Test that are compiling are those with no comments.
Other commented tests have either pointer inisde or or need a
specific wrapper
Signed-off-by: Omar Shrit <omar@shrit.me>
Remove functions defined in boost serialization namespace.
It is no longer required since it has been replaced by cereal
Signed-off-by: Omar Shrit <omar@shrit.me>
It seems that cereal supports nested complex type such as
std::unordered_map<int, std::pair<int, int>>. However in order to
be able to do this we need to include the <cereal/types/utility.hpp>
Signed-off-by: Omar Shrit <omar@shrit.me>
author kartikdutt18 <kartikdutt@live.in> 1593966541 +0530
committer kartikdutt18 <kartikdutt@live.in> 1594273531 +0530
Set running vars to 1
Fix equation definition.
Support explicit dimension lists in ARFF files.
Make one dimension "harder" by using T/F not 1/0.
Oops, print training accuracy when the user specifies.
Now a higher minimum split is necessary to make the test work.
Fix iterator end overrun.
Style Fixes
Linking RL tutorial
adding poisson nll loss
use
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
use class name in class description
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
LaTeX format in parameter description
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
changes in description
fix type error
fix type error
added description of accessor methods
correction in header guards
Co-authored-by: Mikhail Lozhnikov <lozhnikovma@gmail.com>
reverting back changes in unrelated code by mistake
adding more tests
check if probs are in range [0, 1]
adding tests for logInput = false
remove check from Backward
change variable name reduction to mean
Update batch_norm_impl.hpp
Better comments and style fixes
Don't use welford in minibatchnorm
Don't use welford method anywhere add tests from pytorch
Serialization Fix
Does momentum part fail
Does making var const& fix the error
Change var initialization
Revert to previous definition -> make atomic changes
Lets change the definition first
Single implementation
Rever last 3 commits
Input Stream Fix
Dont transpose
Redo the whole implementation, cleaner simpler code
Only batchnorm2d
Remove merge redundant files
Use cubes as done in conv layers
Style Fixes
Add serialization of multiplicative factor
Remove multiplication factor
Add the factor in expression
Add numerical stability