Abstract class for loading a tensor network with TensorRT. More...

#include <tensorNet.h>

Inheritance diagram for tensorNet:

Classes
struct	layerInfo

class	Logger
	Logger class for GIE info/warning/errors. More...

class	Profiler
	Profiler interface for measuring layer timings. More...

Public Member Functions
virtual	~tensorNet ()
	Destory. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean=NULL, const char input_blob="data", const char output_blob="prob", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const char input_blob, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple output layers. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple input layers. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const char input_blob, const Dims3 &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance (this variant is used for UFF models) More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const std::vector< std::string > &input_blobs, const std::vector< Dims3 > &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple input layers (used for UFF models) More...

bool	LoadEngine (const char engine_filename, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load a network instance from a serialized engine plan file. More...

bool	LoadEngine (char engine_stream, size_t engine_size, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load a network instance from a serialized engine plan file. More...

bool	LoadEngine (nvinfer1::ICudaEngine *engine, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load network resources from an existing TensorRT engine instance. More...

bool	LoadEngine (const char filename, char stream, size_t size)
	Load a serialized engine plan file into memory. More...

void	EnableLayerProfiler ()
	Manually enable layer profiling times. More...

void	EnableDebug ()
	Manually enable debug messages and synchronization. More...

bool	AllowGPUFallback () const
	Return true if GPU fallback is enabled. More...

deviceType	GetDevice () const
	Retrieve the device being used for execution. More...

precisionType	GetPrecision () const
	Retrieve the type of precision being used. More...

bool	IsPrecision (precisionType type) const
	Check if a particular precision is being used. More...

cudaStream_t	GetStream () const
	Retrieve the stream that the device is operating on. More...

cudaStream_t	CreateStream (bool nonBlocking=true)
	Create and use a new stream for execution. More...

void	SetStream (cudaStream_t stream)
	Set the stream that the device is operating on. More...

const char *	GetPrototxtPath () const
	Retrieve the path to the network prototxt file. More...

const char *	GetModelPath () const
	Retrieve the full path to model file, including the filename. More...

const char *	GetModelFilename () const
	Retrieve the filename of the file, excluding the directory. More...

modelType	GetModelType () const
	Retrieve the format of the network model. More...

bool	IsModelType (modelType type) const
	Return true if the model is of the specified format. More...

uint32_t	GetInputLayers () const
	Retrieve the number of input layers to the network. More...

uint32_t	GetOutputLayers () const
	Retrieve the number of output layers to the network. More...

Dims3	GetInputDims (uint32_t layer=0) const
	Retrieve the dimensions of network input layer. More...

uint32_t	GetInputWidth (uint32_t layer=0) const
	Retrieve the width of network input layer. More...

uint32_t	GetInputHeight (uint32_t layer=0) const
	Retrieve the height of network input layer. More...

uint32_t	GetInputSize (uint32_t layer=0) const
	Retrieve the size (in bytes) of network input layer. More...

float *	GetInputPtr (uint32_t layer=0) const
	Get the CUDA pointer to the input layer's memory. More...

Dims3	GetOutputDims (uint32_t layer=0) const
	Retrieve the dimensions of network output layer. More...

uint32_t	GetOutputWidth (uint32_t layer=0) const
	Retrieve the width of network output layer. More...

uint32_t	GetOutputHeight (uint32_t layer=0) const
	Retrieve the height of network output layer. More...

uint32_t	GetOutputSize (uint32_t layer=0) const
	Retrieve the size (in bytes) of network output layer. More...

float *	GetOutputPtr (uint32_t layer=0) const
	Get the CUDA pointer to the output memory. More...

float	GetNetworkFPS ()
	Retrieve the network frames per second (FPS). More...

float	GetNetworkTime ()
	Retrieve the network runtime (in milliseconds). More...

const char *	GetNetworkName () const
	Retrieve the network name (it's filename). More...

float2	GetProfilerTime (profilerQuery query)
	Retrieve the profiler runtime (in milliseconds). More...

float	GetProfilerTime (profilerQuery query, profilerDevice device)
	Retrieve the profiler runtime (in milliseconds). More...

void	PrintProfilerTimes ()
	Print the profiler times (in millseconds). More...

