template<typename Architecture_t, typename Layer_t = VGeneralLayer<Architecture_t>>
class TMVA::DNN::TDeepNet< Architecture_t, Layer_t >

Generic Deep Neural Network class.

This classs encapsulates the information for all types of Deep Neural Networks.

Template Parameters

Architecture The Architecture type that holds the architecture-specific data types.

Definition at line 75 of file DeepNet.h.

Public Types
using	Matrix_t = typename Architecture_t::Matrix_t

using	Scalar_t = typename Architecture_t::Scalar_t

using	Tensor_t = typename Architecture_t::Tensor_t

Public Member Functions
	TDeepNet ()
	Default Constructor. More...

	TDeepNet (const TDeepNet &)
	Copy-constructor. More...

	TDeepNet (size_t BatchSize, size_t InputDepth, size_t InputHeight, size_t InputWidth, size_t BatchDepth, size_t BatchHeight, size_t BatchWidth, ELossFunction fJ, EInitialization fI=EInitialization::kZero, ERegularization fR=ERegularization::kNone, Scalar_t fWeightDecay=0.0, bool isTraining=false)
	Constructor. More...

	~TDeepNet ()
	Destructor. More...

TBasicGRULayer< Architecture_t > *	AddBasicGRULayer (size_t stateSize, size_t inputSize, size_t timeSteps, bool rememberState=false, bool returnSequence=false, bool resetGateAfter=false)
	Function for adding GRU Layer in the Deep Neural Network, with given parameters. More...

void	AddBasicGRULayer (TBasicGRULayer< Architecture_t > *basicGRULayer)
	Function for adding GRU Layer in the Deep Neural Network, when the layer is already created. More...

TBasicLSTMLayer< Architecture_t > *	AddBasicLSTMLayer (size_t stateSize, size_t inputSize, size_t timeSteps, bool rememberState=false, bool returnSequence=false)
	Function for adding LSTM Layer in the Deep Neural Network, with given parameters. More...

void	AddBasicLSTMLayer (TBasicLSTMLayer< Architecture_t > *basicLSTMLayer)
	Function for adding LSTM Layer in the Deep Neural Network, when the layer is already created. More...

TBasicRNNLayer< Architecture_t > *	AddBasicRNNLayer (size_t stateSize, size_t inputSize, size_t timeSteps, bool rememberState=false, bool returnSequence=false, EActivationFunction f=EActivationFunction::kTanh)
	Function for adding Recurrent Layer in the Deep Neural Network, with given parameters. More...

void	AddBasicRNNLayer (TBasicRNNLayer< Architecture_t > *basicRNNLayer)
	Function for adding Vanilla RNN when the layer is already created. More...

TBatchNormLayer< Architecture_t > *	AddBatchNormLayer (Scalar_t momentum=-1, Scalar_t epsilon=0.0001)
	Function for adding a Batch Normalization layer with given parameters. More...

TConvLayer< Architecture_t > *	AddConvLayer (size_t depth, size_t filterHeight, size_t filterWidth, size_t strideRows, size_t strideCols, size_t paddingHeight, size_t paddingWidth, EActivationFunction f, Scalar_t dropoutProbability=1.0)
	Function for adding Convolution layer in the Deep Neural Network, with a given depth, filter height and width, striding in rows and columns, the zero paddings, as well as the activation function and the dropout probability. More...

void	AddConvLayer (TConvLayer< Architecture_t > *convLayer)
	Function for adding Convolution Layer in the Deep Neural Network, when the layer is already created. More...

TDenseLayer< Architecture_t > *	AddDenseLayer (size_t width, EActivationFunction f, Scalar_t dropoutProbability=1.0)
	Function for adding Dense Connected Layer in the Deep Neural Network, with a given width, activation function and dropout probability. More...

void	AddDenseLayer (TDenseLayer< Architecture_t > *denseLayer)
	Function for adding Dense Layer in the Deep Neural Network, when the layer is already created. More...

void	AddMaxPoolLayer (CNN::TMaxPoolLayer< Architecture_t > *maxPoolLayer)
	Function for adding Max Pooling layer in the Deep Neural Network, when the layer is already created. More...

