SampleMovieLens Class Reference

The SampleMovieLens class implements the MovieLens sample. More...

Collaboration diagram for SampleMovieLens:

Public Member Functions
	SampleMovieLens (const SampleMovieLensParams &params)
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< nvinfer1::INetworkDefinition > &network, SampleUniquePtr< nvinfer1::IBuilderConfig > &config, SampleUniquePtr< nvuffparser::IUffParser > &parser)
	Parses a Uff model for a MLP NCF model, creates a TensorRT network, and builds a TensorRT engine. More...
bool	processInput (const samplesCommon::BufferManager &buffers)
	Copies a batch of input data from SampleMovieLensParams into managed input buffers. More...
std::string	readNextLine (std::ifstream &file, char delim)
	Helper function to read the next line of the MovieLens dataset .csv file and return the contents of the line after the delimeter. More...
void	readInputSample (std::ifstream &file, OutputParams &outParams, std::string line)
	Extracts needed dataset values for a single user in the MovieLens, dataset .csv file, and populates the corresponding ground truth data struct. More...
void	parseMovieLensData ()
	Parses the MovieLens dataset and populates the SampleMovieLensParams data structure. More...
void	printOutputParams (OutputParams &outParams)
	Prints the expected recommendation results (ground truth) from the MovieLens dataset for a given user. More...
bool	verifyOutput (uint32_t *userInputPtr, uint32_t *, uint32_t *topKItemNumberPtr, float *topKItemProbPtr)
	Verifies the inference output with ground truth and logs the results. More...

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

Detailed Description

The SampleMovieLens class implements the MovieLens sample.

It creates the network using a uff model

Member Typedef Documentation

SampleUniquePtr

template<typename T >

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

private

Constructor & Destructor Documentation

SampleMovieLens()

SampleMovieLens::SampleMovieLens ( const SampleMovieLensParams &  params )

inline

Member Function Documentation

build()

bool SampleMovieLens::build

(

)

Builds the network engine.

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

This function creates the MLP NCF network by parsing the Uff model and builds the engine that will be used to generate recommendations (mEngine)

Returns

Returns true if the engine was created successfully and false otherwise

Here is the call graph for this function:

infer()

bool SampleMovieLens::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 SampleMovieLens::teardown

(

)

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

Here is the call graph for this function:

constructNetwork()

void SampleMovieLens::constructNetwork ( SampleUniquePtr< nvinfer1::IBuilder > &  builder, SampleUniquePtr< nvinfer1::INetworkDefinition > &  network, SampleUniquePtr< nvinfer1::IBuilderConfig > &  config, SampleUniquePtr< nvuffparser::IUffParser > &  parser  )

private

Parses a Uff model for a MLP NCF model, creates a TensorRT network, and builds a TensorRT engine.

Here is the call graph for this function:

Here is the caller graph for this function:

processInput()

bool SampleMovieLens::processInput ( const samplesCommon::BufferManager &  buffers )

private

Copies a batch of input data from SampleMovieLensParams into managed input buffers.

Here is the call graph for this function:

Here is the caller graph for this function:

readNextLine()

std::string SampleMovieLens::readNextLine ( std::ifstream &  file, char  delim  )

private

Helper function to read the next line of the MovieLens dataset .csv file and return the contents of the line after the delimeter.

This function is called from SampleMovieLens::readInputSample() to extract the needed values per user.

Here is the caller graph for this function:

readInputSample()

void SampleMovieLens::readInputSample ( std::ifstream &  file, OutputParams &  outParams, std::string  line  )

private

Extracts needed dataset values for a single user in the MovieLens, dataset .csv file, and populates the corresponding ground truth data struct.

Here is the call graph for this function:

Here is the caller graph for this function:

parseMovieLensData()

void SampleMovieLens::parseMovieLensData ( )

private

Parses the MovieLens dataset and populates the SampleMovieLensParams data structure.

Here is the call graph for this function:

Here is the caller graph for this function:

printOutputParams()

void SampleMovieLens::printOutputParams ( OutputParams &  outParams )

private

Prints the expected recommendation results (ground truth) from the MovieLens dataset for a given user.

Here is the caller graph for this function:

verifyOutput()

bool SampleMovieLens::verifyOutput ( uint32_t *  userInputPtr, uint32_t *  , uint32_t *  topKItemNumberPtr, float *  topKItemProbPtr  )

private

Verifies the inference output with ground truth and logs the results.

Compares the inference output with ground truth and logs the results.

Here is the caller graph for this function:

Member Data Documentation

mParams

SampleMovieLensParams SampleMovieLens::mParams

private

mEngine

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

private

The TensorRT engine used to run the network.

---

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

• sampleMovieLens.cpp