Static Public Member Functions
static bool	LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, int expectedClasses=-1)
	Load class descriptions from a label file. More...

static bool	LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, std::vector< std::string > &synsets, int expectedClasses=-1)
	Load class descriptions and synset strings from a label file. More...

static bool	LoadClassColors (const char filename, float4 colors, int expectedClasses, float defaultAlpha=255.0f)
	Load class colors from a text file. More...

static bool	LoadClassColors (const char filename, float4 *colors, int expectedClasses, float defaultAlpha=255.0f)
	Load class colors from a text file. More...

static float4	GenerateColor (uint32_t classID, float alpha=255.0f)
	Procedurally generate a color for a given class index with the specified alpha value. More...

static precisionType	SelectPrecision (precisionType precision, deviceType device=DEVICE_GPU, bool allowInt8=true)
	Resolve a desired precision to a specific one that's available. More...

static precisionType	FindFastestPrecision (deviceType device=DEVICE_GPU, bool allowInt8=true)
	Determine the fastest native precision on a device. More...

static std::vector< precisionType >	DetectNativePrecisions (deviceType device=DEVICE_GPU)
	Detect the precisions supported natively on a device. More...

static bool	DetectNativePrecision (const std::vector< precisionType > &nativeTypes, precisionType type)
	Detect if a particular precision is supported natively. More...

static bool	DetectNativePrecision (precisionType precision, deviceType device=DEVICE_GPU)
	Detect if a particular precision is supported natively. More...

Protected Member Functions
	tensorNet ()
	Constructor. More...

bool	ProcessNetwork (bool sync=true)
	Execute processing of the network. More...

bool	ProfileModel (const std::string &deployFile, const std::string &modelFile, const std::vector< std::string > &inputs, const std::vector< Dims3 > &inputDims, const std::vector< std::string > &outputs, uint32_t maxBatchSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator calibrator, char engineStream, size_t engineSize)
	Create and output an optimized network model. More...

bool	ConfigureBuilder (nvinfer1::IBuilder builder, uint32_t maxBatchSize, uint32_t workspaceSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator calibrator)
	Configure builder options. More...

bool	ValidateEngine (const char model_path, const char cache_path, const char *checksum_path)
	Validate that the model already has a built TensorRT engine that exists and doesn't need updating. More...

void	PROFILER_BEGIN (profilerQuery query)
	Begin a profiling query, before network is run. More...

void	PROFILER_END (profilerQuery query)
	End a profiling query, after the network is run. More...

bool	PROFILER_QUERY (profilerQuery query)
	Query the CUDA part of a profiler query. More...

Protected Attributes
tensorNet::Logger	gLogger

tensorNet::Profiler	gProfiler

std::string	mPrototxtPath

std::string	mModelPath

std::string	mModelFile

std::string	mMeanPath

std::string	mCacheEnginePath

std::string	mCacheCalibrationPath

std::string	mChecksumPath

deviceType	mDevice

precisionType	mPrecision

modelType	mModelType

cudaStream_t	mStream

cudaEvent_t	mEventsGPU [PROFILER_TOTAL *2]

timespec	mEventsCPU [PROFILER_TOTAL *2]

nvinfer1::IRuntime *	mInfer

nvinfer1::ICudaEngine *	mEngine

nvinfer1::IExecutionContext *	mContext

float2	mProfilerTimes [PROFILER_TOTAL+1]

uint32_t	mProfilerQueriesUsed

uint32_t	mProfilerQueriesDone

uint32_t	mWorkspaceSize

uint32_t	mMaxBatchSize

bool	mEnableProfiler

bool	mEnableDebug

bool	mAllowGPUFallback

void **	mBindings

std::vector< layerInfo >	mInputs

std::vector< layerInfo >	mOutputs

Detailed Description

Abstract class for loading a tensor network with TensorRT.

For example implementations,

See also: imageNet and; detectNet

Constructor & Destructor Documentation

◆ ~tensorNet()

virtual tensorNet::~tensorNet ( )

virtual

Destory.

◆ tensorNet()

tensorNet::tensorNet ( )

protected

Constructor.

Member Function Documentation

◆ AllowGPUFallback()

bool tensorNet::AllowGPUFallback ( ) const

inline

Return true if GPU fallback is enabled.