TMaxPoolLayer< Architecture_t > *	AddMaxPoolLayer (size_t frameHeight, size_t frameWidth, size_t strideRows, size_t strideCols, Scalar_t dropoutProbability=1.0)
	Function for adding Pooling layer in the Deep Neural Network, with a given filter height and width, striding in rows and columns as well as the dropout probability. More...

TReshapeLayer< Architecture_t > *	AddReshapeLayer (size_t depth, size_t height, size_t width, bool flattening)
	Function for adding Reshape Layer in the Deep Neural Network, with a given height and width. More...

void	AddReshapeLayer (TReshapeLayer< Architecture_t > *reshapeLayer)
	Function for adding Reshape Layer in the Deep Neural Network, when the layer is already created. More...

void	Backward (const Tensor_t &input, const Matrix_t &groundTruth, const Matrix_t &weights)
	Function that executes the entire backward pass in the network. More...

void	Clear ()
	Remove all layers from the network. More...

void	Forward (Tensor_t &input, bool applyDropout=false)
	Function that executes the entire forward pass in the network. More...

size_t	GetBatchDepth () const

size_t	GetBatchHeight () const

size_t	GetBatchSize () const
	Getters. More...

size_t	GetBatchWidth () const

size_t	GetDepth () const

EInitialization	GetInitialization () const

size_t	GetInputDepth () const

size_t	GetInputHeight () const

size_t	GetInputWidth () const

Layer_t *	GetLayerAt (size_t i)
	Get the layer in the vector of layers at poistion i. More...

const Layer_t *	GetLayerAt (size_t i) const

std::vector< Layer_t * > &	GetLayers ()

const std::vector< Layer_t * > &	GetLayers () const

ELossFunction	GetLossFunction () const

size_t	GetOutputWidth () const

ERegularization	GetRegularization () const

Scalar_t	GetWeightDecay () const

void	Initialize ()
	DAE functions. More...

bool	IsTraining () const

Scalar_t	Loss (const Matrix_t &groundTruth, const Matrix_t &weights, bool includeRegularization=true) const
	Function for evaluating the loss, based on the activations stored in the last layer. More...

Scalar_t	Loss (Tensor_t &input, const Matrix_t &groundTruth, const Matrix_t &weights, bool inTraining=false, bool includeRegularization=true)
	Function for evaluating the loss, based on the propagation of the given input. More...

void	Prediction (Matrix_t &predictions, EOutputFunction f) const
	Prediction based on activations stored in the last layer. More...

void	Prediction (Matrix_t &predictions, Tensor_t &input, EOutputFunction f)
	Prediction for the given inputs, based on what network learned. More...

void	Print () const
	Print the Deep Net Info. More...

Scalar_t	RegularizationTerm () const
	Function for computing the regularizaton term to be added to the loss function More...

void	ResetTraining ()
	Function that reset some training flags after looping all the events but not the weights. More...

void	SetBatchDepth (size_t batchDepth)

void	SetBatchHeight (size_t batchHeight)

void	SetBatchSize (size_t batchSize)
	Setters. More...

void	SetBatchWidth (size_t batchWidth)

void	SetDropoutProbabilities (const std::vector< Double_t > &probabilities)

void	SetInitialization (EInitialization I)

void	SetInputDepth (size_t inputDepth)

void	SetInputHeight (size_t inputHeight)

void	SetInputWidth (size_t inputWidth)

void	SetLossFunction (ELossFunction J)

void	SetRegularization (ERegularization R)

void	SetWeightDecay (Scalar_t weightDecay)

void	Update (Scalar_t learningRate)
	Function that will update the weights and biases in the layers that contain weights and biases. More...

