template<typename Architecture_t>
class TMVA::DNN::TBatchNormLayer< Architecture_t >

Layer implementing Batch Normalization.

The input from each batch are normalized during training to have zero mean and unit variance and they are then scaled by two parameter, different for each input variable:

a scale factor gamma
an offset beta

In addition a running batch mean and variance is computed and stored in the class During inference the inputs are not normalized using the batch mean but the previously computed at running mean and variance If momentum is in [0,1) the running mean and variances are the exponetial averages using the momentum value runnig_mean = momentum * running_mean + (1-momentum) * batch_mean If instead momentum<1 the cumulative average is computed running_mean = (nb/(nb+1) * running_mean + 1/(nb+1) * batch_mean

See more at [https://arxiv.org/pdf/1502.03167v3.pdf]

Definition at line 64 of file BatchNormLayer.h.

Public Types
using	BNormDescriptors_t = typename Architecture_t::BNormDescriptors_t

using	HelperDescriptor_t = typename Architecture_t::TensorDescriptor_t

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
	TBatchNormLayer (const TBatchNormLayer &)
	Copy Constructor.

	TBatchNormLayer (size_t batchSize, size_t inputDepth, size_t inputHeight, size_t inputWidth, const std::vector< size_t > &shape, int axis=-1, Scalar_t momentum=-1., Scalar_t epsilon=0.0001)
	Constructor.

	TBatchNormLayer (TBatchNormLayer< Architecture_t > *layer)
	Copy the dense layer provided as a pointer.

	~TBatchNormLayer ()
	Destructor.

virtual void	AddWeightsXMLTo (void *parent)
	Writes the information and the weights about the layer in an XML node.

void	Backward (Tensor_t &gradients_backward, const Tensor_t &activations_backward)
	Compute weight, bias and activation gradients.

void	Forward (Tensor_t &input, bool inTraining=true)
	Compute activation of the layer for the given input.

Matrix_t &	GetBatchMean ()

const Matrix_t &	GetBatchMean () const

Scalar_t	GetEpsilon () const

std::vector< Matrix_t >	GetExtraLayerParameters () const

Matrix_t &	GetIVariance ()

const Matrix_t &	GetIVariance () const

Scalar_t	GetMomentum () const

Matrix_t &	GetMuVector ()

const Matrix_t &	GetMuVector () const

Scalar_t	GetNormAxis () const

int &	GetNTrainedBatches ()

const int &	GetNTrainedBatches () const

Matrix_t &	GetReshapedData ()

const Matrix_t &	GetReshapedData () const

Matrix_t &	GetVariance ()

const Matrix_t &	GetVariance () const

Matrix_t &	GetVarVector ()

const Matrix_t &	GetVarVector () const

virtual void	Initialize ()
	Initialize the weights and biases according to the given initialization method.

void	Print () const
	Printing the layer info.

virtual void	ReadWeightsFromXML (void *parent)
	Read the information and the weights about the layer from XML node.

void	ResetTraining ()
	Reset some training flags after a loop on all batches Some layer (e.g.

void	SetExtraLayerParameters (const std::vector< Matrix_t > &params)

Public Member Functions inherited from TMVA::DNN::VGeneralLayer< Architecture_t >
	VGeneralLayer (const VGeneralLayer &)
	Copy Constructor.

	VGeneralLayer (size_t BatchSize, size_t InputDepth, size_t InputHeight, size_t InputWidth, size_t Depth, size_t Height, size_t Width, size_t WeightsNSlices, size_t WeightsNRows, size_t WeightsNCols, size_t BiasesNSlices, size_t BiasesNRows, size_t BiasesNCols, size_t OutputNSlices, size_t OutputNRows, size_t OutputNCols, EInitialization Init)
	Constructor.

	VGeneralLayer (size_t BatchSize, size_t InputDepth, size_t InputHeight, size_t InputWidth, size_t Depth, size_t Height, size_t Width, size_t WeightsNSlices, std::vector< size_t > WeightsNRows, std::vector< size_t > WeightsNCols, size_t BiasesNSlices, std::vector< size_t > BiasesNRows, std::vector< size_t > BiasesNCols, size_t OutputNSlices, size_t OutputNRows, size_t OutputNCols, EInitialization Init)
	General Constructor with different weights dimension.

