c@gmail.com>
+  Copyright 2021, Tru Hoang <trugiahoang@gmail.com>
 
 License: BSD-3-clause
   All rights reserved.

From 08d2a6d68db1eb4b7ecc3b043789684b6ab6806e Mon Sep 17 00:00:00 2001
From: Oleksandr Nikolskyy <onikolskyy@gmail.com>
Date: Thu, 4 Mar 2021 20:33:56 +0100
Subject: [PATCH 229/253] add WeightSize() Method for linear_no_bias and
 radial_basis_function

---
 src/mlpack/methods/ann/layer/linear_no_bias.hpp        | 6 ++++++
 src/mlpack/methods/ann/layer/linear_no_bias_impl.hpp   | 2 +-
 src/mlpack/methods/ann/layer/radial_basis_function.hpp | 6 ++++++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/src/mlpack/methods/ann/layer/linear_no_bias.hpp b/src/mlpack/methods/ann/layer/linear_no_bias.hpp
index 7182e84238..5426f1ff4f 100644
--- a/src/mlpack/methods/ann/layer/linear_no_bias.hpp
+++ b/src/mlpack/methods/ann/layer/linear_no_bias.hpp
@@ -123,6 +123,12 @@ class LinearNoBias
   //! Modify the gradient.
   OutputDataType& Gradient() { return gradient; }
 
+  //! Get the size of the weights.
+  size_t WeightSize() const
+  {
+    return inSize * outSize;
+  }
+
   //! Get the shape of the input.
   size_t InputShape() const
   {
diff --git a/src/mlpack/methods/ann/layer/linear_no_bias_impl.hpp b/src/mlpack/methods/ann/layer/linear_no_bias_impl.hpp
index 032552f599..dbea56e94f 100644
--- a/src/mlpack/methods/ann/layer/linear_no_bias_impl.hpp
+++ b/src/mlpack/methods/ann/layer/linear_no_bias_impl.hpp
@@ -38,7 +38,7 @@ LinearNoBias<InputDataType, OutputDataType, RegularizerType>::LinearNoBias(
     outSize(outSize),
     regularizer(regularizer)
 {
-  weights.set_size(outSize * inSize, 1);
+  weights.set_size(WeightSize(), 1);
 }
 
 template<typename InputDataType, typename OutputDataType,
diff --git a/src/mlpack/methods/ann/layer/radial_basis_function.hpp b/src/mlpack/methods/ann/layer/radial_basis_function.hpp
index 2387d612ab..6f84303360 100644
--- a/src/mlpack/methods/ann/layer/radial_basis_function.hpp
+++ b/src/mlpack/methods/ann/layer/radial_basis_function.hpp
@@ -110,6 +110,12 @@ class RBF
   //! Modify the delta.
   OutputDataType& Delta() { return delta; }
 
+  //! Get the size of the weights.
+  size_t WeightSize() const
+  {
+    return 0;
+  }
+
   //! Get the shape of the input.
   size_t InputShape() const
   {

From 5a59f757ed3514e68c4fff6853898089944ad64a Mon Sep 17 00:00:00 2001
From: Oleksandr Nikolskyy <onikolskyy@gmail.com>
Date: Thu, 4 Mar 2021 20:42:12 +0100
Subject: [PATCH 230/253] add WeightSize() Method for constant

---
 src/mlpack/methods/ann/layer/constant.hpp | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/src/mlpack/methods/ann/layer/constant.hpp b/src/mlpack/methods/ann/layer/constant.hpp
index b908a0018e..9a0956ddf8 100644
--- a/src/mlpack/methods/ann/layer/constant.hpp
+++ b/src/mlpack/methods/ann/layer/constant.hpp
@@ -79,6 +79,12 @@ class Constant
   //! Get the output size.
   size_t OutSize() const { return outSize; }
 
+  //! Get the size of the weights.
+  size_t WeightSize() const
+  {
+    return 0;
+  }
+
   /**
    * Serialize the layer.
    */

From 6e241b33617364876179951d888114a81396c5be Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 5 Mar 2021 00:09:59 -0500
Subject: [PATCH 231/253] Fix anchor links in generated Markdown documentation
 (#2856)

* Use the correct binding name to generate the anchor link.

* Fix compilation warnings.
---
 src/mlpack/bindings/go/print_type_doc_impl.hpp     |  2 +-
 src/mlpack/bindings/markdown/print_docs.cpp        | 14 ++++++++++++--
 .../simple_residue_termination.hpp                 |  6 +++---
 .../svd_complete_incremental_learning.hpp          |  2 +-
 4 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/bindings/go/print_type_doc_impl.hpp b/src/mlpack/bindings/go/print_type_doc_impl.hpp
index 0755f60b8a..d0a5fef659 100644
--- a/src/mlpack/bindings/go/print_type_doc_impl.hpp
+++ b/src/mlpack/bindings/go/print_type_doc_impl.hpp
@@ -84,7 +84,7 @@ std::string PrintTypeDoc(
  */
 template<typename T>
 std::string PrintTypeDoc(
-    util::ParamData& data,
+    util::ParamData& /* data */,
     const typename std::enable_if<arma::is_arma_type<T>::value>::type*)
 {
   if (T::is_col || T::is_row)
diff --git a/src/mlpack/bindings/markdown/print_docs.cpp b/src/mlpack/bindings/markdown/print_docs.cpp
index 45b9807afa..44adf69e93 100644
--- a/src/mlpack/bindings/markdown/print_docs.cpp
+++ b/src/mlpack/bindings/markdown/print_docs.cpp
@@ -36,8 +36,18 @@ void PrintHeaders(const std::string& bindingName,
   {
     BindingInfo::Language() = languages[i];
 
-    cout << " - [" << GetBindingName(bindingName) << "](#" << languages[i]
-        << "_" << bindingName << "){: .language-link #" << languages[i] << " }"
+    // Get the name of the binding in the target language, and convert it to
+    // lowercase (since the anchor link will be in lowercase).
+    const std::string langBindingName = GetBindingName(bindingName);
+    std::string anchorName = langBindingName;
+    std::transform(anchorName.begin(), anchorName.end(), anchorName.begin(),
+        [](unsigned char c) { return std::tolower(c); });
+    // Strip '()' from the end if needed.
+    if (anchorName.substr(anchorName.size() - 2, 2) == "()")
+      anchorName = anchorName.substr(0, anchorName.size() - 2);
+
+    cout << " - [" << langBindingName << "](#" << languages[i]
+        << "_" << anchorName << "){: .language-link #" << languages[i] << " }"
         << endl;
   }
 }
diff --git a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
index 86631e32ce..6c214795c4 100644
--- a/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
+++ b/src/mlpack/methods/amf/termination_policies/simple_residue_termination.hpp
@@ -45,9 +45,9 @@ class SimpleResidueTermination
     maxIterations(maxIterations),
     residue(0.0),
     iteration(0),
-    nm(0),
-    normOld(0)
-  { 
+    normOld(0),
+    nm(0)
+  {
     // Nothing to do here.
   }
 
diff --git a/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp b/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
index 37b7ab8c0a..ab2e9d2503 100644
--- a/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
+++ b/src/mlpack/methods/amf/update_rules/svd_complete_incremental_learning.hpp
@@ -172,7 +172,7 @@ class SVDCompleteIncrementalLearning<arma::sp_mat>
   SVDCompleteIncrementalLearning(double u = 0.01,
                                  double kw = 0,
                                  double kh = 0)
-            : u(u), kw(kw), kh(kh), it(NULL), m(0), n(0), isStart(false)
+            : u(u), kw(kw), kh(kh), n(0), m(0), it(NULL), isStart(false)
     {}
 
   ~SVDCompleteIncrementalLearning()

From d53b08d936971531be77a8d3cca2737846d13692 Mon Sep 17 00:00:00 2001
From: Anush V Kini <anushkini@gmail.com>
Date: Fri, 5 Mar 2021 13:17:05 +0530
Subject: [PATCH 232/253] Removed loop from bootstrap

---
 src/mlpack/methods/random_forest/bootstrap.hpp | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/methods/random_forest/bootstrap.hpp b/src/mlpack/methods/random_forest/bootstrap.hpp
index fa6e5af6be..abbbbbaa05 100644
--- a/src/mlpack/methods/random_forest/bootstrap.hpp
+++ b/src/mlpack/methods/random_forest/bootstrap.hpp
@@ -38,13 +38,10 @@ void Bootstrap(const MatType& dataset,
   // Random sampling with replacement.
   arma::uvec indices = arma::randi<arma::uvec>(dataset.n_cols,
       arma::distr_param(0, dataset.n_cols - 1));
-  for (size_t i = 0; i < dataset.n_cols; ++i)
-  {
-    bootstrapDataset.col(i) = dataset.col(indices[i]);
-    bootstrapLabels[i] = labels[indices[i]];
-    if (UseWeights)
-      bootstrapWeights[i] = weights[indices[i]];
-  }
+  bootstrapDataset = dataset.cols(indices);
+  bootstrapLabels = labels.cols(indices);
+  if (UseWeights)
+    bootstrapWeights = weights.cols(indices);
 }
 
 } // namespace tree

From 3bd4567bdfbbfe5cbb29bcb76d5c1ef88dc13d1a Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 5 Mar 2021 09:29:29 -0500
Subject: [PATCH 233/253] Add functions to access and modify parameters for
 training.