◆ ConfigureBuilder()

bool tensorNet::ConfigureBuilder	(	nvinfer1::IBuilder *	builder,
		uint32_t	maxBatchSize,
		uint32_t	workspaceSize,
		precisionType	precision,
		deviceType	device,
		bool	allowGPUFallback,
		nvinfer1::IInt8Calibrator *	calibrator
	)

protected

Configure builder options.

◆ CreateStream()

cudaStream_t tensorNet::CreateStream ( bool nonBlocking = true )

Create and use a new stream for execution.

◆ DetectNativePrecision() [1/2]

static bool tensorNet::DetectNativePrecision	(	const std::vector< precisionType > &	nativeTypes,
		precisionType	type
	)

static

Detect if a particular precision is supported natively.

◆ DetectNativePrecision() [2/2]

static bool tensorNet::DetectNativePrecision	(	precisionType	precision,
		deviceType	device = `DEVICE_GPU`
	)

static

Detect if a particular precision is supported natively.

◆ DetectNativePrecisions()

static std::vector<precisionType> tensorNet::DetectNativePrecisions ( deviceType device = DEVICE_GPU )

static

Detect the precisions supported natively on a device.

◆ EnableDebug()

void tensorNet::EnableDebug ( )

Manually enable debug messages and synchronization.

◆ EnableLayerProfiler()

void tensorNet::EnableLayerProfiler ( )

Manually enable layer profiling times.

◆ FindFastestPrecision()

static precisionType tensorNet::FindFastestPrecision	(	deviceType	device = `DEVICE_GPU`,
		bool	allowInt8 = `true`
	)

static

Determine the fastest native precision on a device.

◆ GenerateColor()

static float4 tensorNet::GenerateColor	(	uint32_t	classID,
		float	alpha = `255.0f`
	)

static

Procedurally generate a color for a given class index with the specified alpha value.

This function can be used to generate a range of colors when a colors.txt file isn't available.

◆ GetDevice()

deviceType tensorNet::GetDevice ( ) const

inline

Retrieve the device being used for execution.

◆ GetInputDims()

Dims3 tensorNet::GetInputDims ( uint32_t layer = 0 ) const

inline

Retrieve the dimensions of network input layer.

◆ GetInputHeight()

uint32_t tensorNet::GetInputHeight ( uint32_t layer = 0 ) const

inline

Retrieve the height of network input layer.

◆ GetInputLayers()

uint32_t tensorNet::GetInputLayers ( ) const

inline

Retrieve the number of input layers to the network.

◆ GetInputPtr()

float* tensorNet::GetInputPtr ( uint32_t layer = 0 ) const

inline

Get the CUDA pointer to the input layer's memory.

◆ GetInputSize()

uint32_t tensorNet::GetInputSize ( uint32_t layer = 0 ) const

inline

Retrieve the size (in bytes) of network input layer.

◆ GetInputWidth()

uint32_t tensorNet::GetInputWidth ( uint32_t layer = 0 ) const

inline

Retrieve the width of network input layer.

◆ GetModelFilename()

const char* tensorNet::GetModelFilename ( ) const

inline

Retrieve the filename of the file, excluding the directory.

◆ GetModelPath()

const char* tensorNet::GetModelPath ( ) const

inline

Retrieve the full path to model file, including the filename.

◆ GetModelType()

modelType tensorNet::GetModelType ( ) const

inline

Retrieve the format of the network model.

◆ GetNetworkFPS()

float tensorNet::GetNetworkFPS ( )

inline

Retrieve the network frames per second (FPS).

◆ GetNetworkName()

const char* tensorNet::GetNetworkName ( ) const

inline

Retrieve the network name (it's filename).

◆ GetNetworkTime()

float tensorNet::GetNetworkTime ( )

inline

Retrieve the network runtime (in milliseconds).

◆ GetOutputDims()

Dims3 tensorNet::GetOutputDims ( uint32_t layer = 0 ) const

inline

Retrieve the dimensions of network output layer.

◆ GetOutputHeight()

uint32_t tensorNet::GetOutputHeight ( uint32_t layer = 0 ) const

inline

Retrieve the height of network output layer.

◆ GetOutputLayers()

uint32_t tensorNet::GetOutputLayers ( ) const

inline

Retrieve the number of output layers to the network.

◆ GetOutputPtr()

float* tensorNet::GetOutputPtr ( uint32_t layer = 0 ) const

inline

Get the CUDA pointer to the output memory.