	VGeneralLayer (VGeneralLayer< Architecture_t > *layer)
	Copy the layer provided as a pointer.

virtual	~VGeneralLayer ()
	Virtual Destructor.

void	CopyBiases (const std::vector< Matrix_t > &otherBiases)
	Copies the biases provided as an input.

template<typename Arch >
void	CopyParameters (const VGeneralLayer< Arch > &layer)
	Copy all trainable weight and biases from another equivalent layer but with different architecture The function can copy also extra parameters in addition to weights and biases if they are return by the function GetExtraLayerParameters.

void	CopyWeights (const std::vector< Matrix_t > &otherWeights)
	Copies the weights provided as an input.

Tensor_t &	GetActivationGradients ()

const Tensor_t &	GetActivationGradients () const

Matrix_t	GetActivationGradientsAt (size_t i)

const Matrix_t &	GetActivationGradientsAt (size_t i) const

size_t	GetBatchSize () const
	Getters.

std::vector< Matrix_t > &	GetBiases ()

const std::vector< Matrix_t > &	GetBiases () const

Matrix_t &	GetBiasesAt (size_t i)

const Matrix_t &	GetBiasesAt (size_t i) const

std::vector< Matrix_t > &	GetBiasGradients ()

const std::vector< Matrix_t > &	GetBiasGradients () const

Matrix_t &	GetBiasGradientsAt (size_t i)

const Matrix_t &	GetBiasGradientsAt (size_t i) const

size_t	GetDepth () const

size_t	GetHeight () const

EInitialization	GetInitialization () const

size_t	GetInputDepth () const

size_t	GetInputHeight () const

size_t	GetInputWidth () const

Tensor_t &	GetOutput ()

const Tensor_t &	GetOutput () const

Matrix_t	GetOutputAt (size_t i)

const Matrix_t &	GetOutputAt (size_t i) const

std::vector< Matrix_t > &	GetWeightGradients ()

const std::vector< Matrix_t > &	GetWeightGradients () const

Matrix_t &	GetWeightGradientsAt (size_t i)

const Matrix_t &	GetWeightGradientsAt (size_t i) const

std::vector< Matrix_t > &	GetWeights ()

const std::vector< Matrix_t > &	GetWeights () const

Matrix_t &	GetWeightsAt (size_t i)

const Matrix_t &	GetWeightsAt (size_t i) const

size_t	GetWidth () const

bool	IsTraining () const

void	ReadMatrixXML (void node, const char name, Matrix_t &matrix)

void	SetBatchSize (size_t batchSize)
	Setters.

void	SetDepth (size_t depth)

virtual void	SetDropoutProbability (Scalar_t)
	Set Dropout probability.

void	SetHeight (size_t height)

void	SetInputDepth (size_t inputDepth)

void	SetInputHeight (size_t inputHeight)

void	SetInputWidth (size_t inputWidth)

void	SetIsTraining (bool isTraining)

void	SetWidth (size_t width)

void	Update (const Scalar_t learningRate)
	Updates the weights and biases, given the learning rate.

void	UpdateBiases (const std::vector< Matrix_t > &biasGradients, const Scalar_t learningRate)
	Updates the biases, given the gradients and the learning rate.

void	UpdateBiasGradients (const std::vector< Matrix_t > &biasGradients, const Scalar_t learningRate)
	Updates the bias gradients, given some other weight gradients and learning rate.

void	UpdateWeightGradients (const std::vector< Matrix_t > &weightGradients, const Scalar_t learningRate)
	Updates the weight gradients, given some other weight gradients and learning rate.

void	UpdateWeights (const std::vector< Matrix_t > &weightGradients, const Scalar_t learningRate)
	Updates the weights, given the gradients and the learning rate,.

void	WriteMatrixToXML (void node, const char name, const Matrix_t &matrix)

void	WriteTensorToXML (void node, const char name, const std::vector< Matrix_t > &tensor)
	helper functions for XML

Static Protected Member Functions
static size_t	CalculateNormDim (int axis, size_t c, size_t h, size_t w)

Private Attributes
Tensor_t	fDerivatives
	First fDerivatives of the activations of this layer.

TDescriptors *	fDescriptors = nullptr

Scalar_t	fEpsilon

Matrix_t	fIVar

Scalar_t	fMomentum
	The weight decay.

Matrix_t	fMu

Matrix_t	fMu_Training

int	fNormAxis
	Normalization axis. For each element of this axis we will compute mean and stddev.

Tensor_t	fReshapedData

int	fTrainedBatches = 0

Matrix_t	fVar

Matrix_t	fVar_Training

Additional Inherited Members
Protected Attributes inherited from TMVA::DNN::VGeneralLayer< Architecture_t >
Tensor_t	fActivationGradients
	Gradients w.r.t. the activations of this layer.

size_t	fBatchSize
	Batch size used for training and evaluation.

std::vector< Matrix_t >	fBiases
	The biases associated to the layer.

std::vector< Matrix_t >	fBiasGradients
	Gradients w.r.t. the bias values of the layer.

size_t	fDepth
	The depth of the layer.

size_t	fHeight
	The height of the layer.