---
 src/mlpack/methods/lars/lars.cpp |  4 ++++
 src/mlpack/methods/lars/lars.hpp | 20 ++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/src/mlpack/methods/lars/lars.cpp b/src/mlpack/methods/lars/lars.cpp
index 03612406fc..16bfa64124 100644
--- a/src/mlpack/methods/lars/lars.cpp
+++ b/src/mlpack/methods/lars/lars.cpp
@@ -178,6 +178,10 @@ double LARS::Train(const arma::mat& matX,
   isIgnored.clear();
   matUtriCholFactor.reset();
 
+  // Update values in case lambda1 or lambda2 changed.
+  lasso = (lambda1 != 0);
+  elasticNet = (lambda1 != 0 && lambda2 != 0);
+
   // This matrix may end up holding the transpose -- if necessary.
   arma::mat dataTrans;
   // dataRef is row-major.
diff --git a/src/mlpack/methods/lars/lars.hpp b/src/mlpack/methods/lars/lars.hpp
index 8989d13e55..d019fec900 100644
--- a/src/mlpack/methods/lars/lars.hpp
+++ b/src/mlpack/methods/lars/lars.hpp
@@ -249,6 +249,26 @@ class LARS
                arma::rowvec& predictions,
                const bool rowMajor = false) const;
 
+  //! Get the L1 regularization coefficient.
+  double Lambda1() const { return lambda1; }
+  //! Modify the L1 regularization coefficient.
+  double& Lambda1() { return lambda1; }
+
+  //! Get the L2 regularization coefficient.
+  double Lambda2() const { return lambda2; }
+  //! Modify the L2 regularization coefficient.
+  double& Lambda2() { return lambda2; }
+
+  //! Get whether to use the Cholesky decomposition.
+  bool UseCholesky() const { return useCholesky; }
+  //! Modify whether to use the Cholesky decomposition.
+  bool& UseCholesky() { return useCholesky; }
+
+  //! Get the tolerance for maximum correlation during training.
+  double Tolerance() const { return tolerance; }
+  //! Modify the tolerance for maximum correlation during training.
+  double& Tolerance() { return tolerance; }
+
   //! Access the set of active dimensions.
   const std::vector<size_t>& ActiveSet() const { return activeSet; }
 

From b11720c4defe4af59764e5c7d0b768208bb910aa Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 5 Mar 2021 09:31:44 -0500
Subject: [PATCH 234/253] Update history.

---
 HISTORY.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/HISTORY.md b/HISTORY.md
index 12692b8308..f0b696d6ac 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -34,6 +34,9 @@
   * `NegativeLogLikelihood<>` now expects classes in the range `0` to
     `numClasses - 1` (#2534).
 
+  * Add `Lambda1()`, `Lambda2()`, `UseCholesky()`, and `Tolerance()` members to
+    `LARS` so parameters for training can be modified (#2861).
+
 ### mlpack 3.4.2
 ###### 2020-10-26
   * Added Mean Absolute Percentage Error.

From 5d078b4e173a818e4393c26a73677fd12a63d288 Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Fri, 5 Mar 2021 18:21:45 -0500
Subject: [PATCH 235/253] Loosen tolerances: AdaBoost does not guarantee better
 performance than a single weak learner.

---
 src/mlpack/tests/adaboost_test.cpp | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/src/mlpack/tests/adaboost_test.cpp b/src/mlpack/tests/adaboost_test.cpp
index cccf6f42d8..6f584a0f04 100644
--- a/src/mlpack/tests/adaboost_test.cpp
+++ b/src/mlpack/tests/adaboost_test.cpp
@@ -67,7 +67,7 @@ TEST_CASE("HammingLossBoundIris", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on the UCI Iris dataset.  It
  * checks if the error returned by running a single instance of the weak learner
- * is worse than running the boosted weak learner using adaboost.
+ * close to that of the boosted weak learner using adaboost.
  */
 TEST_CASE("WeakLearnerErrorIris", "[AdaBoostTest]")
 {
@@ -105,7 +105,7 @@ TEST_CASE("WeakLearnerErrorIris", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);;
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error <= weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**
@@ -151,7 +151,7 @@ TEST_CASE("HammingLossBoundVertebralColumn", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on the UCI Vertebral Column
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using adaboost.
+ * weak learner is close to that of a boosted weak learner using adaboost.
  */
 TEST_CASE("WeakLearnerErrorVertebralColumn", "[AdaBoostTest]")
 {
@@ -187,7 +187,7 @@ TEST_CASE("WeakLearnerErrorVertebralColumn", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error <= weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**
@@ -233,7 +233,7 @@ TEST_CASE("HammingLossBoundNonLinearSepData", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on a non-linearly separable
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using AdaBoost.
+ * weak learner is close to that of a boosted weak learner using AdaBoost.
  */
 TEST_CASE("WeakLearnerErrorNonLinearSepData", "[AdaBoostTest]")
 {
@@ -269,7 +269,7 @@ TEST_CASE("WeakLearnerErrorNonLinearSepData", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error == weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**
@@ -314,7 +314,7 @@ TEST_CASE("HammingLossIris_DS", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on a non-linearly separable
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using adaboost.
+ * weak learner is close to that of a boosted weak learner using adaboost.
  * This is for the weak learner: decision stumps.
  */
 TEST_CASE("WeakLearnerErrorIris_DS", "[AdaBoostTest]")
@@ -355,13 +355,13 @@ TEST_CASE("WeakLearnerErrorIris_DS", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error <= weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**
  * This test case runs the AdaBoost.mh algorithm on the UCI Vertebral Column
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using adaboost.
+ * weak learner is close to that of a boosted weak learner using adaboost.
  * This is for the weak learner: decision stumps.
  */
 TEST_CASE("HammingLossBoundVertebralColumn_DS", "[AdaBoostTest]")
@@ -403,7 +403,7 @@ TEST_CASE("HammingLossBoundVertebralColumn_DS", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on the UCI Vertebral Column
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using adaboost.
+ * weak learner is close to that of a boosted weak learner using adaboost.
  * This is for the weak learner: decision stumps.
  */
 TEST_CASE("WeakLearnerErrorVertebralColumn_DS", "[AdaBoostTest]")
@@ -440,7 +440,7 @@ TEST_CASE("WeakLearnerErrorVertebralColumn_DS", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error <= weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**
@@ -487,7 +487,7 @@ TEST_CASE("HammingLossBoundNonLinearSepData_DS", "[AdaBoostTest]")
 /**
  * This test case runs the AdaBoost.mh algorithm on a non-linearly separable
  * dataset.  It checks if the error returned by running a single instance of the
- * weak learner is worse than running the boosted weak learner using adaboost.
+ * weak learner is close to that of a boosted weak learner using adaboost.
  * This for the weak learner: decision stumps.
  */
 TEST_CASE("WeakLearnerErrorNonLinearSepData_DS", "[AdaBoostTest]")
@@ -526,7 +526,7 @@ TEST_CASE("WeakLearnerErrorNonLinearSepData_DS", "[AdaBoostTest]")
   size_t countError = arma::accu(labels != predictedLabels);
   double error = (double) countError / labels.n_cols;
 
-  REQUIRE(error <= weakLearnerErrorRate);
+  REQUIRE(error <= weakLearnerErrorRate + 0.03);
 }
 
 /**

From 4a4de532dc3a539a075e6d648ce3129b13cc544f Mon Sep 17 00:00:00 2001
From: Ryan Curtin <ryan@ratml.org>
Date: Sat, 6 Mar 2021 17:56:00 -0500
Subject: [PATCH 236/253] Move initialization of static members into a cpp
 file.

---
 .../environment/CMakeLists.txt                |  1 +
 .../environment/env_type.cpp                  | 27 +++++++++++++++++++
 .../environment/env_type.hpp                  |  4 ---
 3 files changed, 28 insertions(+), 4 deletions(-)
 create mode 100644 src/mlpack/methods/reinforcement_learning/environment/env_type.cpp

diff --git a/src/mlpack/methods/reinforcement_learning/environment/CMakeLists.txt b/src/mlpack/methods/reinforcement_learning/environment/CMakeLists.txt
index 04e5b8b2a8..f93995ab75 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/CMakeLists.txt
+++ b/src/mlpack/methods/reinforcement_learning/environment/CMakeLists.txt
@@ -2,6 +2,7 @@
 # Anything not in this list will not be compiled into mlpack.
 set(SOURCES
   env_type.hpp
+  env_type.cpp
   mountain_car.hpp
   cart_pole.hpp
   continuous_mountain_car.hpp
diff --git a/src/mlpack/methods/reinforcement_learning/environment/env_type.cpp b/src/mlpack/methods/reinforcement_learning/environment/env_type.cpp
new file mode 100644
index 0000000000..d5363b5501
--- /dev/null
+++ b/src/mlpack/methods/reinforcement_learning/environment/env_type.cpp
@@ -0,0 +1,27 @@
+/**
+ * @file methods/reinforcement_learning/environment/env_type.cpp
+ * @author Nishant Kumar
+ *
+ * This file defines the static variables used by the discrete and continuous
+ * environments.
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include "env_type.hpp"
+
+namespace mlpack {
+namespace rl {
+
+// Instantiate static members.
+
+size_t DiscreteActionEnv::State::dimension = 0;
+size_t DiscreteActionEnv::Action::size = 0;
+
+size_t ContinuousActionEnv::State::dimension = 0;
+size_t ContinuousActionEnv::Action::size = 0;
+
+} // namespace rl
+} // namespace mlpack
diff --git a/src/mlpack/methods/reinforcement_learning/environment/env_type.hpp b/src/mlpack/methods/reinforcement_learning/environment/env_type.hpp
index e8513e3bb9..4fcf797322 100644
--- a/src/mlpack/methods/reinforcement_learning/environment/env_type.hpp
+++ b/src/mlpack/methods/reinforcement_learning/environment/env_type.hpp
@@ -105,8 +105,6 @@ class DiscreteActionEnv
    */
   bool IsTerminal(const State& /* state */) const { return false; }
 };
-size_t DiscreteActionEnv::State::dimension = 0;
-size_t DiscreteActionEnv::Action::size = 0;
 