Private Member Functions
size_t	calculateDimension (int imgDim, int fltDim, int padding, int stride)

bool	isInteger (Scalar_t x) const

Private Attributes
size_t	fBatchDepth
	The depth of the batch used for training/testing. More...

size_t	fBatchHeight
	The height of the batch used for training/testing. More...

size_t	fBatchSize
	Batch size used for training and evaluation. More...

size_t	fBatchWidth
	The width of the batch used for training/testing. More...

EInitialization	fI
	The initialization method of the network. More...

size_t	fInputDepth
	The depth of the input. More...

size_t	fInputHeight
	The height of the input. More...

size_t	fInputWidth
	The width of the input. More...

bool	fIsTraining
	Is the network training? More...

ELossFunction	fJ
	The loss function of the network. More...

std::vector< Layer_t * >	fLayers
	The layers consisting the DeepNet. More...

ERegularization	fR
	The regularization used for the network. More...

Scalar_t	fWeightDecay
	The weight decay factor. More...

#include <TMVA/DNN/DeepNet.h>

Member Typedef Documentation

◆ Matrix_t

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

using TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Matrix_t = typename Architecture_t::Matrix_t

Definition at line 79 of file DeepNet.h.

◆ Scalar_t

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

using TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Scalar_t = typename Architecture_t::Scalar_t

Definition at line 80 of file DeepNet.h.

◆ Tensor_t

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

using TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Tensor_t = typename Architecture_t::Tensor_t

Definition at line 78 of file DeepNet.h.

Constructor & Destructor Documentation

◆ TDeepNet() [1/3]

template<typename Architecture_t , typename Layer_t >

TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::TDeepNet

Default Constructor.

Definition at line 380 of file DeepNet.h.

◆ TDeepNet() [2/3]

template<typename Architecture_t , typename Layer_t >

TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::TDeepNet	(	size_t	BatchSize,
		size_t	InputDepth,
		size_t	InputHeight,
		size_t	InputWidth,
		size_t	BatchDepth,
		size_t	BatchHeight,
		size_t	BatchWidth,
		ELossFunction	fJ,
		EInitialization	fI = `EInitialization::kZero`,
		ERegularization	fR = `ERegularization::kNone`,
		Scalar_t	fWeightDecay = `0.0`,
		bool	isTraining = `false`
	)

Constructor.

Definition at line 390 of file DeepNet.h.

◆ TDeepNet() [3/3]

template<typename Architecture_t , typename Layer_t >

TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::TDeepNet ( const TDeepNet< Architecture_t, Layer_t > & deepNet )

Copy-constructor.

Definition at line 402 of file DeepNet.h.

◆ ~TDeepNet()

template<typename Architecture_t , typename Layer_t >

TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::~TDeepNet

Destructor.

Definition at line 413 of file DeepNet.h.

Member Function Documentation

◆ AddBasicGRULayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TBasicGRULayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicGRULayer	(	size_t	stateSize,
		size_t	inputSize,
		size_t	timeSteps,
		bool	rememberState = `false`,
		bool	returnSequence = `false`,
		bool	resetGateAfter = `false`
	)

Function for adding GRU Layer in the Deep Neural Network, with given parameters.

Definition at line 610 of file DeepNet.h.

◆ AddBasicGRULayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicGRULayer ( TBasicGRULayer< Architecture_t > * basicGRULayer )

Function for adding GRU Layer in the Deep Neural Network, when the layer is already created.

Definition at line 643 of file DeepNet.h.

◆ AddBasicLSTMLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TBasicLSTMLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicLSTMLayer	(	size_t	stateSize,
		size_t	inputSize,
		size_t	timeSteps,
		bool	rememberState = `false`,
		bool	returnSequence = `false`
	)

Function for adding LSTM Layer in the Deep Neural Network, with given parameters.

Definition at line 569 of file DeepNet.h.

◆ AddBasicLSTMLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicLSTMLayer ( TBasicLSTMLayer< Architecture_t > * basicLSTMLayer )

Function for adding LSTM Layer in the Deep Neural Network, when the layer is already created.