EInitialization	fInit
	The initialization method.

size_t	fInputDepth
	The depth of the previous layer or input.

size_t	fInputHeight
	The height of the previous layer or input.

size_t	fInputWidth
	The width of the previous layer or input.

bool	fIsTraining
	Flag indicating the mode.

Tensor_t	fOutput
	Activations of this layer.

std::vector< Matrix_t >	fWeightGradients
	Gradients w.r.t. the weights of the layer.

std::vector< Matrix_t >	fWeights
	The weights associated to the layer.

size_t	fWidth
	The width of this layer.

#include <TMVA/DNN/BatchNormLayer.h>

Inheritance diagram for TMVA::DNN::TBatchNormLayer< Architecture_t >:

[legend]

Member Typedef Documentation

◆ BNormDescriptors_t

template<typename Architecture_t >

using TMVA::DNN::TBatchNormLayer< Architecture_t >::BNormDescriptors_t = typename Architecture_t::BNormDescriptors_t

Definition at line 72 of file BatchNormLayer.h.

◆ HelperDescriptor_t

template<typename Architecture_t >

using TMVA::DNN::TBatchNormLayer< Architecture_t >::HelperDescriptor_t = typename Architecture_t::TensorDescriptor_t

Definition at line 71 of file BatchNormLayer.h.

◆ Matrix_t

template<typename Architecture_t >

using TMVA::DNN::TBatchNormLayer< Architecture_t >::Matrix_t = typename Architecture_t::Matrix_t

Definition at line 68 of file BatchNormLayer.h.

◆ Scalar_t

template<typename Architecture_t >

using TMVA::DNN::TBatchNormLayer< Architecture_t >::Scalar_t = typename Architecture_t::Scalar_t

Definition at line 67 of file BatchNormLayer.h.

◆ Tensor_t

template<typename Architecture_t >

using TMVA::DNN::TBatchNormLayer< Architecture_t >::Tensor_t = typename Architecture_t::Tensor_t

Definition at line 69 of file BatchNormLayer.h.

Constructor & Destructor Documentation

◆ TBatchNormLayer() [1/3]

template<typename Architecture_t >

TMVA::DNN::TBatchNormLayer< Architecture_t >::TBatchNormLayer	(	size_t	batchSize,
		size_t	inputDepth,
		size_t	inputHeight,
		size_t	inputWidth,
		const std::vector< size_t > &	shape,
		int	axis = `-1`,
		Scalar_t	momentum = `-1.`,
		Scalar_t	epsilon = `0.0001`
	)

Constructor.

Definition at line 219 of file BatchNormLayer.h.

◆ TBatchNormLayer() [2/3]

template<typename Architecture_t >

TMVA::DNN::TBatchNormLayer< Architecture_t >::TBatchNormLayer ( TBatchNormLayer< Architecture_t > * layer )

Copy the dense layer provided as a pointer.

Definition at line 242 of file BatchNormLayer.h.

◆ TBatchNormLayer() [3/3]

template<typename Architecture_t >

TMVA::DNN::TBatchNormLayer< Architecture_t >::TBatchNormLayer ( const TBatchNormLayer< Architecture_t > & layer )

Copy Constructor.

Definition at line 251 of file BatchNormLayer.h.

◆ ~TBatchNormLayer()

template<typename Architecture_t >

TMVA::DNN::TBatchNormLayer< Architecture_t >::~TBatchNormLayer

Destructor.

Definition at line 259 of file BatchNormLayer.h.

Member Function Documentation

◆ AddWeightsXMLTo()

template<typename Architecture_t >

void TMVA::DNN::TBatchNormLayer< Architecture_t >::AddWeightsXMLTo ( void * parent )

virtual

Writes the information and the weights about the layer in an XML node.

Implements TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 387 of file BatchNormLayer.h.

◆ Backward()

template<typename Architecture_t >

auto TMVA::DNN::TBatchNormLayer< Architecture_t >::Backward	(	Tensor_t &	gradients_backward,
		const Tensor_t &	activations_backward
	)

virtual

Compute weight, bias and activation gradients.

Uses the precomputed first partial derviatives of the activation function computed during forward propagation and modifies them. Must only be called directly a the corresponding call to Forward(...).

Implements TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 337 of file BatchNormLayer.h.