 /**
  * To use the dummy environment, one may start by specifying the state and
@@ -201,8 +199,6 @@ class ContinuousActionEnv
    */
   bool IsTerminal(const State& /* state */) const { return false; }
 };
-size_t ContinuousActionEnv::State::dimension = 0;
-size_t ContinuousActionEnv::Action::size = 0;
 
 } // namespace rl
 } // namespace mlpack

From e516f72472bd606fc2b1d46acca1285e60fe5781 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Sun, 7 Mar 2021 18:27:01 +0530
Subject: [PATCH 237/253] Added SplitHelper to remove redundant code

---
 src/mlpack/core/data/split_data.hpp | 256 ++++++++++++----------------
 1 file changed, 105 insertions(+), 151 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 61f9860f54..1fa9bab6db 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -18,6 +18,101 @@
 namespace mlpack {
 namespace data {
 
+template<typename InputType, typename LabelsType>
+void SplitHelper(const InputType& input,
+           const LabelsType& inputLabel,
+           InputType& trainData,
+           InputType& testData,
+           LabelsType& trainLabel,
+           LabelsType& testLabel,
+           const double testRatio,
+           const bool shuffleData = true)
+{
+  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
+  const size_t trainSize = input.n_cols - testSize;
+
+  trainData.set_size(input.n_rows, trainSize);
+  testData.set_size(input.n_rows, testSize);
+  trainLabel.set_size(inputLabel.n_rows, trainSize);
+  testLabel.set_size(inputLabel.n_rows, testSize);
+
+  if (shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+
+    if (trainSize > 0)
+    {
+      for (size_t i = 0; i < trainSize; ++i)
+      {
+        trainData.col(i) = input.col(order(i));
+        trainLabel.col(i) = inputLabel.col(order(i));
+      }
+    }
+    if (trainSize < input.n_cols)
+    {
+      for (size_t i = trainSize; i < input.n_cols; ++i)
+      {
+        testData.col(i - trainSize) = input.col(order(i));
+        testLabel.col(i - trainSize) = inputLabel.col(order(i));
+      }
+    }
+  }
+  else
+  {
+    if (trainSize > 0)
+    {
+      trainData = input.cols(0, trainSize - 1);
+      trainLabel = inputLabel.cols(0, trainSize - 1);
+    }
+
+    if (trainSize < input.n_cols)
+    {
+      testData = input.cols(trainSize, input.n_cols - 1);
+      testLabel = inputLabel.cols(trainSize, inputLabel.n_cols - 1);
+    }
+  }
+}
+
+template<typename InputType>
+void SplitHelper(const InputType& input,
+           InputType& trainData,
+           InputType& testData,
+           const double testRatio,
+           const bool shuffleData = true)
+{
+  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
+  const size_t trainSize = input.n_cols - testSize;
+
+  trainData.set_size(input.n_rows, trainSize);
+  testData.set_size(input.n_rows, testSize);
+
+  if (shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+
+    if (trainSize > 0)
+    {
+      for (size_t i = 0; i < trainSize; ++i)
+        trainData.col(i) = input.col(order(i));
+    }
+    if (trainSize < input.n_cols)
+    {
+      for (size_t i = trainSize; i < input.n_cols; ++i)
+        testData.col(i - trainSize) = input.col(order(i));
+    }
+  }
+  else
+  {
+    if (trainSize > 0)
+      trainData = input.cols(0, trainSize - 1);
+
+    if (trainSize < input.n_cols)
+      testData = input.cols(trainSize, input.n_cols - 1);
+  }
+}
+
 /**
  * Given an input dataset and labels, stratify into a training set and test set.
  * It is recommended to have the input labels between the range [0, n) where n
@@ -92,8 +187,8 @@ void StratifiedSplit(const arma::Mat<T>& input,
 
   trainData.set_size(input.n_rows, trainSize);
   testData.set_size(input.n_rows, testSize);
-  trainLabel.set_size(trainSize);
-  testLabel.set_size(testSize);
+  trainLabel.set_size(inputLabel.n_rows, trainSize);
+  testLabel.set_size(inputLabel.n_rows, testSize);
 
   if (shuffleData)
   {
@@ -184,44 +279,9 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
-  const size_t trainSize = input.n_cols - testSize;
-  trainData.set_size(input.n_rows, trainSize);
-  testData.set_size(input.n_rows, testSize);
-  trainLabel.set_size(1, trainSize);
-  testLabel.set_size(1, testSize);
-
-  if (shuffleData)
-  {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0, input.n_cols - 1,
-        input.n_cols));
-
-    if (trainSize > 0)
-    {
-      trainData = input.cols(order.subvec(0, trainSize - 1));
-      trainLabel = inputLabel.cols(order.subvec(0, trainSize - 1));
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
-      testLabel = inputLabel.cols(order.subvec(trainSize, input.n_cols - 1));
-    }
-  }
-  else
-  {
-    if (trainSize > 0)
-    {
-      trainData = input.cols(0, trainSize - 1);
-      trainLabel = inputLabel.cols(0, trainSize - 1);
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      testData = input.cols(trainSize, input.n_cols - 1);
-      testLabel = inputLabel.cols(trainSize, inputLabel.n_cols - 1);
-    }
-  }
+  SplitHelper(input, inputLabel, trainData,
+              testData, trainLabel, testLabel, testRatio,
+              shuffleData);
 }
 
 /**
@@ -254,30 +314,7 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
-  const size_t trainSize = input.n_cols - testSize;
-  trainData.set_size(input.n_rows, trainSize);
-  testData.set_size(input.n_rows, testSize);
-
-  if (shuffleData)
-  {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(
-        0, input.n_cols - 1, input.n_cols));
-
-    if (trainSize > 0)
-      trainData = input.cols(order.subvec(0, trainSize - 1));
-
-    if (trainSize < input.n_cols)
-      testData = input.cols(order.subvec(trainSize, input.n_cols - 1));
-  }
-  else
-  {
-    if (trainSize > 0)
-      trainData = input.cols(0, trainSize - 1);
-
-    if (trainSize < input.n_cols)
-      testData = input.cols(trainSize , input.n_cols - 1);
-  }
+  SplitHelper(input, trainData, testData, testRatio, shuffleData);
 }
 
 /**
@@ -418,56 +455,9 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
-  const size_t trainSize = input.n_cols - testSize;
-
-  trainData.set_size(1, trainSize);
-  testData.set_size(1, testSize);
-  trainLabel.set_size(trainSize);
-  testLabel.set_size(testSize);
-
-  if (shuffleData)
-  {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
-        input.n_cols - 1, input.n_cols));
-
-    if (trainSize > 0)
-    {
-      for (size_t i = 0; i < trainSize; ++i)
-      {
-        trainData[i] = input(0, order(i));
-        trainLabel[i] = inputLabel(0, order(i));
-      }
-    }
-    if (trainSize < input.n_cols)
-    {
-      for (size_t i = trainSize; i < input.n_cols; ++i)
-      {
-        testData[i - trainSize] = input(0, order(i));
-        testLabel[i - trainSize] = inputLabel(0, order(i));
-      }
-    }
-  }
-  else
-  {
-    if (trainSize > 0)
-    {
-      for (size_t i = 0; i < trainSize; ++i)
-      {
-        trainData[i] = input(0, i);
-        trainLabel[i] = inputLabel(0, i);
-      }
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      for (size_t i = trainSize; i < input.n_cols; ++i)
-      {
-        testData[i - trainSize] = input(0, i);
-        testLabel[i - trainSize] = inputLabel(0, i);
-      }
-    }
-  }
+  SplitHelper(input, inputLabel, trainData,
+              testData, trainLabel, testLabel, testRatio,
+              shuffleData);
 }
 
 /**
@@ -508,43 +498,7 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
-  const size_t trainSize = input.n_cols - testSize;
-
-  trainData.set_size(1, trainSize);
-  testData.set_size(1, testSize);
-
-  if (shuffleData)
-  {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
-        input.n_cols - 1, input.n_cols));
-
-    if (trainSize > 0)
-    {
-      for (size_t i = 0; i < trainSize; i++)
-        trainData[i] = input(0, order(i));
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      for (size_t i = trainSize; i < input.n_cols - 1; ++i)
-         testData[i - trainSize] = input(0, order(i));
-    }
-  }
-  else
-  {
-    if (trainSize > 0)
-    {
-      for (size_t i = 0; i < trainSize; i++)
-        trainData[i] = input(0, i);
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      for (size_t i = trainSize; i < input.n_cols - 1; ++i)
-         testData[i - trainSize] = input(0, i);
-    }
-  }
+  SplitHelper(input, trainData, testData, testRatio, shuffleData);
 }
 
 /**

From 9ae544a31b1d16b535b4ea7067e53cd67e96fbe5 Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Tue, 9 Mar 2021 19:15:32 +0100
Subject: [PATCH 238/253] Clean Coverage, no longer used

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 CMakeLists.txt | 34 ----------------------------------
 1 file changed, 34 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 2ecd13769c..38785e0165 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -80,8 +80,6 @@ option(BUILD_R_BINDINGS "Build R bindings." OFF)
 # generation.
 option(BUILD_MARKDOWN_BINDINGS "Build Markdown bindings for website documentation." OFF)
 
-option(BUILD_WITH_COVERAGE
-    "Build with support for code coverage tools (gcc only)." OFF)
 option(MATHJAX
     "Use MathJax for HTML Doxygen output (disabled by default)." OFF)
 option(FORCE_CXX11
@@ -196,38 +194,6 @@ if(CMAKE_COMPILER_IS_GNUCC)
       ${CMAKE_THREAD_LIBS_INIT})
 endif()
 
-# Setup build for test coverage
-if(BUILD_WITH_COVERAGE)
-  # Currently coverage only works with GNU g++.
-  if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
-    # Find gcov and lcov
-    find_program(GCOV gcov)
-    find_program(LCOV lcov)
-
-    if(NOT GCOV)
-      message(FATAL_ERROR
-          "gcov not found! gcov is required when BUILD_WITH_COVERAGE=ON.")
-    endif()
-
-    set(MLPACK_LIBRARIES ${MLPACK_LIBRARIES} "supc++")
-    set(MLPACK_LIBRARIES ${MLPACK_LIBRARIES} "quadmath")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} --coverage -fno-inline -fno-inline-small-functions -fno-default-inline -fprofile-arcs -fkeep-inline-functions")
-    message(STATUS "Adding debug compile options for code coverage.")
-    # Remove optimizations for better line coverage
-    set(DEBUG ON)
-
-    if(LCOV)
-      configure_file(CMake/mlpack_coverage.in mlpack_coverage @ONLY)
-      add_custom_target(mlpack_coverage DEPENDS mlpack_test COMMAND ${PROJECT_BINARY_DIR}/mlpack_coverage)
-    else()
-      message(WARNING "'lcov' not found; local coverage report is disabled. "
-          "Install 'lcov' and rerun cmake to generate local coverage report.")
-    endif()
-  else()
-    message(FATAL_ERROR "BUILD_WITH_COVERAGE can only work with GNU environment.")
-  endif()
-endif()
-
 # Debugging CFLAGS.  Turn optimizations off; turn debugging symbols on.
 if(DEBUG)
   if (NOT MSVC)

From 9a1a6e983e32a4dec741fd8fa02c6676fcb23249 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Wed, 10 Mar 2021 11:25:35 +0530
Subject: [PATCH 239/253] Update src/mlpack/core/data/split_data.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/data/split_data.hpp | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 1fa9bab6db..67f8491c68 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -20,13 +20,13 @@ namespace data {
 
 template<typename InputType, typename LabelsType>
 void SplitHelper(const InputType& input,
-           const LabelsType& inputLabel,
-           InputType& trainData,
-           InputType& testData,
-           LabelsType& trainLabel,
-           LabelsType& testLabel,
-           const double testRatio,
-           const bool shuffleData = true)
+                const LabelsType& inputLabel,
+                InputType& trainData,
+                InputType& testData,
+                LabelsType& trainLabel,
+                LabelsType& testLabel,
+                const double testRatio,
+                const bool shuffleData = true)
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;

From b39ef0f9a9cd09e94200aaac274300fa7c06a92c Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Wed, 10 Mar 2021 12:25:39 +0530
Subject: [PATCH 240/253] Removed un needed overload of SplitHelper

---
 src/mlpack/core/data/split_data.hpp | 125 ++++++++++++----------------
 1 file changed, 51 insertions(+), 74 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 67f8491c68..1dd1abc62c 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -18,68 +18,12 @@
 namespace mlpack {
 namespace data {
 
-template<typename InputType, typename LabelsType>
-void SplitHelper(const InputType& input,
-                const LabelsType& inputLabel,
-                InputType& trainData,
-                InputType& testData,
-                LabelsType& trainLabel,
-                LabelsType& testLabel,
-                const double testRatio,
-                const bool shuffleData = true)
-{
-  const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
-  const size_t trainSize = input.n_cols - testSize;
-
-  trainData.set_size(input.n_rows, trainSize);
-  testData.set_size(input.n_rows, testSize);
-  trainLabel.set_size(inputLabel.n_rows, trainSize);
-  testLabel.set_size(inputLabel.n_rows, testSize);
-
-  if (shuffleData)
-  {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
-        input.n_cols - 1, input.n_cols));
-
-    if (trainSize > 0)
-    {
-      for (size_t i = 0; i < trainSize; ++i)
-      {
-        trainData.col(i) = input.col(order(i));
-        trainLabel.col(i) = inputLabel.col(order(i));
-      }
-    }
-    if (trainSize < input.n_cols)
-    {
-      for (size_t i = trainSize; i < input.n_cols; ++i)
-      {
-        testData.col(i - trainSize) = input.col(order(i));
-        testLabel.col(i - trainSize) = inputLabel.col(order(i));
-      }
-    }
-  }
-  else
-  {
-    if (trainSize > 0)
-    {
-      trainData = input.cols(0, trainSize - 1);
-      trainLabel = inputLabel.cols(0, trainSize - 1);
-    }
-
-    if (trainSize < input.n_cols)
-    {
-      testData = input.cols(trainSize, input.n_cols - 1);
-      testLabel = inputLabel.cols(trainSize, inputLabel.n_cols - 1);
-    }
-  }
-}
-
 template<typename InputType>
 void SplitHelper(const InputType& input,
-           InputType& trainData,
-           InputType& testData,
-           const double testRatio,
-           const bool shuffleData = true)
+                 InputType& trainData,
+                 InputType& testData,
+                 const double testRatio,
+                 const arma::uvec* order = nullptr)
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
@@ -87,20 +31,17 @@ void SplitHelper(const InputType& input,
   trainData.set_size(input.n_rows, trainSize);
   testData.set_size(input.n_rows, testSize);
 
-  if (shuffleData)
+  if (order)
   {
-    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
-        input.n_cols - 1, input.n_cols));
-
     if (trainSize > 0)
     {
       for (size_t i = 0; i < trainSize; ++i)
-        trainData.col(i) = input.col(order(i));
+        trainData.col(i) = input.col( (*order)(i) );
     }
     if (trainSize < input.n_cols)
     {
       for (size_t i = trainSize; i < input.n_cols; ++i)
-        testData.col(i - trainSize) = input.col(order(i));
+        testData.col(i - trainSize) = input.col( (*order)(i) );
     }
   }
   else
@@ -279,9 +220,18 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  SplitHelper(input, inputLabel, trainData,
-              testData, trainLabel, testLabel, testRatio,
-              shuffleData);
+  if(shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+    SplitHelper(input, trainData, testData, testRatio, &order);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, &order);
+  }
+  else
+  {
+    SplitHelper(input, trainData, testData, testRatio);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio);
+  }
 }
 
 /**
@@ -314,7 +264,16 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  SplitHelper(input, trainData, testData, testRatio, shuffleData);
+  if(shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+    SplitHelper(input, trainData, testData, testRatio, &order);
+  }
+  else
+  {
+    SplitHelper(input, trainData, testData, testRatio);
+  }
 }
 
 /**
@@ -455,9 +414,18 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  SplitHelper(input, inputLabel, trainData,
-              testData, trainLabel, testLabel, testRatio,
-              shuffleData);
+  if(shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+    SplitHelper(input, trainData, testData, testRatio, &order);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, &order);
+  }
+  else
+  {
+    SplitHelper(input, trainData, testData, testRatio);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio);
+  }
 }
 
 /**
@@ -498,7 +466,16 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  SplitHelper(input, trainData, testData, testRatio, shuffleData);
+  if(shuffleData)
+  {
+    arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
+        input.n_cols - 1, input.n_cols));
+    SplitHelper(input, trainData, testData, testRatio, &order);
+  }
+  else
+  {
+    SplitHelper(input, trainData, testData, testRatio);
+  }
 }
 
 /**

From 0557f042bf80ffcac471cbb0f461fb1103ea3db5 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Wed, 10 Mar 2021 12:26:59 +0530
Subject: [PATCH 241/253] Resurrected StratifiedSplit implementation
 explanation

---
 src/mlpack/core/data/split_data.hpp | 33 +++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 1dd1abc62c..7d61e434ec 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -101,6 +101,39 @@ void StratifiedSplit(const arma::Mat<T>& input,
                      const double testRatio,
                      const bool shuffleData = true)
 {
+  /**
+   * Basic idea:
+   * Let us say we have to stratify a dataset based on labels:
+   * 0 0 0 0 0 (5 0s)
+   * 1 1 1 1 1 1 1 1 1 1 1 (11 1s)
+   *
+   * Let our test ratio be 0.2.
+   * Then, the number of 0 labels in our test set = floor(5 * 0.2) = 1.
+   * The number of 1 labels in our test set = floor(11 * 0.2) = 2.
+   *
+   * In our first pass over the dataset,
+   * We visit each label and keep count of each label in our 'labelCounts' uvec.
+   *
+   * We then take a second pass over the dataset.
+   * We now maintain an additional uvec 'testLabelCounts' to hold the label
+   * counts of our test set.
+   *
+   * In this pass, when we encounter a label we check the 'testLabelCounts' uvec
+   * for the count of this label in the test set.
+   * If this count is less than the required number of labels in the test set,
+   * we add the data to the test set and increment the label count in the uvec.
+   * If this count is equal to or more than the required count in the test set,
+   * we add this data to the train set.
+   *
+   * Based on the above steps, we get the following labels in the split set:
+   * Train set (4 0s, 9 1s)
+   * 0 0 0 0
+   * 1 1 1 1 1 1 1 1 1
+   *
+   * Test set (1 0s, 2 1s)
+   * 0
+   * 1 1
+   */
   const bool typeCheck = (arma::is_Row<LabelsType>::value)
       || (arma::is_Col<LabelsType>::value);
   if (!typeCheck)

