Merge pull request #2828 from abh2k/lp

Added LP pooling  layer.

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

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"

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>
@@ -219,6 +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>*,

src/mlpack/methods/ann/layer/lp_pooling.hpp

@@ -0,0 +1,284 @@
+/**
+ * @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 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 normType,
+            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 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; }
+  //! 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 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) = pow(arma::accu(arma::pow(subInput,
+            normType)), 1.0 / normType);
+      }
+    }
+  }
+
+  /**
+   * 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 = 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, normType - 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 normType;
+
+  //! 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;
+
+  //! 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

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 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),
+    strideHeight(strideHeight),
+    floor(floor),
+    inSize(0),
+    outSize(0),
+    inputWidth(0),
+    inputHeight(0),
+    outputWidth(0),
+    outputHeight(0),
+    reset(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(normType));
+  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

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.
    *

src/mlpack/tests/ann_layer_test.cpp

@@ -3838,6 +3838,51 @@ TEST_CASE("TransposedConvolutionLayerPaddingTest", "[ANNLayerTest]")
   REQUIRE(arma::accu(delta) == 0.0);
 }
 
+/**
+ * Simple test for Lp Pooling layer.
+ */
+TEST_CASE("LpMaxPoolingTestCase", "[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.
+  LpPooling<> 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.
+  LpPooling<> 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.
  */