◆ CalculateNormDim()

template<typename Architecture_t >

static size_t TMVA::DNN::TBatchNormLayer< Architecture_t >::CalculateNormDim	(	int	axis,
		size_t	c,
		size_t	h,
		size_t	w
	)

inlinestaticprotected

Definition at line 199 of file BatchNormLayer.h.

◆ Forward()

template<typename Architecture_t >

auto TMVA::DNN::TBatchNormLayer< Architecture_t >::Forward	(	Tensor_t &	input,
		bool	inTraining = `true`
	)

virtual

Compute activation of the layer for the given input.

The input must be in 3D tensor form with the different matrices corresponding to different events in the batch. Computes activations as well as the first partial derivative of the activation function at those activations.

Implements TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 295 of file BatchNormLayer.h.

◆ GetBatchMean() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetBatchMean ( )

inline

Definition at line 149 of file BatchNormLayer.h.

◆ GetBatchMean() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetBatchMean ( ) const

inline

Definition at line 148 of file BatchNormLayer.h.

◆ GetEpsilon()

template<typename Architecture_t >

Scalar_t TMVA::DNN::TBatchNormLayer< Architecture_t >::GetEpsilon ( ) const

inline

Definition at line 177 of file BatchNormLayer.h.

◆ GetExtraLayerParameters()

template<typename Architecture_t >

std::vector< Matrix_t > TMVA::DNN::TBatchNormLayer< Architecture_t >::GetExtraLayerParameters ( ) const

inlinevirtual

Reimplemented from TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 185 of file BatchNormLayer.h.

◆ GetIVariance() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetIVariance ( )

inline

Definition at line 161 of file BatchNormLayer.h.

◆ GetIVariance() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetIVariance ( ) const

inline

Definition at line 160 of file BatchNormLayer.h.

◆ GetMomentum()

template<typename Architecture_t >

Scalar_t TMVA::DNN::TBatchNormLayer< Architecture_t >::GetMomentum ( ) const

inline

Definition at line 174 of file BatchNormLayer.h.

◆ GetMuVector() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetMuVector ( )

inline

Definition at line 165 of file BatchNormLayer.h.

◆ GetMuVector() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetMuVector ( ) const

inline

Definition at line 164 of file BatchNormLayer.h.

◆ GetNormAxis()

template<typename Architecture_t >

Scalar_t TMVA::DNN::TBatchNormLayer< Architecture_t >::GetNormAxis ( ) const

inline

Definition at line 180 of file BatchNormLayer.h.

◆ GetNTrainedBatches() [1/2]

template<typename Architecture_t >

int & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetNTrainedBatches ( )

inline

Definition at line 145 of file BatchNormLayer.h.

◆ GetNTrainedBatches() [2/2]

template<typename Architecture_t >

const int & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetNTrainedBatches ( ) const

inline

Definition at line 144 of file BatchNormLayer.h.

◆ GetReshapedData() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetReshapedData ( )

inline

Definition at line 183 of file BatchNormLayer.h.

◆ GetReshapedData() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetReshapedData ( ) const

inline

Definition at line 182 of file BatchNormLayer.h.

◆ GetVariance() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetVariance ( )

inline

Definition at line 157 of file BatchNormLayer.h.

◆ GetVariance() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetVariance ( ) const

inline

Definition at line 156 of file BatchNormLayer.h.

◆ GetVarVector() [1/2]

template<typename Architecture_t >

Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetVarVector ( )

inline

Definition at line 169 of file BatchNormLayer.h.

◆ GetVarVector() [2/2]

template<typename Architecture_t >

const Matrix_t & TMVA::DNN::TBatchNormLayer< Architecture_t >::GetVarVector ( ) const

inline

Definition at line 168 of file BatchNormLayer.h.

◆ Initialize()

template<typename Architecture_t >

auto TMVA::DNN::TBatchNormLayer< Architecture_t >::Initialize

virtual

Initialize the weights and biases according to the given initialization method.

Reimplemented from TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 269 of file BatchNormLayer.h.

◆ Print()

template<typename Architecture_t >

void TMVA::DNN::TBatchNormLayer< Architecture_t >::Print

virtual

Printing the layer info.

Implements TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 369 of file BatchNormLayer.h.

◆ ReadWeightsFromXML()

template<typename Architecture_t >

void TMVA::DNN::TBatchNormLayer< Architecture_t >::ReadWeightsFromXML ( void * parent )

virtual

Read the information and the weights about the layer from XML node.

Implements TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 412 of file BatchNormLayer.h.

◆ ResetTraining()

template<typename Architecture_t >

void TMVA::DNN::TBatchNormLayer< Architecture_t >::ResetTraining ( )

inlinevirtual

Reset some training flags after a loop on all batches Some layer (e.g.

batchnormalization) might need to implement the function in case some operations are needed after looping an all batches

Reimplemented from TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 129 of file BatchNormLayer.h.

◆ SetExtraLayerParameters()

template<typename Architecture_t >

void TMVA::DNN::TBatchNormLayer< Architecture_t >::SetExtraLayerParameters ( const std::vector< Matrix_t > & params )

inlinevirtual

Reimplemented from TMVA::DNN::VGeneralLayer< Architecture_t >.

Definition at line 192 of file BatchNormLayer.h.

Member Data Documentation

◆ fDerivatives

template<typename Architecture_t >

Tensor_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fDerivatives

private

First fDerivatives of the activations of this layer.

Definition at line 77 of file BatchNormLayer.h.

◆ fDescriptors

template<typename Architecture_t >

TDescriptors* TMVA::DNN::TBatchNormLayer< Architecture_t >::fDescriptors = nullptr

private

Definition at line 97 of file BatchNormLayer.h.

◆ fEpsilon

template<typename Architecture_t >

Scalar_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fEpsilon

private

Definition at line 82 of file BatchNormLayer.h.

◆ fIVar

template<typename Architecture_t >

Matrix_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fIVar

private

Definition at line 86 of file BatchNormLayer.h.

◆ fMomentum

template<typename Architecture_t >

Scalar_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fMomentum

private

The weight decay.

Definition at line 81 of file BatchNormLayer.h.

◆ fMu

template<typename Architecture_t >

Matrix_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fMu

private

Definition at line 84 of file BatchNormLayer.h.

◆ fMu_Training

template<typename Architecture_t >

Matrix_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fMu_Training

private

Definition at line 88 of file BatchNormLayer.h.

◆ fNormAxis

template<typename Architecture_t >

int TMVA::DNN::TBatchNormLayer< Architecture_t >::fNormAxis

private

Normalization axis. For each element of this axis we will compute mean and stddev.

Definition at line 79 of file BatchNormLayer.h.

◆ fReshapedData

template<typename Architecture_t >

Tensor_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fReshapedData

private

Definition at line 92 of file BatchNormLayer.h.

◆ fTrainedBatches

template<typename Architecture_t >

int TMVA::DNN::TBatchNormLayer< Architecture_t >::fTrainedBatches = 0

private

Definition at line 95 of file BatchNormLayer.h.

◆ fVar

template<typename Architecture_t >

Matrix_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fVar

private

Definition at line 85 of file BatchNormLayer.h.

◆ fVar_Training

template<typename Architecture_t >

Matrix_t TMVA::DNN::TBatchNormLayer< Architecture_t >::fVar_Training

private

Definition at line 89 of file BatchNormLayer.h.

tmva/tmva/inc/TMVA/DNN/BatchNormLayer.h

Public Types

Public Member Functions

Static Protected Member Functions

Private Attributes

Additional Inherited Members

Member Typedef Documentation

◆ BNormDescriptors_t

◆ HelperDescriptor_t

◆ Matrix_t

◆ Scalar_t

◆ Tensor_t

Constructor & Destructor Documentation

◆ TBatchNormLayer() [1/3]

◆ TBatchNormLayer() [2/3]

◆ TBatchNormLayer() [3/3]

◆ ~TBatchNormLayer()

Member Function Documentation

◆ AddWeightsXMLTo()

◆ Backward()

◆ CalculateNormDim()

◆ Forward()

◆ GetBatchMean() [1/2]

◆ GetBatchMean() [2/2]

◆ GetEpsilon()

◆ GetExtraLayerParameters()

◆ GetIVariance() [1/2]

◆ GetIVariance() [2/2]

◆ GetMomentum()

◆ GetMuVector() [1/2]

◆ GetMuVector() [2/2]

◆ GetNormAxis()

◆ GetNTrainedBatches() [1/2]

◆ GetNTrainedBatches() [2/2]

◆ GetReshapedData() [1/2]

◆ GetReshapedData() [2/2]

◆ GetVariance() [1/2]

◆ GetVariance() [2/2]

◆ GetVarVector() [1/2]

◆ GetVarVector() [2/2]

◆ Initialize()

◆ Print()

◆ ReadWeightsFromXML()

◆ ResetTraining()

◆ SetExtraLayerParameters()

Member Data Documentation

◆ fDerivatives

◆ fDescriptors

◆ fEpsilon

◆ fIVar

◆ fMomentum

◆ fMu

◆ fMu_Training

◆ fNormAxis

◆ fReshapedData

◆ fTrainedBatches

◆ fVar

◆ fVar_Training