From 1117300efb742cc1fe0cb53aba3d2ba5b1b2c8bb Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Wed, 10 Mar 2021 12:40:09 +0530
Subject: [PATCH 242/253] Added documentation

---
 src/mlpack/core/data/split_data.hpp | 32 ++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 7d61e434ec..a97058d29b 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -18,39 +18,47 @@
 namespace mlpack {
 namespace data {
 
+/**
+ * This helper function splits any `input` data into training and testing parts.
+ * In order to shuffle the input data before spliting, an array of shuffled
+ * indices of the input data is passed in the form of argument `order`.
+ */
 template<typename InputType>
 void SplitHelper(const InputType& input,
-                 InputType& trainData,
-                 InputType& testData,
+                 InputType& train,
+                 InputType& test,
                  const double testRatio,
                  const arma::uvec* order = nullptr)
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
 
-  trainData.set_size(input.n_rows, trainSize);
-  testData.set_size(input.n_rows, testSize);
+  // Initialising the sizes of outputs if not already initialized.
+  train.set_size(input.n_rows, trainSize);
+  test.set_size(input.n_rows, testSize);
 
+  // Shuffling and spliting simultaneously.
   if (order)
   {
     if (trainSize > 0)
     {
       for (size_t i = 0; i < trainSize; ++i)
-        trainData.col(i) = input.col( (*order)(i) );
+        train.col(i) = input.col( (*order)(i) );
     }
     if (trainSize < input.n_cols)
     {
       for (size_t i = trainSize; i < input.n_cols; ++i)
-        testData.col(i - trainSize) = input.col( (*order)(i) );
+        test.col(i - trainSize) = input.col( (*order)(i) );
     }
   }
+  // Spliting only.
   else
   {
     if (trainSize > 0)
-      trainData = input.cols(0, trainSize - 1);
+      train = input.cols(0, trainSize - 1);
 
     if (trainSize < input.n_cols)
-      testData = input.cols(trainSize, input.n_cols - 1);
+      test = input.cols(trainSize, input.n_cols - 1);
   }
 }
 
@@ -253,7 +261,7 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  if(shuffleData)
+  if (shuffleData)
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
@@ -297,7 +305,7 @@ void Split(const arma::Mat<T>& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  if(shuffleData)
+  if (shuffleData)
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
@@ -447,7 +455,7 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  if(shuffleData)
+  if (shuffleData)
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
@@ -499,7 +507,7 @@ void Split(const FieldType& input,
            const double testRatio,
            const bool shuffleData = true)
 {
-  if(shuffleData)
+  if (shuffleData)
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));

From 43760f7aa36163d11d90a623b61cd0a244de6f3c Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Wed, 10 Mar 2021 11:43:45 +0100
Subject: [PATCH 243/253] Remove the coverage badge

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 README.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/README.md b/README.md
index bb8ba1be6c..84eb8260b4 100644
--- a/README.md
+++ b/README.md
@@ -15,7 +15,6 @@ src="https://cdn.rawgit.com/mlpack/mlpack.org/e7d36ed8/mlpack-black.svg" style="
 
 <p align="center">
   <a href="http://ci.mlpack.org/job/mlpack%20-%20git%20commit%20test/"><img src="https://img.shields.io/jenkins/build.svg?jobUrl=http%3A%2F%2Fci.mlpack.org%2Fjob%2Fmlpack%2520-%2520git%2520commit%2520test%2F&label=Linux%20build&style=flat-square" alt="Jenkins"></a>
-  <a href="https://coveralls.io/github/mlpack/mlpack?branch=master"><img src="https://img.shields.io/coveralls/mlpack/mlpack/master.svg?style=flat-square" alt="Coveralls"></a>
   <a href="https://opensource.org/licenses/BSD-3-Clause"><img src="https://img.shields.io/badge/License-BSD%203--Clause-blue.svg?style=flat-square" alt="License"></a>
   <a href="http://numfocus.org/donate-to-mlpack"><img src="https://img.shields.io/badge/sponsored%20by-NumFOCUS-orange.svg?style=flat-square&colorA=E1523D&colorB=007D8A" alt="NumFOCUS"></a>
 </p>

From bd8a5e44c08b6a7b68e79ab8d1155946ab69abfd Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Wed, 10 Mar 2021 22:35:39 +0100
Subject: [PATCH 244/253] Remove appveyor, no longer used

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 .appveyor.yml | 219 --------------------------------------------------
 1 file changed, 219 deletions(-)
 delete mode 100644 .appveyor.yml

