#include <acts/blob/sPHENIX/Plugins/Onnx/include/Acts/Plugins/Onnx/OnnxRuntimeBase.hpp>

Inheritance diagram for Acts::OnnxRuntimeBase:

Collaboration diagram for Acts::OnnxRuntimeBase:

Public Member Functions
	OnnxRuntimeBase ()=default
	Default constructor.

	OnnxRuntimeBase (Ort::Env &env, const char *modelPath)
	Parametrized constructor.

	~OnnxRuntimeBase ()=default
	Default destructor.

std::vector< float >	runONNXInference (std::vector< float > &inputTensorValues) const
	Run the ONNX inference function.

std::vector< std::vector< float > >	runONNXInference (NetworkBatchInput &inputTensorValues) const
	Run the ONNX inference function for a batch of input.

std::vector< std::vector < std::vector< float > > >	runONNXInferenceMultiOutput (NetworkBatchInput &inputTensorValues) const
	Run the multi-output ONNX inference function for a batch of input.

Private Attributes
std::unique_ptr< Ort::Session >	m_session
	ONNX runtime session / model properties.

std::vector < Ort::AllocatedStringPtr >	m_inputNodeNamesAllocated

std::vector< const char * >	m_inputNodeNames

std::vector< int64_t >	m_inputNodeDims

std::vector < Ort::AllocatedStringPtr >	m_outputNodeNamesAllocated

std::vector< const char * >	m_outputNodeNames

std::vector< std::vector < int64_t > >	m_outputNodeDims

Detailed Description

Definition at line 22 of file OnnxRuntimeBase.hpp.

View newest version in sPHENIX GitHub at line 22 of file OnnxRuntimeBase.hpp

Constructor & Destructor Documentation

Acts::OnnxRuntimeBase::OnnxRuntimeBase ( )

default

Default constructor.

Acts::OnnxRuntimeBase::OnnxRuntimeBase	(	Ort::Env &	env,
		const char *	modelPath
	)

Parametrized constructor.

Parameters

env	the ONNX runtime environment
modelPath	the path to the ML model in *.onnx format

Definition at line 15 of file OnnxRuntimeBase.cpp.

View newest version in sPHENIX GitHub at line 15 of file OnnxRuntimeBase.cpp

References conf::env, i, m_inputNodeDims, m_inputNodeNames, m_inputNodeNamesAllocated, m_outputNodeDims, m_outputNodeNames, m_outputNodeNamesAllocated, and m_session.

Acts::OnnxRuntimeBase::~OnnxRuntimeBase ( )

default

Default destructor.

Member Function Documentation

std::vector< float > Acts::OnnxRuntimeBase::runONNXInference ( std::vector< float > & inputTensorValues ) const

Run the ONNX inference function.

Parameters

inputTensorValues The input feature values used for prediction

Returns: The output (predicted) values

Definition at line 57 of file OnnxRuntimeBase.cpp.

View newest version in sPHENIX GitHub at line 57 of file OnnxRuntimeBase.cpp

References i.

Referenced by Acts::AmbiguityTrackClassifier::inferScores(), and Acts::MLTrackClassifier::predictTrackLabel().

Here is the caller graph for this function:

std::vector< std::vector< float > > Acts::OnnxRuntimeBase::runONNXInference ( Acts::NetworkBatchInput & inputTensorValues ) const

Run the ONNX inference function for a batch of input.

Parameters

inputTensorValues Vector of the input feature values of all the inputs used for prediction

Returns: The vector of output (predicted) values

Definition at line 69 of file OnnxRuntimeBase.cpp.

View newest version in sPHENIX GitHub at line 69 of file OnnxRuntimeBase.cpp

std::vector< std::vector< std::vector< float > > > Acts::OnnxRuntimeBase::runONNXInferenceMultiOutput ( NetworkBatchInput & inputTensorValues ) const

Run the multi-output ONNX inference function for a batch of input.

Parameters

inputTensorValues Vector of the input feature values of all the inputs used for prediction