SamplePlugin Class Reference

The SamplePlugin class implements samplePlugin. More...

Collaboration diagram for SamplePlugin:

Public Member Functions
	SamplePlugin (const samplesCommon::CaffeSampleParams &params)
	~SamplePlugin ()
bool	build ()
	Builds the network engine. More...
bool	infer ()
	Runs the TensorRT inference engine for this sample. More...
bool	teardown ()
	Used to clean up any state created in the sample class. More...

Private Types
template<typename T >
using	SampleUniquePtr = std::unique_ptr< T, samplesCommon::InferDeleter >

Private Member Functions
void	constructNetwork (SampleUniquePtr< nvinfer1::IBuilder > &builder, SampleUniquePtr< nvcaffeparser1::ICaffeParser > &parser, SampleUniquePtr< nvinfer1::INetworkDefinition > &network)
	Uses a Caffe parser to create the MNIST Network and marks the output layers. More...
bool	processInput (const samplesCommon::BufferManager &buffers, const std::string &inputTensorName, int inputFileIdx) const
	Reads the input and mean data, preprocesses, and stores the result in a managed buffer. More...
bool	verifyOutput (const samplesCommon::BufferManager &buffers, const std::string &outputTensorName, int groundTruthDigit) const
	Verifies that the output is correct and prints it. More...

Private Attributes
std::shared_ptr< nvinfer1::ICudaEngine >	mEngine {nullptr}
	The TensorRT engine used to run the network. More...
samplesCommon::CaffeSampleParams	mParams
	The parameters for the sample. More...
SampleUniquePtr< nvcaffeparser1::IBinaryProtoBlob >	mMeanBlob
	The mean blob, which need to keep around until build time. More...
nvinfer1::Dims	mInputDims
	The dimensions of the input to the network. More...
PluginFactory	runtimePluginFactory

Detailed Description

The SamplePlugin class implements samplePlugin.

It creates the network using a trained Caffe MNIST classification model, and replaces the final FC layer with a custom plugin layer.

Member Typedef Documentation

SampleUniquePtr

template<typename T >

using SamplePlugin::SampleUniquePtr = std::unique_ptr<T, samplesCommon::InferDeleter>

private

Constructor & Destructor Documentation

SamplePlugin()

SamplePlugin::SamplePlugin ( const samplesCommon::CaffeSampleParams &  params )

inline

~SamplePlugin()

SamplePlugin::~SamplePlugin ( )

inline

Member Function Documentation

build()

bool SamplePlugin::build

(

)

Builds the network engine.

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

This function creates the MNIST network by parsing the caffe model and builds the engine with a custom FC plugin layer

Returns

Returns true if the engine was created successfully and false otherwise

Here is the call graph for this function:

infer()

bool SamplePlugin::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, executes the engine, and verifies the output.

Here is the call graph for this function:

teardown()

bool SamplePlugin::teardown

(

)

Used to clean up any state created in the sample class.

Clean up the libprotobuf files as the parsing is complete

Note

It is not safe to use any other part of the protocol buffers library after ShutdownProtobufLibrary() has been called.

Here is the call graph for this function:

constructNetwork()

void SamplePlugin::constructNetwork ( SampleUniquePtr< nvinfer1::IBuilder > &  builder, SampleUniquePtr< nvcaffeparser1::ICaffeParser > &  parser, SampleUniquePtr< nvinfer1::INetworkDefinition > &  network  )

private

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

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

Parameters

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

Here is the call graph for this function:

Here is the caller graph for this function:

processInput()

bool SamplePlugin::processInput ( const samplesCommon::BufferManager &  buffers, const std::string &  inputTensorName, int  inputFileIdx  ) const

private

Reads the input and mean data, preprocesses, and stores the result in a managed buffer.

Here is the call graph for this function:

Here is the caller graph for this function:

verifyOutput()

bool SamplePlugin::verifyOutput ( const samplesCommon::BufferManager &  buffers, const std::string &  outputTensorName, int  groundTruthDigit  ) const

private

Verifies that the output is correct and prints it.

Here is the call graph for this function:

Here is the caller graph for this function:

Member Data Documentation

mEngine

std::shared_ptr<nvinfer1::ICudaEngine> SamplePlugin::mEngine {nullptr}

private

The TensorRT engine used to run the network.

mParams

samplesCommon::CaffeSampleParams SamplePlugin::mParams

private

The parameters for the sample.

mMeanBlob

SampleUniquePtr<nvcaffeparser1::IBinaryProtoBlob> SamplePlugin::mMeanBlob

private

The mean blob, which need to keep around until build time.

mInputDims

nvinfer1::Dims SamplePlugin::mInputDims

private

The dimensions of the input to the network.

runtimePluginFactory

PluginFactory SamplePlugin::runtimePluginFactory

private

---

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

• samplePlugin.cpp