diff --git a/.appveyor.yml b/.appveyor.yml
deleted file mode 100644
index 722a597468..0000000000
--- a/.appveyor.yml
+++ /dev/null
@@ -1,219 +0,0 @@
-clone_depth: 10
-
-environment:
-  BOOST_MATH : "C:/projects/mlpack/\
-  boost_math_c99-vc140.1.60.0.0/lib/native/address-model-64/lib/*.*"
-  BOOST_RANDOM : "C:/projects/mlpack/\
-  boost_random-vc140.1.60.0.0/lib/native/address-model-64/lib/*.*"
-  ARMADILLO_DOWNLOAD : "https://data.kurg.org/armadillo-8.400.0.tar.xz"
-  ARMADILLO_LIBRARY : "C:/projects/mlpack/armadillo-8.400.0/\
-  build/Debug/armadillo.lib"
-  BLAS_LIBRARY : "%APPVEYOR_BUILD_FOLDER%/OpenBLAS.0.2.14.1/lib/native/lib/x64/\
-  libopenblas.dll.a"
-  BOOST_INCLUDE : "C:/projects/mlpack/boost.1.60.0.0/lib/native/include"
-  JENKINS_DOC_DOWNLOAD : "http://ci.mlpack.org/job/mlpack%20-%20doxygen%20\
-  build/lastSuccessfulBuild/artifact/build/doc/html/*zip*/html.zip"
-  JENKINS_DOC : "C:/projects/mlpack/dist/win-installer/jenkinsdoc.zip"
-  GIT_VERSION_FILE : "C:/projects/mlpack/src/mlpack/core/util/gitversion.hpp"
-  matrix:
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2019
-      VSVER: Visual Studio 16 2019
-      MSBUILD: C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\MSBuild\Current\Bin\MSBuild.exe
-
-# We have removed the VS studio 15 2017 build since it is not possible to complete
-# or finish the build due to the `compiler out of heap space issues`.
-# Therefore, in the meanwhile, we are only doing the installation for VS 16 2019.
-
-configuration: Release
-
-os: Visual Studio 2019
-
-install:
-  - ps: nuget install boost -o "${env:APPVEYOR_BUILD_FOLDER}" -Version 1.60.0
-  - ps: >
-      nuget install boost_random-vc140
-      -o "${env:APPVEYOR_BUILD_FOLDER}" -Version 1.60.0
-  - ps: >
-      nuget install boost_math_c99-vc140
-      -o "${env:APPVEYOR_BUILD_FOLDER}" -Version 1.60.0
-  - ps: >
-      nuget install unofficial-flayan-cereal
-      -o "${env:APPVEYOR_BUILD_FOLDER}"
-  - ps: nuget install OpenBLAS -o "${env:APPVEYOR_BUILD_FOLDER}"
-  - set path=C:\Program Files (x86)\WiX Toolset v3.11\bin;%path%
-
-build_script:
-  - mkdir boost_libs
-  - ps: cp ${env:BOOST_MATH} C:\projects\mlpack\boost_libs\
-  - ps: cp ${env:BOOST_RANDOM} C:\projects\mlpack\boost_libs\
-  - echo TEST_ARMA is %ARMADILLO_DOWNLOAD%
-  - >
-    appveyor DownloadFile %ARMADILLO_DOWNLOAD%
-    -FileName armadillo.tar.xz
-  - 7z x armadillo.tar.xz -so -txz | 7z x -si -ttar > nul
-  - cd armadillo-8.400.0 && mkdir build && cd build
-  - >
-    cmake -G "%VSVER%"
-    -DBLAS_LIBRARY:FILEPATH=%BLAS_LIBRARY%
-    -DLAPACK_LIBRARY:FILEPATH=%BLAS_LIBRARY%
-    -DCMAKE_PREFIX:FILEPATH="%APPVEYOR_BUILD_FOLDER%/armadillo"
-    -DBUILD_SHARED_LIBS=OFF
-    -DCMAKE_BUILD_TYPE=Release ..
-  - >
-    "%MSBUILD%" "C:\projects\mlpack\armadillo-8.400.0\build\armadillo.sln"
-    /m /verbosity:quiet /p:Configuration=Release;Platform=x64
-  - cd C:\projects\mlpack && mkdir build && cd build
-  - >
-    cmake -G "%VSVER%"
-    -DBLAS_LIBRARIES:FILEPATH=%BLAS_LIBRARY%
-    -DLAPACK_LIBRARIES:FILEPATH=%BLAS_LIBRARY%
-    -DARMADILLO_INCLUDE_DIR="C:/projects/mlpack/armadillo-8.400.0/include"
-    -DARMADILLO_LIBRARY:FILEPATH=%ARMADILLO_LIBRARY%
-    -DCEREAL_INCLUDE_DIR="C:/projects/mlpack/unofficial-flayan-cereal.1.2.2/build/native/include"
-    -DBOOST_INCLUDEDIR:PATH=%BOOST_INCLUDE%
-    -DDEBUG=OFF
-    -DPROFILE=OFF
-    -DBUILD_PYTHON_BINDINGS=OFF
-    -DBUILD_GO_BINDINGS=OFF
-    -DBUILD_R_BINDINGS=OFF
-    -DBUILD_TESTS=OFF
-    -DCMAKE_BUILD_TYPE=Release ..
-  - >
-    "%MSBUILD%" "C:\projects\mlpack\build\mlpack.sln"
-    /m /verbosity:minimal /nologo /p:BuildInParallel=true
-    /p:Configuration=Release;Platform=x64
-
-  # Zip Artifacts.
-  - >
-    7z a mlpack-windows-no-libs.zip
-    "%APPVEYOR_BUILD_FOLDER%\build\Release\*.exe"
-  - >
-    7z a mlpack-windows.zip
-    "%APPVEYOR_BUILD_FOLDER%\build\Release\*.*"
-    "%APPVEYOR_BUILD_FOLDER%/OpenBLAS.0.2.14.1/lib/native/lib/x64/*.*"
-
-  # Pulling documentation for the installer.
-  - ps: >
-      try{(new-object net.webclient).DownloadFile(${env:JENKINS_DOC_DOWNLOAD},
-      'C:\projects\mlpack\dist\win-installer\jenkinsdoc.zip')}
-      catch{Write-Output "Unable to pull jenkins doc, skipping!"}
-  - ps: >
-      try{(Add-Type -AssemblyName System.IO.Compression.FileSystem);
-      [System.IO.Compression.ZipFile]::ExtractToDirectory(${env:JENKINS_DOC},
-      'C:\projects\mlpack\dist\win-installer\staging\doc')}
-      catch{Write-Output "Unable to add doc to installer, skipping!"}
-
-  # Preparing installer staging.
-  - cd C:\projects\mlpack\dist\win-installer\staging && mkdir lib
-  - ps: >
-      cp C:\projects\mlpack\build\Release\*.lib
-      C:\projects\mlpack\dist\win-installer\staging\lib\
-  - ps: >
-      cp C:\projects\mlpack\build\Release\*.exp
-      C:\projects\mlpack\dist\win-installer\staging\lib\
-  - ps: >
-      cp C:\projects\mlpack\build\Release\*.dll
-      C:\projects\mlpack\dist\win-installer\staging\
-  - ps: >
-      cp C:\projects\mlpack\build\Release\*.exe
-      C:\projects\mlpack\dist\win-installer\staging\
-  - ps: >
-      cp C:\projects\mlpack\OpenBLAS.0.2.14.1\lib\native\bin\x64\*.dll
-      C:\projects\mlpack\dist\win-installer\staging\
-  - ps: >
-      cp C:\projects\mlpack\build\include\mlpack
-      C:\projects\mlpack\dist\win-installer\staging -recurse
-  - ps: >
-      cp C:\projects\mlpack\doc\examples
-      C:\projects\mlpack\dist\win-installer\staging -recurse
-  - ps: >
-      cp C:\projects\mlpack\src\mlpack\tests\data\german.csv
-      C:\projects\mlpack\dist\win-installer\staging\examples\sample-ml-app\sample-ml-app\data\
-
-  # Checking current gitversion or mlpack version.
-  - ps: >
-      $ver = (Get-Content
-      "${env:APPVEYOR_BUILD_FOLDER}\src\mlpack\core\util\version.hpp" |
-      where {$_ -like "*MLPACK_VERSION*"});
-      $env:MLPACK_VERSION += $ver[0].substring($ver[0].length - 1, 1) + '.';
-      $env:MLPACK_VERSION += $ver[1].substring($ver[1].length - 1, 1) + '.';
-      $env:MLPACK_VERSION += $ver[2].substring($ver[2].length - 1, 1);
-
-      if (Test-Path ${env:GIT_VERSION_FILE})
-      {
-        $ver = (Get-Content ${env:GIT_VERSION_FILE});
-        $env:INSTALL_VERSION = $ver.Split('"')[1].Split(' ')[1];
-      }
-      else
-      {
-        $env:INSTALL_VERSION = $env:MLPACK_VERSION;
-      }
-  - echo INSTALL_VERSION is %INSTALL_VERSION%
-
-  # Building MSI installer.
-  - cd C:\projects\mlpack\dist\win-installer\mlpack-win-installer
-  - >
-    heat dir ..\staging
-    -cg HeatGenerated
-    -dr INSTALLFOLDER
-    -sreg
-    -srd
-    -var var.HarvestPath
-    -ag
-    -sfrag
-    -out HeatGeneratedFileList.wxs
-  - >
-    candle -dHarvestPath=..\staging
-    -dConfiguration=Release
-    -dOutDir=bin\x64\Release\
-    -dPlatform=x64
-    -dProjectDir=.
-    -dProjectExt=.wixproj
-    -dProjectFileName=mlpack-win-installer.wixproj
-    -dProjectName=mlpack-win-installer
-    -dProjectPath=mlpack-win-installer.wixproj
-    -dTargetDir=.\bin\x64\Release\
-    -dTargetExt=.msi
-    -dTargetFileName=mlpack-windows.msi
-    -dTargetName=mlpack-windows
-    -dTargetPath=.\bin\x64\Release\mlpack-windows.msi
-    -out obj\x64\Release\
-    -arch x64
-    -ext "C:\Program Files (x86)\WiX Toolset v3.11\bin\\WixUIExtension.dll"
-    Product.wxs HeatGeneratedFileList.wxs
-  - >
-    light -out .\bin\x64\Release\mlpack-%INSTALL_VERSION%.msi
-    -pdbout .\bin\x64\Release\mlpack-windows.wixpdb
-    -cultures:null
-    -loc mlpack-localization.wxl
-    -ext "C:\Program Files (x86)\WiX Toolset v3.11\bin\\WixUIExtension.dll"
-    -contentsfile
-    obj\x64\Release\mlpack-win-installer.wixproj.BindContentsFileListnull.txt
-    -outputsfile
-    obj\x64\Release\mlpack-win-installer.wixproj.BindOutputsFileListnull.txt
-    -builtoutputsfile
-    obj\x64\Release\mlpack-win-installer.wixproj.BindBuiltOutputsFileListnull.txt
-    -wixprojectfile
-    mlpack-win-installer.wixproj
-    obj\x64\Release\Product.wixobj
-    obj\x64\Release\HeatGeneratedFileList.wixobj
-
-artifacts:
-  - path: 'build\*.zip'
-    name: mlpack-windows-zip
-
-  - path: 'dist\win-installer\mlpack-win-installer\bin\x64\Release\*.msi'
-    name: mlpack-windows-installer
-
-notifications:
-- provider: Email
-  to:
-  - mlpack-git@lists.mlpack.org
-  on_build_success: true
-  on_build_failure: true
-  on_build_status_changed: true
-
-cache:
-  - packages -> **\packages.config
-  - armadillo.tar.xz -> appveyor.yaml
-

From d384a83c3dbc6448320ba4ef5aa07d90ca356d67 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Thu, 11 Mar 2021 07:31:15 +0530
Subject: [PATCH 245/253] Update src/mlpack/tests/split_data_test.cpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/tests/split_data_test.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 8d2b5e470e..075347bd3a 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -388,7 +388,7 @@ TEST_CASE("SplitMatrixLabeledData", "[SplitDataTest]")
   CheckMatrices(labels, labels_concat);
 }
 
-/*
+/**
  * Split with input of type field<mat> and label of type field<vec>.
  */
 TEST_CASE("SplitLabeledDataResultField", "[SplitDataTest]")

From 9339e42c1f51e3502a45c58b840890ab335c82a8 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Thu, 11 Mar 2021 07:31:33 +0530
Subject: [PATCH 246/253] Update src/mlpack/tests/test_catch_tools.hpp

Co-authored-by: Marcus Edel <marcus.edel@fu-berlin.de>
---
 src/mlpack/tests/test_catch_tools.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/tests/test_catch_tools.hpp b/src/mlpack/tests/test_catch_tools.hpp
index dfd0577b19..879cac8b49 100644
--- a/src/mlpack/tests/test_catch_tools.hpp
+++ b/src/mlpack/tests/test_catch_tools.hpp
@@ -53,7 +53,7 @@ inline void CheckMatrices(const arma::Mat<size_t>& a,
 template <typename FieldType,
           typename = std::enable_if_t<
               arma::is_arma_type<typename FieldType::object_type>::value>>
-// Check the values of two field types
+// Check the values of two field types.
 inline void CheckFields(const FieldType& a,
                         const FieldType& b)
 {

From 3c67db795d83c59f80634af2549ff66dd0e07546 Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Fri, 12 Mar 2021 10:28:41 +0100
Subject: [PATCH 247/253] Remove doc and config related to coverage