Definition at line 602 of file DeepNet.h.

◆ AddBasicRNNLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TBasicRNNLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicRNNLayer	(	size_t	stateSize,
		size_t	inputSize,
		size_t	timeSteps,
		bool	rememberState = `false`,
		bool	returnSequence = `false`,
		EActivationFunction	f = `EActivationFunction::kTanh`
	)

Function for adding Recurrent Layer in the Deep Neural Network, with given parameters.

Definition at line 526 of file DeepNet.h.

◆ AddBasicRNNLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBasicRNNLayer ( TBasicRNNLayer< Architecture_t > * basicRNNLayer )

Function for adding Vanilla RNN when the layer is already created.

Definition at line 562 of file DeepNet.h.

◆ AddBatchNormLayer()

template<typename Architecture_t , typename Layer_t >

TBatchNormLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddBatchNormLayer	(	Scalar_t	momentum = `-1`,
		Scalar_t	epsilon = `0.0001`
	)

Function for adding a Batch Normalization layer with given parameters.

Definition at line 827 of file DeepNet.h.

◆ AddConvLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TConvLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddConvLayer	(	size_t	depth,
		size_t	filterHeight,
		size_t	filterWidth,
		size_t	strideRows,
		size_t	strideCols,
		size_t	paddingHeight,
		size_t	paddingWidth,
		EActivationFunction	f,
		Scalar_t	dropoutProbability = `1.0`
	)

Function for adding Convolution layer in the Deep Neural Network, with a given depth, filter height and width, striding in rows and columns, the zero paddings, as well as the activation function and the dropout probability.

Based on these parameters, it calculates the width and height of the convolutional layer.

Definition at line 441 of file DeepNet.h.

◆ AddConvLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddConvLayer ( TConvLayer< Architecture_t > * convLayer )

Function for adding Convolution Layer in the Deep Neural Network, when the layer is already created.

Definition at line 480 of file DeepNet.h.

◆ AddDenseLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TDenseLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddDenseLayer	(	size_t	width,
		EActivationFunction	f,
		Scalar_t	dropoutProbability = `1.0`
	)

Function for adding Dense Connected Layer in the Deep Neural Network, with a given width, activation function and dropout probability.

Based on the previous layer dimensions, it calculates the input width of the fully connected layer.

Definition at line 742 of file DeepNet.h.

◆ AddDenseLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddDenseLayer ( TDenseLayer< Architecture_t > * denseLayer )

Function for adding Dense Layer in the Deep Neural Network, when the layer is already created.

Definition at line 768 of file DeepNet.h.

◆ AddMaxPoolLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddMaxPoolLayer ( CNN::TMaxPoolLayer< Architecture_t > * maxPoolLayer )

Function for adding Max Pooling layer in the Deep Neural Network, when the layer is already created.

Definition at line 519 of file DeepNet.h.

◆ AddMaxPoolLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

TMaxPoolLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddMaxPoolLayer	(	size_t	frameHeight,
		size_t	frameWidth,
		size_t	strideRows,
		size_t	strideCols,
		Scalar_t	dropoutProbability = `1.0`
	)

Function for adding Pooling layer in the Deep Neural Network, with a given filter height and width, striding in rows and columns as well as the dropout probability.

The depth is same as the previous layer depth. Based on these parameters, it calculates the width and height of the pooling layer.

Definition at line 487 of file DeepNet.h.

◆ AddReshapeLayer() [1/2]

template<typename Architecture_t , typename Layer_t >

TReshapeLayer< Architecture_t > * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddReshapeLayer	(	size_t	depth,
		size_t	height,
		size_t	width,
		bool	flattening
	)

Function for adding Reshape Layer in the Deep Neural Network, with a given height and width.

It will take every matrix from the previous layer and reshape it to a matrix with new dimensions.

Definition at line 775 of file DeepNet.h.

