feedforward_network_test.cpp File Reference

#include <mlpack/core.hpp>
#include <mlpack/methods/ann/layer/layer.hpp>
#include <mlpack/methods/ann/loss_functions/mean_squared_error.hpp>
#include <mlpack/methods/ann/ffn.hpp>
#include <ensmallen.hpp>
#include "catch.hpp"
#include "serialization.hpp"
#include "custom_layer.hpp"

Include dependency graph for feedforward_network_test.cpp:

Functions
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)
	Train and evaluate a model with the specified structure.
template<typename MatType = arma::mat, typename ModelType >
void	CheckCopyFunction (ModelType *network1, MatType &trainData, MatType &trainLabels, const size_t maxEpochs)
template<typename MatType = arma::mat, typename ModelType >
void	CheckMoveFunction (ModelType *network1, MatType &trainData, MatType &trainLabels, const size_t maxEpochs)
	TEST_CASE ("CheckCopyMovingVanillaNetworkTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving Vanila network is working or not.
	TEST_CASE ("CheckCopyMovingReparametrizationNetworkTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving network with Reparametrization is working or not.
	TEST_CASE ("CheckCopyMovingLinear3DNetworkTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving network with linear3d is working or not.
	TEST_CASE ("CheckCopyMovingNoisyLinearTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving of Noisy Linear layer is working or not.
	TEST_CASE ("CheckCopyMovingConcatenateTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving of concatenate layer is working or not.
	TEST_CASE ("CheckCopyMovingDropoutNetworkTest", "[FeedForwardNetworkTest]")
	Check whether copying and moving of Dropout network is working or not.
	TEST_CASE ("FFVanillaNetworkTest", "[FeedForwardNetworkTest]")
	Train the vanilla network on a larger dataset.
	TEST_CASE ("ForwardBackwardTest", "[FeedForwardNetworkTest]")
	TEST_CASE ("DropoutNetworkTest", "[FeedForwardNetworkTest]")
	Train the dropout network on a larger dataset.
	TEST_CASE ("HighwayNetworkTest", "[FeedForwardNetworkTest]")
	Train the highway network on a larger dataset.
	TEST_CASE ("DropConnectNetworkTest", "[FeedForwardNetworkTest]")
	Train the DropConnect network on a larger dataset.
	TEST_CASE ("FFNMiscTest", "[FeedForwardNetworkTest]")
	Test miscellaneous things of FFN, e.g. More...
	TEST_CASE ("FFSerializationTest", "[FeedForwardNetworkTest]")
	Test that serialization works ok.
	TEST_CASE ("CustomLayerTest", "[FeedForwardNetworkTest]")
	Test if the custom layers work. More...
	TEST_CASE ("PartialForwardTest", "[FeedForwardNetworkTest]")
	Test the overload of Forward function which allows partial forward pass.
	TEST_CASE ("FFNTrainReturnObjective", "[FeedForwardNetworkTest]")
	Test that FFN::Train() returns finite objective value.
	TEST_CASE ("FFNReturnModel", "[FeedForwardNetworkTest]")
	Test that FFN::Model() allows us to access the instantiated network.
	TEST_CASE ("OptimizerTest", "[FeedForwardNetworkTest]")
	Test to see if the FFN code compiles when the Optimizer doesn't have the MaxIterations() method.
	TEST_CASE ("FFNCheckInputShapeTest", "[FeedForwardNetworkTest]")
	Test to see if an exception is thrown when input with wrong shape is provided to a FFN.

Detailed Description

Author

Marcus Edel

Palash Ahuja

Tests the feed forward network.

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.

Function Documentation

TEST_CASE() [1/2]

TEST_CASE	(	"FFNMiscTest"	,
		""	[FeedForwardNetworkTest]
	)

Test miscellaneous things of FFN, e.g.

copy/move constructor, assignment operator.

TEST_CASE() [2/2]

TEST_CASE	(	"CustomLayerTest"	,
		""	[FeedForwardNetworkTest]
	)

Test if the custom layers work.

The target is to see if the code compiles when the Train and Prediction are called.