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 CMake/mlpack_coverage.in | 135 ---------------------------------------
 doc/guide/build.hpp      |   2 -
 2 files changed, 137 deletions(-)
 delete mode 100755 CMake/mlpack_coverage.in

diff --git a/CMake/mlpack_coverage.in b/CMake/mlpack_coverage.in
deleted file mode 100755
index b67ecf3cc1..0000000000
--- a/CMake/mlpack_coverage.in
+++ /dev/null
@@ -1,135 +0,0 @@
-#!/bin/bash
-# This script gets the test coverage for mlpack_test.
-test_case="ALL"
-gcov_loc=""
-token=""
-clean=true
-current_log_file=`date +'%Y.%h.%d:%H:%M:%S-coverage.log'`
-current_coverage_file=`date +'%Y.%h.%d:%H:%M:%S-coverage.info'`
-max_cov_count=50000
-
-# default directories
-root_dir="../"
-
-# Extract arguments.
-for i in "$@"
-do
-case $i in
-    -h|--help)
-    echo "Usage: mlpack_coverage --help|-h"
-    echo "       mlpack_coverage [-r=test_suite] [-g=gcov_tool_location]"
-    echo "                       [--token=coveralls_token]"
-    echo "Optional parameters:"
-    echo "    -n|--no_test               Do not run test before coverage computation"
-    echo "    -r|--run_test              Run tests with specific test suite"
-    echo "       --no_clean              Do not remove existing gcda file"
-    echo "    -g|--gcov_tool_location    Gcov location if not default"
-    echo "    -t|--token                 Upload to coveralls with given token"
-    echo "       --max_cov_count         Max line coverage count (default 50000)"
-    echo "       --root_dir              Set the root directory from which gcov will be called. (default ../)"
-    exit 0
-    shift
-    ;;
-    -n|--no_test)
-    test_case=""
-    shift
-    ;;
-    -r=*|--run_test=*)
-    test_case="${i#*=}"
-    shift # past argument=value
-    ;;
-    --no_clean)
-    clean=false
-    shift
-    ;;
-    -g=*|--gcov_tool_location=*)
-    gcov_loc="${i#*=}"
-    shift # past argument=value
-    ;;
-    -t=*|--token=*)
-    token="${i#*=}"
-    shift # past argument=value
-    ;;
-    --max_cov_count)
-    max_cov_count="${i#*=}"
-    shift
-    ;;
-    --root_dir=*)
-    root_dir="${i#*=}"
-    shift
-    ;;
-    *)
-            # unknown option
-    ;;
-esac
-done
-
-if [ "$clean" = true ]; then
-  echo "Deleting existing coverage data..."
-  find ./ -name "*.gcda" -type f -delete
-fi
-
-# Initial pass.
-echo "Generating primary coverage report."
-[[ -d ./coveragehistory/ ]] || mkdir coveragehistory
-lcov -b . -c -i -d ./ -o .coverage.wtest.base > ./coveragehistory/$current_log_file
-
-# Run the tests.
-if [ "$test_case" = "ALL" ]; then
-  echo "Running all the tests..."
-  "@CMAKE_BINARY_DIR@"/bin/mlpack_test
-elif ! [ "$test_case" = "" ]; then
-  echo "Running test suite: $test_case"
-  "@CMAKE_BINARY_DIR@"/bin/mlpack_test --run_test=$test_case
-fi
-
-# Generate coverage based on executed tests.
-echo "Computing coverage..."
-if [ "$gcov_loc" = "" ];
-then lcov -b . -c -d ./ -o .coverage.wtest.run >> ./coveragehistory/$current_log_file
-else
-  lcov -b . -c -d ./ -o .coverage.wtest.run --gcov-tool=$gcov_loc >> ./coveragehistory/$current_log_file
-fi
-
-echo "Filtering coverage files..."
-# Clear negative entries in coverage file
-sed -E 's/-([0-9]+)/$max_cov_count/g' -i .coverage.wtest.run
-# Merge coverage tracefiles.
-lcov -a .coverage.wtest.base -a .coverage.wtest.run  -o .coverage.total >> ./coveragehistory/$current_log_file
-
-# Filtering, extracting project files.
-lcov -e .coverage.total "@CMAKE_CURRENT_SOURCE_DIR@/src/mlpack/*" -o .coverage.total.filtered >> ./coveragehistory/$current_log_file
-
-# Filtering, removing test-files and main.cpp.
-lcov -r .coverage.total.filtered "@CMAKE_CURRENT_SOURCE_DIR@/src/mlpack/*/*_main.cpp" -o .coverage.total.filtered >> ./coveragehistory/$current_log_file
-lcov -r .coverage.total.filtered "@CMAKE_CURRENT_SOURCE_DIR@/src/mlpack/tests/*" -o .coverage.total.filtered >> ./coveragehistory/$current_log_file
-
-# Remove untestable files.
-lcov -r .coverage.total.filtered "@CMAKE_CURRENT_SOURCE_DIR@/src/mlpack/core/util/gitversion.hpp" -o .coverage.total.filtered >> ./coveragehistory/$current_log_file
-lcov -r .coverage.total.filtered "@CMAKE_CURRENT_SOURCE_DIR@/src/mlpack/core/util/arma_config.hpp" -o .coverage.total.filtered >> ./coveragehistory/$current_log_file
-
-# Extra:  Replace /build/ with /src/ to unify directories.
-cat .coverage.total.filtered > .coverage.total
-
-# Extra: Clear up previous data, create html folder.
-if [[ -d ./coverage/ ]] ; then
-    rm -rf ./coverage/*
-else
-    mkdir coverage
-fi
-
-# Step 9: Generate webpage.
-genhtml -o ./coverage/ .coverage.total
-
-# Extra: Preserve coverage file in coveragehistory folder.
-coverage_file=$current_coverage_file
-cp .coverage.total ./coveragehistory/$current_coverage_file
-
-# Clean temporary coverage files.
-#rm .coverage.*
-
-# Upload the result to coveralls if token is provided.
-if ! [ "$token" = "" ]; then
-  cpp-coveralls -n -r $root_dir -b $root_dir -l ./coveragehistory/$current_coverage_file -t "$token" --max-cov-count $max_cov_count
-fi
-
diff --git a/doc/guide/build.hpp b/doc/guide/build.hpp
index 9996f5132d..9356f725cc 100644
--- a/doc/guide/build.hpp
+++ b/doc/guide/build.hpp
@@ -191,8 +191,6 @@ The full list of options mlpack allows:
  - DOWNLOAD_ENSMALLEN=(ON/OFF): If ensmallen is not found, download it
        (default ON)
  - DOWNLOAD_STB_IMAGE=(ON/OFF): If STB is not found, download it (default ON)
- - BUILD_WITH_COVERAGE=(ON/OFF): Build with support for code coverage tools
-      (gcc only) (default OFF)
  - PYTHON_EXECUTABLE=(/path/to/python_version): Path to specific Python executable
  - PYTHON_INSTALL_PREFIX=(/path/to/python/): Path to root of Python installation
  - JULIA_EXECUTABLE=(/path/to/julia): Path to specific Julia executable

From a41fc26651c2696ca75758ff186dc58ab006cff2 Mon Sep 17 00:00:00 2001
From: Omar Shrit <omar@shrit.me>
Date: Fri, 12 Mar 2021 11:13:32 +0100
Subject: [PATCH 248/253] Remove addition t from the word test

I do think this is a typo, unless if this is intended

Signed-off-by: Omar Shrit <omar@shrit.me>
---
 src/mlpack/tests/tree_traits_test.cpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/mlpack/tests/tree_traits_test.cpp b/src/mlpack/tests/tree_traits_test.cpp
index caa642c71f..e7c95d1cd4 100644
--- a/src/mlpack/tests/tree_traits_test.cpp
+++ b/src/mlpack/tests/tree_traits_test.cpp
@@ -31,7 +31,7 @@ using namespace mlpack::metric;
 // weird things and will cause bizarre problems.
 
 // Test the defaults.
-TEST_CASE("DefaultsTraitsTest", "[TreeTraitsTestt]")
+TEST_CASE("DefaultsTraitsTest", "[TreeTraitsTest]")
 {
   // An irrelevant non-tree type class is used here so that the default
   // implementation of TreeTraits is chosen.
@@ -48,7 +48,7 @@ TEST_CASE("DefaultsTraitsTest", "[TreeTraitsTestt]")
 }
 
 // Test the binary space tree traits.
-TEST_CASE("BinarySpaceTreeTraitsTest", "[TreeTraitsTestt]")
+TEST_CASE("BinarySpaceTreeTraitsTest", "[TreeTraitsTest]")
 {
   typedef BinarySpaceTree<LMetric<2, false>> TreeType;
 
@@ -74,7 +74,7 @@ TEST_CASE("BinarySpaceTreeTraitsTest", "[TreeTraitsTestt]")
 }
 
 // Test the cover tree traits.
-TEST_CASE("CoverTreeTraitsTest", "[TreeTraitsTestt]")
+TEST_CASE("CoverTreeTraitsTest", "[TreeTraitsTest]")
 {
   // Children may be overlapping.
   bool b = TreeTraits<CoverTree<>>::HasOverlappingChildren;

From 10ea5a0706c6ddae4f55f30f7d93c216fe279f01 Mon Sep 17 00:00:00 2001
From: Nippun Sharma <53967069+NippunSharma@users.noreply.github.com>
Date: Fri, 12 Mar 2021 19:40:24 +0530
Subject: [PATCH 249/253] remove_matlab_1

---
 CMakeLists.txt | 1 -
 1 file changed, 1 deletion(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 2ecd13769c..1a6e1e5bd8 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -9,7 +9,6 @@ include(CMake/CheckHash.cmake)
 option(DEBUG "Compile with debugging information." OFF)
 option(PROFILE "Compile with profiling information." OFF)
 option(ARMA_EXTRA_DEBUG "Compile with extra Armadillo debugging symbols." OFF)
-option(MATLAB_BINDINGS "Compile MATLAB bindings if MATLAB is found." OFF)
 option(TEST_VERBOSE "Run test cases with verbose output." OFF)
 option(BUILD_TESTS "Build tests." ON)
 option(BUILD_CLI_EXECUTABLES "Build command-line executables." ON)

From 14996379dbb4150d6e61824c03ce5f22865a109a Mon Sep 17 00:00:00 2001
From: NippunSharma <nippun.expert@gmail.com>
Date: Fri, 12 Mar 2021 19:49:53 +0530
Subject: [PATCH 250/253] removed_matlab_2