◆ AddReshapeLayer() [2/2]

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::AddReshapeLayer ( TReshapeLayer< Architecture_t > * reshapeLayer )

Function for adding Reshape Layer in the Deep Neural Network, when the layer is already created.

Definition at line 872 of file DeepNet.h.

◆ Backward()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Backward	(	const Tensor_t &	input,
		const Matrix_t &	groundTruth,
		const Matrix_t &	weights
	)

Function that executes the entire backward pass in the network.

Definition at line 1035 of file DeepNet.h.

◆ calculateDimension()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::calculateDimension	(	int	imgDim,
		int	fltDim,
		int	padding,
		int	stride
	)

private

Definition at line 423 of file DeepNet.h.

◆ Clear()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Clear ( )

inline

Remove all layers from the network.

Definition at line 336 of file DeepNet.h.

◆ Forward()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Forward	(	Tensor_t &	input,
		bool	applyDropout = `false`
	)

Function that executes the entire forward pass in the network.

Definition at line 898 of file DeepNet.h.

◆ GetBatchDepth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetBatchDepth ( ) const

inline

Definition at line 344 of file DeepNet.h.

◆ GetBatchHeight()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetBatchHeight ( ) const

inline

Definition at line 345 of file DeepNet.h.

◆ GetBatchSize()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetBatchSize ( ) const

inline

Getters.

Definition at line 339 of file DeepNet.h.

◆ GetBatchWidth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetBatchWidth ( ) const

inline

Definition at line 346 of file DeepNet.h.

◆ GetDepth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetDepth ( ) const

inline

Definition at line 328 of file DeepNet.h.

◆ GetInitialization()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

EInitialization TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetInitialization ( ) const

inline

Definition at line 351 of file DeepNet.h.

◆ GetInputDepth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetInputDepth ( ) const

inline

Definition at line 340 of file DeepNet.h.

◆ GetInputHeight()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetInputHeight ( ) const

inline

Definition at line 341 of file DeepNet.h.

◆ GetInputWidth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetInputWidth ( ) const

inline

Definition at line 342 of file DeepNet.h.

◆ GetLayerAt() [1/2]

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

Layer_t * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetLayerAt ( size_t i )

inline

Get the layer in the vector of layers at poistion i.

Definition at line 324 of file DeepNet.h.

◆ GetLayerAt() [2/2]

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

const Layer_t * TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetLayerAt ( size_t i ) const

inline

Definition at line 325 of file DeepNet.h.

◆ GetLayers() [1/2]

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

std::vector< Layer_t * > & TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetLayers ( )

inline

Definition at line 332 of file DeepNet.h.

◆ GetLayers() [2/2]

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

const std::vector< Layer_t * > & TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetLayers ( ) const

inline

Definition at line 333 of file DeepNet.h.

◆ GetLossFunction()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

ELossFunction TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetLossFunction ( ) const

inline

Definition at line 350 of file DeepNet.h.

◆ GetOutputWidth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetOutputWidth ( ) const

inline

Definition at line 329 of file DeepNet.h.

◆ GetRegularization()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

ERegularization TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetRegularization ( ) const

inline

Definition at line 352 of file DeepNet.h.

◆ GetWeightDecay()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

Scalar_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::GetWeightDecay ( ) const

inline

Definition at line 353 of file DeepNet.h.

◆ Initialize()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Initialize

DAE functions.

Function for initialization of the Neural Net.

Definition at line 879 of file DeepNet.h.

◆ isInteger()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

bool TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::isInteger ( Scalar_t x ) const

inlineprivate

Definition at line 84 of file DeepNet.h.

◆ IsTraining()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

bool TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::IsTraining ( ) const

inline

Definition at line 348 of file DeepNet.h.

◆ Loss() [1/2]

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Loss	(	const Matrix_t &	groundTruth,
		const Matrix_t &	weights,
		bool	includeRegularization = `true`
	)		const

Function for evaluating the loss, based on the activations stored in the last layer.

