Class implementing a simple MNIST patch reconstruction with multi-layer neural net. More...

#include <MNISTPatchReconstructionApplication.hpp>

Inheritance diagram for mic::applications::MNISTPatchReconstructionApplication:

Collaboration diagram for mic::applications::MNISTPatchReconstructionApplication:

Public Member Functions
	MNISTPatchReconstructionApplication (std::string node_name_="mnist_patch_autoencoder_reconstruction")

virtual	~MNISTPatchReconstructionApplication ()

Protected Member Functions
virtual void	initializePropertyDependentVariables ()

virtual void	initialize (int argc, char *argv[])

virtual bool	performLearningStep ()

virtual void	collectTestStatistics ()

virtual void	populateTestStatistics ()

Private Attributes
mic::types::MatrixXfPtr	input_image
	Input image/matrix. More...

mic::types::MatrixXfPtr	reconstructed_image
	Reconstructed image/matrix. More...

mic::importers::MNISTPatchImporter *	training_dataset_importer
	Importer responsible for loading training dataset. More...

mic::importers::MNISTPatchImporter *	test_dataset_importer
	Importer responsible for loading testing dataset. More...

WindowMatrix2D *	w2d_input
	Window for displaying the input image. More...

WindowMatrix2D *	w2d_reconstruction
	Window for displaying the reconstructed image. More...

WindowCollectorChart< float > *	w_chart
	Window for displaying chart with statistics. More...

size_t	patch_size
	Size of the patch - copied from importers. More...

mic::utils::DataCollectorPtr < std::string, float >	collector_ptr
	Data collector. More...

mic::configuration::Property < std::string >	mlnn_filename
	Property: name of the file to which the neural network will be serialized (or deserialized from). More...

mic::configuration::Property < bool >	mlnn_save
	Property: flag denoting whether the nn should be saved to a file (after every episode end). More...

mic::configuration::Property < bool >	mlnn_load
	Property: flag denoting whether the nn should be loaded from a file (at the initialization of the task). More...

BackpropagationNeuralNetwork < float >	neural_net
	Multi-layer neural network. More...

Detailed Description

Class implementing a simple MNIST patch reconstruction with multi-layer neural net.

Author: tkornuta

Definition at line 47 of file MNISTPatchReconstructionApplication.hpp.

Constructor & Destructor Documentation

mic::applications::MNISTPatchReconstructionApplication::MNISTPatchReconstructionApplication ( std::string node_name_ = "mnist_patch_autoencoder_reconstruction" )

Default Constructor. Sets the application/node name, default values of variables, initializes classifier etc.

Parameters

node_name_ Name of the application/node (in configuration file).

Definition at line 58 of file MNISTPatchReconstructionApplication.cpp.

References mlnn_filename, mlnn_load, mlnn_save, test_dataset_importer, and training_dataset_importer.

mic::applications::MNISTPatchReconstructionApplication::~MNISTPatchReconstructionApplication ( )

virtual

Destructor.

Definition at line 76 of file MNISTPatchReconstructionApplication.cpp.

References test_dataset_importer, training_dataset_importer, w2d_input, w2d_reconstruction, and w_chart.

Member Function Documentation

void mic::applications::MNISTPatchReconstructionApplication::collectTestStatistics ( )

protectedvirtual

Collects test statistics, executed in every testing step.

Definition at line 178 of file MNISTPatchReconstructionApplication.cpp.

References collector_ptr, mic::mlnn::MultiLayerNeuralNetwork< eT >::getPredictions(), neural_net, patch_size, reconstructed_image, mic::mlnn::BackpropagationNeuralNetwork< eT >::test(), and test_dataset_importer.

Here is the call graph for this function:

void mic::applications::MNISTPatchReconstructionApplication::initialize	(	int	argc,
		char *	argv[]
	)

protectedvirtual

Method initializes GLUT and OpenGL windows.

Parameters

argc	Number of application parameters.
argv	Array of application parameters.

Definition at line 85 of file MNISTPatchReconstructionApplication.cpp.

References collector_ptr, w2d_input, w2d_reconstruction, and w_chart.

void mic::applications::MNISTPatchReconstructionApplication::initializePropertyDependentVariables ( )

protectedvirtual

Initializes all variables that are property-dependent, imports MNIST datasets, for both learning and testing purposes.

Definition at line 105 of file MNISTPatchReconstructionApplication.cpp.

References input_image, mic::mlnn::MultiLayerNeuralNetwork< eT >::load(), mlnn_filename, mlnn_load, neural_net, patch_size, mic::mlnn::MultiLayerNeuralNetwork< eT >::pushLayer(), reconstructed_image, mic::mlnn::BackpropagationNeuralNetwork< eT >::setLoss(), test_dataset_importer, training_dataset_importer, w2d_input, and w2d_reconstruction.

Here is the call graph for this function:

bool mic::applications::MNISTPatchReconstructionApplication::performLearningStep ( )

protectedvirtual

Performs learning step.

