TensorRTEngine Class Reference

The TensorRTEngine class implements a generic TensorRT model. More...

#include <trt_engine_syh.hpp>

Collaboration diagram for TensorRTEngine:

Public Member Functions
	TensorRTEngine (const samplesCommon::OnnxSampleParams &params)
bool	build ()
	Function builds the network engine.
bool	infer ()
	Runs the TensorRT inference engine for this sample.

Private Member Functions
bool	constructNetwork (SampleUniquePtr< nvinfer1::IBuilder > &builder, SampleUniquePtr< nvinfer1::INetworkDefinition > &network, SampleUniquePtr< nvinfer1::IBuilderConfig > &config, SampleUniquePtr< nvonnxparser::IParser > &parser)
	Parses an ONNX model for MNIST and creates a TensorRT network.
bool	processInput (float *filedata, const samplesCommon::BufferManager &buffers)
	Reads the input and stores the result in a managed buffer.

Private Attributes
samplesCommon::OnnxSampleParams	mParams
	The parameters for the sample.
nvinfer1::Dims	mInputDims
	The dimensions of the input to the network.
nvinfer1::Dims	mOutputDims
	The dimensions of the output to the network.
int	mNumber {0}
	The number to classify.
std::shared_ptr< nvinfer1::IRuntime >	mRuntime
	The TensorRT runtime used to deserialize the engine.
std::shared_ptr< nvinfer1::ICudaEngine >	mEngine
	The TensorRT engine used to run the network.

Detailed Description

The TensorRTEngine class implements a generic TensorRT model.

It creates the network using an ONNX model

Definition at line 54 of file trt_engine_syh.hpp.

Constructor & Destructor Documentation

TensorRTEngine()

TensorRTEngine::TensorRTEngine ( const samplesCommon::OnnxSampleParams &  params )

inline

Definition at line 57 of file trt_engine_syh.hpp.

Member Function Documentation

build()

bool TensorRTEngine::build

(

)

Function builds the network engine.

Creates the network, configures the builder and creates the network engine.

This function creates the Onnx MNIST network by parsing the Onnx model and builds the engine that will be used to run MNIST (mEngine)

Returns

true if the engine was created successfully and false otherwise

Definition at line 101 of file trt_engine_syh.hpp.

Referenced by main().

constructNetwork()

bool TensorRTEngine::constructNetwork ( SampleUniquePtr< nvinfer1::IBuilder > &  builder, SampleUniquePtr< nvinfer1::INetworkDefinition > &  network, SampleUniquePtr< nvinfer1::IBuilderConfig > &  config, SampleUniquePtr< nvonnxparser::IParser > &  parser  )

private

Parses an ONNX model for MNIST and creates a TensorRT network.

Uses a ONNX parser to create the Onnx MNIST Network and marks the output layers.

Parameters

network	Pointer to the network that will be populated with the Onnx MNIST network
builder	Pointer to the engine builder

Definition at line 179 of file trt_engine_syh.hpp.

Referenced by build().

infer()

bool TensorRTEngine::infer

(

)

Runs the TensorRT inference engine for this sample.

This function is the main execution function of the sample. It allocates the buffer, sets inputs and executes the engine.

Definition at line 215 of file trt_engine_syh.hpp.

Referenced by main().

processInput()

bool TensorRTEngine::processInput ( float *  filedata, const samplesCommon::BufferManager &  buffers  )

private

Reads the input and stores the result in a managed buffer.

Definition at line 263 of file trt_engine_syh.hpp.

Referenced by infer().

Member Data Documentation

mEngine

std::shared_ptr<nvinfer1::ICudaEngine> TensorRTEngine::mEngine

private

The TensorRT engine used to run the network.

Definition at line 77 of file trt_engine_syh.hpp.

Referenced by build(), and infer().

mInputDims

nvinfer1::Dims TensorRTEngine::mInputDims

private

The dimensions of the input to the network.

Definition at line 72 of file trt_engine_syh.hpp.

Referenced by build(), and processInput().

mNumber

int TensorRTEngine::mNumber {0}

private

The number to classify.

Definition at line 74 of file trt_engine_syh.hpp.

mOutputDims

nvinfer1::Dims TensorRTEngine::mOutputDims

private

The dimensions of the output to the network.

Definition at line 73 of file trt_engine_syh.hpp.

Referenced by build().

mParams

samplesCommon::OnnxSampleParams TensorRTEngine::mParams

private

The parameters for the sample.

Definition at line 70 of file trt_engine_syh.hpp.

Referenced by constructNetwork(), infer(), and processInput().

mRuntime

std::shared_ptr<nvinfer1::IRuntime> TensorRTEngine::mRuntime

private

The TensorRT runtime used to deserialize the engine.

Definition at line 76 of file trt_engine_syh.hpp.

Referenced by build().

---

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

• apps/nnReconstructor/OLD/trt_engine_syh.hpp