Definition at line 1265 of file DeepNet.h.

◆ Loss() [2/2]

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Loss	(	Tensor_t &	input,
		const Matrix_t &	groundTruth,
		const Matrix_t &	weights,
		bool	inTraining = `false`,
		bool	includeRegularization = `true`
	)

Function for evaluating the loss, based on the propagation of the given input.

Definition at line 1281 of file DeepNet.h.

◆ Prediction() [1/2]

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Prediction	(	Matrix_t &	predictions,
		EOutputFunction	f
	)		const

Prediction based on activations stored in the last layer.

Definition at line 1305 of file DeepNet.h.

◆ Prediction() [2/2]

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Prediction	(	Matrix_t &	predictions,
		Tensor_t &	input,
		EOutputFunction	f
	)

Prediction for the given inputs, based on what network learned.

Definition at line 1313 of file DeepNet.h.

◆ Print()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Print

Print the Deep Net Info.

Definition at line 1323 of file DeepNet.h.

◆ RegularizationTerm()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::RegularizationTerm

Function for computing the regularizaton term to be added to the loss function

Definition at line 1291 of file DeepNet.h.

◆ ResetTraining()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::ResetTraining

Function that reset some training flags after looping all the events but not the weights.

Definition at line 888 of file DeepNet.h.

◆ SetBatchDepth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetBatchDepth ( size_t batchDepth )

inline

Definition at line 363 of file DeepNet.h.

◆ SetBatchHeight()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetBatchHeight ( size_t batchHeight )

inline

Definition at line 364 of file DeepNet.h.

◆ SetBatchSize()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetBatchSize ( size_t batchSize )

inline

Setters.

Definition at line 359 of file DeepNet.h.

◆ SetBatchWidth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetBatchWidth ( size_t batchWidth )

inline

Definition at line 365 of file DeepNet.h.

◆ SetDropoutProbabilities()

template<typename Architecture_t , typename Layer_t >

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetDropoutProbabilities ( const std::vector< Double_t > & probabilities )

Definition at line 1342 of file DeepNet.h.

◆ SetInitialization()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetInitialization ( EInitialization I )

inline

Definition at line 367 of file DeepNet.h.

◆ SetInputDepth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetInputDepth ( size_t inputDepth )

inline

Definition at line 360 of file DeepNet.h.

◆ SetInputHeight()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetInputHeight ( size_t inputHeight )

inline

Definition at line 361 of file DeepNet.h.

◆ SetInputWidth()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetInputWidth ( size_t inputWidth )

inline

Definition at line 362 of file DeepNet.h.

◆ SetLossFunction()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetLossFunction ( ELossFunction J )

inline

Definition at line 366 of file DeepNet.h.

◆ SetRegularization()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetRegularization ( ERegularization R )

inline

Definition at line 368 of file DeepNet.h.

◆ SetWeightDecay()

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

void TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::SetWeightDecay ( Scalar_t weightDecay )

inline

Definition at line 369 of file DeepNet.h.

◆ Update()

template<typename Architecture_t , typename Layer_t >

auto TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::Update ( Scalar_t learningRate )

Function that will update the weights and biases in the layers that contain weights and biases.

Definition at line 1256 of file DeepNet.h.

Member Data Documentation

◆ fBatchDepth

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fBatchDepth

private

The depth of the batch used for training/testing.

Definition at line 95 of file DeepNet.h.

◆ fBatchHeight

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fBatchHeight

private

The height of the batch used for training/testing.

Definition at line 96 of file DeepNet.h.

◆ fBatchSize

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fBatchSize

private

Batch size used for training and evaluation.

Definition at line 90 of file DeepNet.h.

◆ fBatchWidth

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fBatchWidth

private

The width of the batch used for training/testing.

Definition at line 97 of file DeepNet.h.

◆ fI

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

EInitialization TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fI

private

The initialization method of the network.

