SampleReformatFreeIO Class Reference

The SampleReformatFreeIO class implements the reformat free I/O sample. More...

Collaboration diagram for SampleReformatFreeIO:

Public Member Functions
	SampleReformatFreeIO (const samplesCommon::CaffeSampleParams &params)
bool	build (int dataWidth)
	Builds the network engine. More...
bool	infer (SampleBuffer &inputBuf, SampleBuffer &outputBuf)
	Runs the TensorRT inference engine for this sample. More...
bool	teardown ()
	Used to clean up any state created in the sample class. More...
bool	reference ()
	Used to run CPU reference and get result. More...
void	compareResult ()
	Used to compare the CPU reference with the TRT result. More...
bool	readDigits (SampleBuffer &buffer, int groundTruthDigit)
	Reads the digit map from the file. More...
template<typename T >
bool	verifyOutput (SampleBuffer &outputBuf, int groundTruthDigit) const
	Verifies that the output is correct and prints it. More...

Public Attributes
samplesCommon::CaffeSampleParams	mParams
nvinfer1::Dims	mInputDims
	The dimensions of the input to the network. More...
nvinfer1::Dims	mOutputDims
	The dimensions of the output to the network. More...
TensorFormat	mTensorFormat {TensorFormat::kLINEAR}
SampleUniquePtr< nvcaffeparser1::IBinaryProtoBlob >	mMeanBlob
int	mDigit

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

Private Member Functions
void	constructNetwork (SampleUniquePtr< nvcaffeparser1::ICaffeParser > &parser, SampleUniquePtr< nvinfer1::INetworkDefinition > &network)
	uses a Caffe parser to create the single layer Network and marks the output layers More...

Private Attributes
std::shared_ptr< nvinfer1::ICudaEngine >	mEngine {nullptr}
	The TensorRT engine used to run the network. More...

Detailed Description

The SampleReformatFreeIO class implements the reformat free I/O sample.

It creates the network using a single conv layer

Member Typedef Documentation

SampleUniquePtr

template<typename T >

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

private

Constructor & Destructor Documentation

SampleReformatFreeIO()

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

inline

Member Function Documentation

build()

bool SampleReformatFreeIO::build

(

int

dataWidth

)

Builds the network engine.

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

This function creates the single layer network by manual insertion and builds the engine

Returns

Returns true if the engine was created successfully and false otherwise

Here is the call graph for this function:

infer()

bool SampleReformatFreeIO::infer	(	SampleBuffer &	inputBuf,
		SampleBuffer &	outputBuf
	)

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 SampleReformatFreeIO::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:

reference()

bool SampleReformatFreeIO::reference

(

)

Used to run CPU reference and get result.

compareResult()

void SampleReformatFreeIO::compareResult

(

)

Used to compare the CPU reference with the TRT result.

readDigits()

bool SampleReformatFreeIO::readDigits	(	SampleBuffer &	buffer,
		int	groundTruthDigit
	)

Reads the digit map from the file.

Reads the digit map from file.

verifyOutput()

template<typename T >

bool SampleReformatFreeIO::verifyOutput	(	SampleBuffer &	outputBuf,
		int	groundTruthDigit
	)		const

Verifies that the output is correct and prints it.

constructNetwork()

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

private

uses a Caffe parser to create the single layer Network and marks the output layers

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

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> SampleReformatFreeIO::mEngine {nullptr}

private

The TensorRT engine used to run the network.

mParams

samplesCommon::CaffeSampleParams SampleReformatFreeIO::mParams

mInputDims

nvinfer1::Dims SampleReformatFreeIO::mInputDims

The dimensions of the input to the network.

mOutputDims

nvinfer1::Dims SampleReformatFreeIO::mOutputDims

The dimensions of the output to the network.

mTensorFormat

TensorFormat SampleReformatFreeIO::mTensorFormat {TensorFormat::kLINEAR}

mMeanBlob

SampleUniquePtr<nvcaffeparser1::IBinaryProtoBlob> SampleReformatFreeIO::mMeanBlob

mDigit

int SampleReformatFreeIO::mDigit

---

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

• sampleReformatFreeIO.cpp