TMVA::Experimental::RSofieReader Class Reference

TMVA::RSofieReader class for reading external Machine Learning models in ONNX files, Keras .h5 or .keras files or PyTorch .pt files and performing the inference using SOFIE It is reccomended to use ONNX if possible since there is a larger support for model operators.

Definition at line 45 of file RSofieReader.hxx.

Classes
struct	CustomOperatorData

Public Member Functions
	RSofieReader ()
	Dummy constructor which needs model loading afterwards.
	RSofieReader (const std::string &path, std::vector< std::vector< size_t > > inputShapes={}, int verbose=0)
	Create TMVA model from ONNX file print level can be 0 (minimal) 1 with info , 2 with all ONNX parsing info.
void	AddCustomOperator (const std::string &opName, const std::string &inputNames, const std::string &outputNames, const std::string &outputShapes, const std::string &fileName)
std::vector< float >	Compute (const std::vector< float > &x)
RTensor< float >	Compute (RTensor< float > &x)
	Compute model prediction on input RTensor The shape of the input tensor should be {nevents, nfeatures} and the return shape will be {nevents, noutputs} support for now only a single input.
template<typename... T>
std::vector< float >	Compute (T... x)
	Compute model prediction on vector.
std::vector< float >	DoCompute (const std::vector< float > &x1)
std::vector< float >	DoCompute (const std::vector< float > &x1, const std::vector< float > &x2)
std::vector< float >	DoCompute (const std::vector< float > &x1, const std::vector< float > &x2, const std::vector< float > &x3)
void	Load (const std::string &path, std::vector< std::vector< size_t > > inputShapes={}, int verbose=0)

Private Attributes
std::vector< CustomOperatorData >	fCustomOperators
void *	fFuncPtr = nullptr
bool	fInitialized = false
int	fNInputs = 0
void *	fSessionPtr = nullptr

#include <TMVA/RSofieReader.hxx>

Constructor & Destructor Documentation

RSofieReader() [1/2]

TMVA::Experimental::RSofieReader::RSofieReader ( )

inline

Dummy constructor which needs model loading afterwards.

Definition at line 50 of file RSofieReader.hxx.

RSofieReader() [2/2]

TMVA::Experimental::RSofieReader::RSofieReader ( const std::string & path, std::vector< std::vector< size_t > > inputShapes = {}, int verbose = 0 )

inline

Create TMVA model from ONNX file print level can be 0 (minimal) 1 with info , 2 with all ONNX parsing info.

Definition at line 53 of file RSofieReader.hxx.

Member Function Documentation

AddCustomOperator()

void TMVA::Experimental::RSofieReader::AddCustomOperator ( const std::string & opName, const std::string & inputNames, const std::string & outputNames, const std::string & outputShapes, const std::string & fileName )

inline

Definition at line 304 of file RSofieReader.hxx.

Compute() [1/3]

std::vector< float > TMVA::Experimental::RSofieReader::Compute ( const std::vector< float > & x )

inline

Definition at line 351 of file RSofieReader.hxx.

Compute() [2/3]

RTensor< float > TMVA::Experimental::RSofieReader::Compute ( RTensor< float > & x )

inline

Compute model prediction on input RTensor The shape of the input tensor should be {nevents, nfeatures} and the return shape will be {nevents, noutputs} support for now only a single input.

Definition at line 366 of file RSofieReader.hxx.

Compute() [3/3]

template<typename... T>

std::vector< float > TMVA::Experimental::RSofieReader::Compute ( T... x )

inline

Compute model prediction on vector.

Definition at line 338 of file RSofieReader.hxx.

DoCompute() [1/3]

std::vector< float > TMVA::Experimental::RSofieReader::DoCompute ( const std::vector< float > & x1 )

inline

Definition at line 311 of file RSofieReader.hxx.

DoCompute() [2/3]

std::vector< float > TMVA::Experimental::RSofieReader::DoCompute ( const std::vector< float > & x1, const std::vector< float > & x2 )

inline

Definition at line 319 of file RSofieReader.hxx.

DoCompute() [3/3]

std::vector< float > TMVA::Experimental::RSofieReader::DoCompute ( const std::vector< float > & x1, const std::vector< float > & x2, const std::vector< float > & x3 )

inline

Definition at line 327 of file RSofieReader.hxx.

Load()

void TMVA::Experimental::RSofieReader::Load ( const std::string & path, std::vector< std::vector< size_t > > inputShapes = {}, int verbose = 0 )

inline

Definition at line 58 of file RSofieReader.hxx.

Member Data Documentation

fCustomOperators

std::vector<CustomOperatorData> TMVA::Experimental::RSofieReader::fCustomOperators

private

Definition at line 402 of file RSofieReader.hxx.

fFuncPtr

void* TMVA::Experimental::RSofieReader::fFuncPtr = nullptr

private

Definition at line 392 of file RSofieReader.hxx.

fInitialized

bool TMVA::Experimental::RSofieReader::fInitialized = false

private

Definition at line 389 of file RSofieReader.hxx.

fNInputs

int TMVA::Experimental::RSofieReader::fNInputs = 0

private

Definition at line 390 of file RSofieReader.hxx.

fSessionPtr

void* TMVA::Experimental::RSofieReader::fSessionPtr = nullptr

private

Definition at line 391 of file RSofieReader.hxx.

Libraries for TMVA::Experimental::RSofieReader:

---

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

• tmva/tmva/inc/TMVA/RSofieReader.hxx