Definition at line 102 of file DeepNet.h.

◆ fInputDepth

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fInputDepth

private

The depth of the input.

Definition at line 91 of file DeepNet.h.

◆ fInputHeight

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fInputHeight

private

The height of the input.

Definition at line 92 of file DeepNet.h.

◆ fInputWidth

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

size_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fInputWidth

private

The width of the input.

Definition at line 93 of file DeepNet.h.

◆ fIsTraining

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

bool TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fIsTraining

private

Is the network training?

Definition at line 99 of file DeepNet.h.

◆ fJ

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

ELossFunction TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fJ

private

The loss function of the network.

Definition at line 101 of file DeepNet.h.

◆ fLayers

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

std::vector<Layer_t *> TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fLayers

private

The layers consisting the DeepNet.

Definition at line 88 of file DeepNet.h.

◆ fR

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

ERegularization TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fR

private

The regularization used for the network.

Definition at line 103 of file DeepNet.h.

◆ fWeightDecay

template<typename Architecture_t , typename Layer_t = VGeneralLayer<Architecture_t>>

Scalar_t TMVA::DNN::TDeepNet< Architecture_t, Layer_t >::fWeightDecay

private

The weight decay factor.

Definition at line 104 of file DeepNet.h.

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

tmva/tmva/inc/TMVA/DNN/DeepNet.h

Public Types

Public Member Functions

Private Member Functions

Private Attributes

Member Typedef Documentation

◆ Matrix_t

◆ Scalar_t

◆ Tensor_t

Constructor & Destructor Documentation

◆ TDeepNet() [1/3]

◆ TDeepNet() [2/3]

◆ TDeepNet() [3/3]

◆ ~TDeepNet()

Member Function Documentation

◆ AddBasicGRULayer() [1/2]

◆ AddBasicGRULayer() [2/2]

◆ AddBasicLSTMLayer() [1/2]

◆ AddBasicLSTMLayer() [2/2]

◆ AddBasicRNNLayer() [1/2]

◆ AddBasicRNNLayer() [2/2]

◆ AddBatchNormLayer()

◆ AddConvLayer() [1/2]

◆ AddConvLayer() [2/2]

◆ AddDenseLayer() [1/2]

◆ AddDenseLayer() [2/2]

◆ AddMaxPoolLayer() [1/2]

◆ AddMaxPoolLayer() [2/2]

◆ AddReshapeLayer() [1/2]

◆ AddReshapeLayer() [2/2]

◆ Backward()

◆ calculateDimension()

◆ Clear()

◆ Forward()

◆ GetBatchDepth()

◆ GetBatchHeight()

◆ GetBatchSize()

◆ GetBatchWidth()

◆ GetDepth()

◆ GetInitialization()

◆ GetInputDepth()

◆ GetInputHeight()

◆ GetInputWidth()

◆ GetLayerAt() [1/2]

◆ GetLayerAt() [2/2]

◆ GetLayers() [1/2]

◆ GetLayers() [2/2]

◆ GetLossFunction()

◆ GetOutputWidth()

◆ GetRegularization()

◆ GetWeightDecay()

◆ Initialize()

◆ isInteger()

◆ IsTraining()

◆ Loss() [1/2]

◆ Loss() [2/2]

◆ Prediction() [1/2]

◆ Prediction() [2/2]

◆ Print()

◆ RegularizationTerm()

◆ ResetTraining()

◆ SetBatchDepth()

◆ SetBatchHeight()

◆ SetBatchSize()

◆ SetBatchWidth()

◆ SetDropoutProbabilities()

◆ SetInitialization()

◆ SetInputDepth()

◆ SetInputHeight()

◆ SetInputWidth()

◆ SetLossFunction()

◆ SetRegularization()

◆ SetWeightDecay()

◆ Update()

Member Data Documentation

◆ fBatchDepth

◆ fBatchHeight

◆ fBatchSize

◆ fBatchWidth

◆ fI

◆ fInputDepth