Logo ROOT   6.16/01
Reference Guide
List of all members | Public Types | Public Member Functions | Private Attributes | List of all members
TMVA::DNN::TTensorBatch< Architecture_t > Class Template Reference

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

TTensorBatch.

Class representing training batches consisting of a vector of matrices as input data and a matrix of output data. The input and output data can be accessed using the GetInput() and GetOutput() member functions.

Template Parameters
Architecture_tThe underlying architecture.

Definition at line 57 of file TensorDataLoader.h.

Public Types

using Matrix_t = typename Architecture_t::Matrix_t
 

Public Member Functions

 TTensorBatch (const TTensorBatch &)=default
 
 TTensorBatch (std::vector< Matrix_t > &, Matrix_t &, Matrix_t &)
 
 TTensorBatch (TTensorBatch &&)=default
 
std::vector< Matrix_t > & GetInput ()
 Return the tensor representing the input data. More...
 
Matrix_tGetOutput ()
 Return the matrix representing the output data. More...
 
Matrix_tGetWeights ()
 Return the matrix holding the event weights. More...
 
TTensorBatchoperator= (const TTensorBatch &)=default
 
TTensorBatchoperator= (TTensorBatch &&)=default
 

Private Attributes

std::vector< Matrix_tfInputTensor
 The input tensor batch, one matrix one input. More...
 
Matrix_t fOutputMatrix
 The output matrix representing the ground truth. More...
 
Matrix_t fWeightMatrix
 

#include <TMVA/DNN/TensorDataLoader.h>

Member Typedef Documentation

◆ Matrix_t

template<typename Architecture_t >
using TMVA::DNN::TTensorBatch< Architecture_t >::Matrix_t = typename Architecture_t::Matrix_t

Definition at line 59 of file TensorDataLoader.h.

Constructor & Destructor Documentation

◆ TTensorBatch() [1/3]

template<typename Architecture_t >
TMVA::DNN::TTensorBatch< Architecture_t >::TTensorBatch ( std::vector< Matrix_t > &  inputTensor,
Matrix_t outputMatrix,
Matrix_t weightMatrix 
)

Definition at line 192 of file TensorDataLoader.h.

◆ TTensorBatch() [2/3]

template<typename Architecture_t >
TMVA::DNN::TTensorBatch< Architecture_t >::TTensorBatch ( const TTensorBatch< Architecture_t > &  )
default

◆ TTensorBatch() [3/3]

template<typename Architecture_t >
TMVA::DNN::TTensorBatch< Architecture_t >::TTensorBatch ( TTensorBatch< Architecture_t > &&  )
default

Member Function Documentation

◆ GetInput()

template<typename Architecture_t >
std::vector< Matrix_t > & TMVA::DNN::TTensorBatch< Architecture_t >::GetInput ( )
inline

Return the tensor representing the input data.

Definition at line 74 of file TensorDataLoader.h.

◆ GetOutput()

template<typename Architecture_t >
Matrix_t & TMVA::DNN::TTensorBatch< Architecture_t >::GetOutput ( )
inline

Return the matrix representing the output data.

Definition at line 76 of file TensorDataLoader.h.

◆ GetWeights()

template<typename Architecture_t >
Matrix_t & TMVA::DNN::TTensorBatch< Architecture_t >::GetWeights ( )
inline

Return the matrix holding the event weights.

Definition at line 78 of file TensorDataLoader.h.

◆ operator=() [1/2]

template<typename Architecture_t >
TTensorBatch & TMVA::DNN::TTensorBatch< Architecture_t >::operator= ( const TTensorBatch< Architecture_t > &  )
default

◆ operator=() [2/2]

template<typename Architecture_t >
TTensorBatch & TMVA::DNN::TTensorBatch< Architecture_t >::operator= ( TTensorBatch< Architecture_t > &&  )
default

Member Data Documentation

◆ fInputTensor

template<typename Architecture_t >
std::vector<Matrix_t> TMVA::DNN::TTensorBatch< Architecture_t >::fInputTensor
private

The input tensor batch, one matrix one input.

Definition at line 62 of file TensorDataLoader.h.

◆ fOutputMatrix

template<typename Architecture_t >
Matrix_t TMVA::DNN::TTensorBatch< Architecture_t >::fOutputMatrix
private

The output matrix representing the ground truth.

Definition at line 63 of file TensorDataLoader.h.

◆ fWeightMatrix

template<typename Architecture_t >
Matrix_t TMVA::DNN::TTensorBatch< Architecture_t >::fWeightMatrix
private

Definition at line 64 of file TensorDataLoader.h.


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