---
 CMake/FindMatlabMex.cmake | 110 --------------------------------------
 1 file changed, 110 deletions(-)
 delete mode 100644 CMake/FindMatlabMex.cmake

diff --git a/CMake/FindMatlabMex.cmake b/CMake/FindMatlabMex.cmake
deleted file mode 100644
index 43b342c4a5..0000000000
--- a/CMake/FindMatlabMex.cmake
+++ /dev/null
@@ -1,110 +0,0 @@
-# This module looks for mex, the MATLAB compiler.
-# The following variables are defined when the script completes:
-#   MATLAB_MEX: location of mex compiler
-#   MATLAB_ROOT: root of MATLAB installation
-#   MATLABMEX_FOUND: 0 if not found, 1 if found
-
-set(MATLABMEX_FOUND 0)
-
-if(WIN32)
-  # This is untested but taken from the older FindMatlab.cmake script as well as
-  # the modifications by Ramon Casero and Tom Doel for Gerardus.
-
-  # Search for a version of Matlab available, starting from the most modern one
-  # to older versions.
-  foreach(MATVER "7.20" "7.19" "7.18" "7.17" "7.16" "7.15" "7.14" "7.13" "7.12"
-"7.11" "7.10" "7.9" "7.8" "7.7" "7.6" "7.5" "7.4")
-    if((NOT DEFINED MATLAB_ROOT)
-        OR ("${MATLAB_ROOT}" STREQUAL "")
-        OR ("${MATLAB_ROOT}" STREQUAL "/registry"))
-      get_filename_component(MATLAB_ROOT
-        "[HKEY_LOCAL_MACHINE\\SOFTWARE\\MathWorks\\MATLAB\\${MATVER};MATLABROOT]"
-        ABSOLUTE)
-      set(MATLAB_VERSION ${MATVER})
-    endif()
-      OR ("${MATLAB_ROOT}" STREQUAL "")
-      OR ("${MATLAB_ROOT}" STREQUAL "/registry"))
-  endforeach()
-
-  find_program(MATLAB_MEX
-    mex
-    ${MATLAB_ROOT}/bin
-    )
-else()
-  # Check if this is a Mac.
-  if(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
-    # This code is untested but taken from the older FindMatlab.cmake script as
-    # well as the modifications by Ramon Casero and Tom Doel for Gerardus.
-
-   set(LIBRARY_EXTENSION .dylib)
-
-    # If this is a Mac and the attempts to find MATLAB_ROOT have so far failed,~
-    # we look in the applications folder
-    if((NOT DEFINED MATLAB_ROOT) OR ("${MATLAB_ROOT}" STREQUAL ""))
-
-    # Search for a version of Matlab available, starting from the most modern
-    # one to older versions
-      foreach(MATVER "R2013b" "R2013a" "R2012b" "R2012a" "R2011b" "R2011a"
-"R2010b" "R2010a" "R2009b" "R2009a" "R2008b")
-        if((NOT DEFINED MATLAB_ROOT) OR ("${MATLAB_ROOT}" STREQUAL ""))
-          if(EXISTS /Applications/MATLAB_${MATVER}.app)
-            set(MATLAB_ROOT /Applications/MATLAB_${MATVER}.app)
-
-          endif()
-        endif()
-      endforeach()
-
-    endif()
-
-    find_program(MATLAB_MEX
-      mex
-      PATHS
-      ${MATLAB_ROOT}/bin
-    )
-
-  else()
-    # On a Linux system.  The goal is to find MATLAB_ROOT.
-    set(LIBRARY_EXTENSION .so)
-
-    find_program(MATLAB_MEX_POSSIBLE_LINK
-      mex
-      PATHS
-      ${MATLAB_ROOT}/bin
-      /opt/matlab/bin
-      /usr/local/matlab/bin
-      $ENV{HOME}/matlab/bin
-      # Now all the versions
-      /opt/matlab/[rR]20[0-9][0-9][abAB]/bin
-      /usr/local/matlab/[rR]20[0-9][0-9][abAB]/bin
-      /opt/matlab-[rR]20[0-9][0-9][abAB]/bin
-      /opt/matlab_[rR]20[0-9][0-9][abAB]/bin
-      /usr/local/matlab-[rR]20[0-9][0-9][abAB]/bin
-      /usr/local/matlab_[rR]20[0-9][0-9][abAB]/bin
-      $ENV{HOME}/matlab/[rR]20[0-9][0-9][abAB]/bin
-      $ENV{HOME}/matlab-[rR]20[0-9][0-9][abAB]/bin
-      $ENV{HOME}/matlab_[rR]20[0-9][0-9][abAB]/bin
-    )
-
-    get_filename_component(MATLAB_MEX "${MATLAB_MEX_POSSIBLE_LINK}" REALPATH)
-    get_filename_component(MATLAB_BIN_ROOT "${MATLAB_MEX}" PATH)
-    # Strip ./bin/.
-    get_filename_component(MATLAB_ROOT "${MATLAB_BIN_ROOT}" PATH)
-  endif()
-endif()
-
-if(NOT EXISTS "${MATLAB_MEX}" AND "${MatlabMex_FIND_REQUIRED}")
-  message(FATAL_ERROR "Could not find MATLAB mex compiler; try specifying MATLAB_ROOT.")
-else()
-  if(EXISTS "${MATLAB_MEX}")
-    message(STATUS "Found MATLAB mex compiler: ${MATLAB_MEX}")
-    message(STATUS "MATLAB root: ${MATLAB_ROOT}")
-    set(MATLABMEX_FOUND 1)
-  endif()
-endif()
-
-mark_as_advanced(
-  MATLAB_MEX
-  MATLABMEX_FOUND
-  MATLAB_ROOT
-)
-

From 3801b16e13d1f8a503e2f618a9d0f317142e4e1f Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Fri, 12 Mar 2021 22:19:43 +0530
Subject: [PATCH 251/253] Removed pointer from default function argument

---
 src/mlpack/core/data/split_data.hpp | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index a97058d29b..12f3b0efec 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -28,7 +28,7 @@ void SplitHelper(const InputType& input,
                  InputType& train,
                  InputType& test,
                  const double testRatio,
-                 const arma::uvec* order = nullptr)
+                 const arma::uvec& order = arma::uvec())
 {
   const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
   const size_t trainSize = input.n_cols - testSize;
@@ -38,17 +38,17 @@ void SplitHelper(const InputType& input,
   test.set_size(input.n_rows, testSize);
 
   // Shuffling and spliting simultaneously.
-  if (order)
+  if (!order.is_empty())
   {
     if (trainSize > 0)
     {
       for (size_t i = 0; i < trainSize; ++i)
-        train.col(i) = input.col( (*order)(i) );
+        train.col(i) = input.col(order(i));
     }
     if (trainSize < input.n_cols)
     {
       for (size_t i = trainSize; i < input.n_cols; ++i)
-        test.col(i - trainSize) = input.col( (*order)(i) );
+        test.col(i - trainSize) = input.col(order(i));
     }
   }
   // Spliting only.
@@ -265,8 +265,8 @@ void Split(const arma::Mat<T>& input,
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
-    SplitHelper(input, trainData, testData, testRatio, &order);
-    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, &order);
+    SplitHelper(input, trainData, testData, testRatio, order);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, order);
   }
   else
   {
@@ -309,7 +309,7 @@ void Split(const arma::Mat<T>& input,
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
-    SplitHelper(input, trainData, testData, testRatio, &order);
+    SplitHelper(input, trainData, testData, testRatio, order);
   }
   else
   {
@@ -459,8 +459,8 @@ void Split(const FieldType& input,
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
-    SplitHelper(input, trainData, testData, testRatio, &order);
-    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, &order);
+    SplitHelper(input, trainData, testData, testRatio, order);
+    SplitHelper(inputLabel, trainLabel, testLabel, testRatio, order);
   }
   else
   {
@@ -511,7 +511,7 @@ void Split(const FieldType& input,
   {
     arma::uvec order = arma::shuffle(arma::linspace<arma::uvec>(0,
         input.n_cols - 1, input.n_cols));
-    SplitHelper(input, trainData, testData, testRatio, &order);
+    SplitHelper(input, trainData, testData, testRatio, order);
   }
   else
   {

From 6ebe71864b46383a79fd46f4fbb194118e11d26d Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Sat, 13 Mar 2021 08:55:30 +0530
Subject: [PATCH 252/253] Update src/mlpack/core/data/split_data.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/data/split_data.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 12f3b0efec..6347d68a98 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -414,7 +414,7 @@ Split(const arma::Mat<T>& input,
  * output parameters given (trainData, testData, trainLabel, and testLabel).
  *
  * The input dataset must be of type arma::field. It should have the shape -
- * (n_rows = 1, n_cols = Number of samples, n_slices = 1)
+ * (n_rows = 1, n_cols = Number of samples, n_slices = 1).
  *
  * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
  *

From 4dd32a662180ba1b6895dce01809c665dc64f104 Mon Sep 17 00:00:00 2001
From: Rishabh Garg <56191449+RishabhGarg108@users.noreply.github.com>
Date: Sat, 13 Mar 2021 08:55:43 +0530
Subject: [PATCH 253/253] Update src/mlpack/core/data/split_data.hpp

Co-authored-by: Ryan Curtin <ryan@ratml.org>
---
 src/mlpack/core/data/split_data.hpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index 6347d68a98..f9b0c1558f 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -416,7 +416,7 @@ Split(const arma::Mat<T>& input,
  * The input dataset must be of type arma::field. It should have the shape -
  * (n_rows = 1, n_cols = Number of samples, n_slices = 1).
  *
- * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>
+ * NOTE: Here FieldType could be arma::field<arma::mat> or arma::field<arma::vec>.
  *
  * @code
  * arma::field<arma::mat> input = loadData();