Definition at line 150 of file MNISTPatchReconstructionApplication.cpp.

References collector_ptr, mic::mlnn::MultiLayerNeuralNetwork< eT >::getPredictions(), neural_net, patch_size, reconstructed_image, mic::mlnn::BackpropagationNeuralNetwork< eT >::train(), and training_dataset_importer.

Here is the call graph for this function:

void mic::applications::MNISTPatchReconstructionApplication::populateTestStatistics ( )

protectedvirtual

Populates test statistics, executed only every number_of_averaged_test_measures testing steps.

Definition at line 205 of file MNISTPatchReconstructionApplication.cpp.

References mlnn_filename, mlnn_save, neural_net, and mic::mlnn::MultiLayerNeuralNetwork< eT >::save().

Here is the call graph for this function:

Member Data Documentation

mic::utils::DataCollectorPtr<std::string, float> mic::applications::MNISTPatchReconstructionApplication::collector_ptr

private

Data collector.

Definition at line 115 of file MNISTPatchReconstructionApplication.hpp.

Referenced by collectTestStatistics(), initialize(), and performLearningStep().

mic::types::MatrixXfPtr mic::applications::MNISTPatchReconstructionApplication::input_image

private

Input image/matrix.

Definition at line 91 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initializePropertyDependentVariables().

mic::configuration::Property<std::string> mic::applications::MNISTPatchReconstructionApplication::mlnn_filename

private

Property: name of the file to which the neural network will be serialized (or deserialized from).

Definition at line 118 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initializePropertyDependentVariables(), MNISTPatchReconstructionApplication(), and populateTestStatistics().

mic::configuration::Property<bool> mic::applications::MNISTPatchReconstructionApplication::mlnn_load

private

Property: flag denoting whether the nn should be loaded from a file (at the initialization of the task).

Definition at line 124 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initializePropertyDependentVariables(), and MNISTPatchReconstructionApplication().

mic::configuration::Property<bool> mic::applications::MNISTPatchReconstructionApplication::mlnn_save

private

Property: flag denoting whether the nn should be saved to a file (after every episode end).

Definition at line 121 of file MNISTPatchReconstructionApplication.hpp.

Referenced by MNISTPatchReconstructionApplication(), and populateTestStatistics().

BackpropagationNeuralNetwork<float> mic::applications::MNISTPatchReconstructionApplication::neural_net

private

Multi-layer neural network.

Definition at line 127 of file MNISTPatchReconstructionApplication.hpp.

Referenced by collectTestStatistics(), initializePropertyDependentVariables(), performLearningStep(), and populateTestStatistics().

size_t mic::applications::MNISTPatchReconstructionApplication::patch_size

private

Size of the patch - copied from importers.

Definition at line 112 of file MNISTPatchReconstructionApplication.hpp.

Referenced by collectTestStatistics(), initializePropertyDependentVariables(), and performLearningStep().

mic::types::MatrixXfPtr mic::applications::MNISTPatchReconstructionApplication::reconstructed_image

private

Reconstructed image/matrix.

Definition at line 94 of file MNISTPatchReconstructionApplication.hpp.

Referenced by collectTestStatistics(), initializePropertyDependentVariables(), and performLearningStep().

mic::importers::MNISTPatchImporter* mic::applications::MNISTPatchReconstructionApplication::test_dataset_importer

private

Importer responsible for loading testing dataset.

Definition at line 100 of file MNISTPatchReconstructionApplication.hpp.

Referenced by collectTestStatistics(), initializePropertyDependentVariables(), MNISTPatchReconstructionApplication(), and ~MNISTPatchReconstructionApplication().

mic::importers::MNISTPatchImporter* mic::applications::MNISTPatchReconstructionApplication::training_dataset_importer

private

Importer responsible for loading training dataset.

Definition at line 97 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initializePropertyDependentVariables(), MNISTPatchReconstructionApplication(), performLearningStep(), and ~MNISTPatchReconstructionApplication().

WindowMatrix2D* mic::applications::MNISTPatchReconstructionApplication::w2d_input

private

Window for displaying the input image.

Definition at line 103 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initialize(), initializePropertyDependentVariables(), and ~MNISTPatchReconstructionApplication().

WindowMatrix2D* mic::applications::MNISTPatchReconstructionApplication::w2d_reconstruction

private

Window for displaying the reconstructed image.

Definition at line 106 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initialize(), initializePropertyDependentVariables(), and ~MNISTPatchReconstructionApplication().

WindowCollectorChart<float>* mic::applications::MNISTPatchReconstructionApplication::w_chart

private

Window for displaying chart with statistics.

Definition at line 109 of file MNISTPatchReconstructionApplication.hpp.

Referenced by initialize(), and ~MNISTPatchReconstructionApplication().

The documentation for this class was generated from the following files:

src/application/MNISTPatchReconstructionApplication.hpp
src/application/MNISTPatchReconstructionApplication.cpp

Public Member Functions

Protected Member Functions

Private Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation