Logo ROOT   6.14/05
Reference Guide
TMVA::DNN::CNN::TConvLayer< Architecture_t > Member List

This is the complete list of members for TMVA::DNN::CNN::TConvLayer< Architecture_t >, including all inherited members.

AddWeightsXMLTo(void *parent)TMVA::DNN::CNN::TConvLayer< Architecture_t >virtual
Backward(std::vector< Matrix_t > &gradients_backward, const std::vector< Matrix_t > &activations_backward, std::vector< Matrix_t > &inp1, std::vector< Matrix_t > &inp2)TMVA::DNN::CNN::TConvLayer< Architecture_t >virtual
CopyBiases(const std::vector< Matrix_t > &otherBiases)TMVA::DNN::VGeneralLayer< Architecture_t >
CopyWeights(const std::vector< Matrix_t > &otherWeights)TMVA::DNN::VGeneralLayer< Architecture_t >
fActivationGradientsTMVA::DNN::VGeneralLayer< Architecture_t >protected
fBackwardIndicesTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fBatchSizeTMVA::DNN::VGeneralLayer< Architecture_t >protected
fBiasesTMVA::DNN::VGeneralLayer< Architecture_t >protected
fBiasGradientsTMVA::DNN::VGeneralLayer< Architecture_t >protected
fDepthTMVA::DNN::VGeneralLayer< Architecture_t >protected
fDerivativesTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fDropoutProbabilityTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fFTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fFilterDepthTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fFilterHeightTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fFilterWidthTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fForwardIndicesTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fHeightTMVA::DNN::VGeneralLayer< Architecture_t >protected
fInitTMVA::DNN::VGeneralLayer< Architecture_t >protected
fInputDepthTMVA::DNN::VGeneralLayer< Architecture_t >protected
fInputHeightTMVA::DNN::VGeneralLayer< Architecture_t >protected
fInputWidthTMVA::DNN::VGeneralLayer< Architecture_t >protected
fIsTrainingTMVA::DNN::VGeneralLayer< Architecture_t >protected
fNLocalViewPixelsTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fNLocalViewsTMVA::DNN::CNN::TConvLayer< Architecture_t >private
Forward(std::vector< Matrix_t > &input, bool applyDropout=false)TMVA::DNN::CNN::TConvLayer< Architecture_t >virtual
fOutputTMVA::DNN::VGeneralLayer< Architecture_t >protected
fPaddingHeightTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fPaddingWidthTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fRegTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fStrideColsTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fStrideRowsTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fWeightDecayTMVA::DNN::CNN::TConvLayer< Architecture_t >private
fWeightGradientsTMVA::DNN::VGeneralLayer< Architecture_t >protected
fWeightsTMVA::DNN::VGeneralLayer< Architecture_t >protected
fWidthTMVA::DNN::VGeneralLayer< Architecture_t >protected
GetActivationFunction() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetActivationGradients() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetActivationGradients()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetActivationGradientsAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetActivationGradientsAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBatchSize() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiases() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiases()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasesAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasesAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasGradients() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasGradients()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasGradientsAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetBiasGradientsAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetDepth() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetDerivatives() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetDerivatives()TMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetDerivativesAt(size_t i)TMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetDerivativesAt(size_t i) constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetDropoutProbability() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetFilterDepth() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetFilterHeight() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetFilterWidth() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetHeight() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetInitialization() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetInputDepth() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetInputHeight() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetInputWidth() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetNLocalViewPixels() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetNLocalViews() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetOutput() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetOutput()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetOutputAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetOutputAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetPaddingHeight() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetPaddingWidth() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetRegularization() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetStrideCols() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetStrideRows() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetWeightDecay() constTMVA::DNN::CNN::TConvLayer< Architecture_t >inline
GetWeightGradients() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeightGradients()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeightGradientsAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeightGradientsAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeights() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeights()TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeightsAt(size_t i) constTMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWeightsAt(size_t i)TMVA::DNN::VGeneralLayer< Architecture_t >inline
GetWidth() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
Initialize()TMVA::DNN::VGeneralLayer< Architecture_t >
IsTraining() constTMVA::DNN::VGeneralLayer< Architecture_t >inline
Matrix_t typedefTMVA::DNN::CNN::TConvLayer< Architecture_t >
Print() constTMVA::DNN::CNN::TConvLayer< Architecture_t >virtual
ReadMatrixXML(void *node, const char *name, Matrix_t &matrix)TMVA::DNN::VGeneralLayer< Architecture_t >
ReadWeightsFromXML(void *parent)TMVA::DNN::CNN::TConvLayer< Architecture_t >virtual
Scalar_t typedefTMVA::DNN::CNN::TConvLayer< Architecture_t >
SetBatchSize(size_t batchSize)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetDepth(size_t depth)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetHeight(size_t height)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetInputDepth(size_t inputDepth)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetInputHeight(size_t inputHeight)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetInputWidth(size_t inputWidth)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetIsTraining(bool isTraining)TMVA::DNN::VGeneralLayer< Architecture_t >inline
SetWidth(size_t width)TMVA::DNN::VGeneralLayer< Architecture_t >inline
TConvLayer(size_t BatchSize, size_t InputDepth, size_t InputHeight, size_t InputWidth, size_t Depth, size_t Height, size_t Width, size_t WeightsNRows, size_t WeightsNCols, size_t BiasesNRows, size_t BiasesNCols, size_t OutputNSlices, size_t OutputNRows, size_t OutputNCols, EInitialization Init, size_t FilterDepth, size_t FilterHeight, size_t FilterWidth, size_t StrideRows, size_t StrideCols, size_t PaddingHeight, size_t PaddingWidth, Scalar_t DropoutProbability, EActivationFunction f, ERegularization Reg, Scalar_t WeightDecay)TMVA::DNN::CNN::TConvLayer< Architecture_t >
TConvLayer(TConvLayer< Architecture_t > *layer)TMVA::DNN::CNN::TConvLayer< Architecture_t >
TConvLayer(const TConvLayer &)TMVA::DNN::CNN::TConvLayer< Architecture_t >
Update(const Scalar_t learningRate)TMVA::DNN::VGeneralLayer< Architecture_t >
UpdateBiases(const std::vector< Matrix_t > &biasGradients, const Scalar_t learningRate)TMVA::DNN::VGeneralLayer< Architecture_t >
UpdateBiasGradients(const std::vector< Matrix_t > &biasGradients, const Scalar_t learningRate)TMVA::DNN::VGeneralLayer< Architecture_t >
UpdateWeightGradients(const std::vector< Matrix_t > &weightGradients, const Scalar_t learningRate)TMVA::DNN::VGeneralLayer< Architecture_t >
UpdateWeights(const std::vector< Matrix_t > &weightGradients, const Scalar_t learningRate)TMVA::DNN::VGeneralLayer< Architecture_t >
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)TMVA::DNN::VGeneralLayer< Architecture_t >
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)TMVA::DNN::VGeneralLayer< Architecture_t >
VGeneralLayer(VGeneralLayer< Architecture_t > *layer)TMVA::DNN::VGeneralLayer< Architecture_t >
VGeneralLayer(const VGeneralLayer &)TMVA::DNN::VGeneralLayer< Architecture_t >
WriteMatrixToXML(void *node, const char *name, const Matrix_t &matrix)TMVA::DNN::VGeneralLayer< Architecture_t >
WriteTensorToXML(void *node, const char *name, const std::vector< Matrix_t > &tensor)TMVA::DNN::VGeneralLayer< Architecture_t >
~TConvLayer()TMVA::DNN::CNN::TConvLayer< Architecture_t >
~VGeneralLayer()TMVA::DNN::VGeneralLayer< Architecture_t >virtual