◆ GetOutputSize()

uint32_t tensorNet::GetOutputSize ( uint32_t layer = 0 ) const

inline

Retrieve the size (in bytes) of network output layer.

◆ GetOutputWidth()

uint32_t tensorNet::GetOutputWidth ( uint32_t layer = 0 ) const

inline

Retrieve the width of network output layer.

◆ GetPrecision()

precisionType tensorNet::GetPrecision ( ) const

inline

Retrieve the type of precision being used.

◆ GetProfilerTime() [1/2]

float2 tensorNet::GetProfilerTime ( profilerQuery query )

inline

Retrieve the profiler runtime (in milliseconds).

◆ GetProfilerTime() [2/2]

float tensorNet::GetProfilerTime	(	profilerQuery	query,
		profilerDevice	device
	)

inline

Retrieve the profiler runtime (in milliseconds).

◆ GetPrototxtPath()

const char* tensorNet::GetPrototxtPath ( ) const

inline

Retrieve the path to the network prototxt file.

◆ GetStream()

cudaStream_t tensorNet::GetStream ( ) const

inline

Retrieve the stream that the device is operating on.

◆ IsModelType()

bool tensorNet::IsModelType ( modelType type ) const

inline

Return true if the model is of the specified format.

◆ IsPrecision()

bool tensorNet::IsPrecision ( precisionType type ) const

inline

Check if a particular precision is being used.

◆ LoadClassColors() [1/2]

static bool tensorNet::LoadClassColors	(	const char *	filename,
		float4 **	colors,
		int	expectedClasses,
		float	defaultAlpha = `255.0f`
	)

static

Load class colors from a text file.

If the number of expected colors aren't parsed, they will be generated. The float4 color array will automatically be allocated in shared CPU/GPU memory by cudaAllocMapped(). If a line in the text file only has RGB, then the defaultAlpha value will be used for the alpha channel.

◆ LoadClassColors() [2/2]

static bool tensorNet::LoadClassColors	(	const char *	filename,
		float4 *	colors,
		int	expectedClasses,
		float	defaultAlpha = `255.0f`
	)

static

Load class colors from a text file.

If the number of expected colors aren't parsed, they will be generated. The float4 color array should be expectedClasses long, and would typically be in shared CPU/GPU memory. If a line in the text file only has RGB, then the defaultAlpha value will be used for the alpha channel.

◆ LoadClassLabels() [1/2]

static bool tensorNet::LoadClassLabels	(	const char *	filename,
		std::vector< std::string > &	descriptions,
		int	expectedClasses = `-1`
	)

static

Load class descriptions from a label file.

Each line of the text file should include one class label (and optionally a synset). If the number of expected labels aren't parsed, they will be automatically generated.

◆ LoadClassLabels() [2/2]

static bool tensorNet::LoadClassLabels	(	const char *	filename,
		std::vector< std::string > &	descriptions,
		std::vector< std::string > &	synsets,
		int	expectedClasses = `-1`
	)

static

Load class descriptions and synset strings from a label file.

Each line of the text file should include one class label (and optionally a synset). If the number of expected labels aren't parsed, they will be automatically generated.

◆ LoadEngine() [1/4]

bool tensorNet::LoadEngine	(	char *	engine_stream,
		size_t	engine_size,
		const std::vector< std::string > &	input_blobs,
		const std::vector< std::string > &	output_blobs,
		nvinfer1::IPluginFactory *	pluginFactory = `NULL`,
		deviceType	device = `DEVICE_GPU`,
		cudaStream_t	stream = `NULL`
	)

Load a network instance from a serialized engine plan file.

Parameters

engine_stream	Memory containing the serialized engine plan file.
engine_size	Size of the serialized engine stream (in bytes).
input_blobs	List of names of the inputs blob data to the network.
output_blobs	List of names of the output blobs from the network.

◆ LoadEngine() [2/4]

bool tensorNet::LoadEngine	(	const char *	engine_filename,
		const std::vector< std::string > &	input_blobs,
		const std::vector< std::string > &	output_blobs,
		nvinfer1::IPluginFactory *	pluginFactory = `NULL`,
		deviceType	device = `DEVICE_GPU`,
		cudaStream_t	stream = `NULL`
	)

Load a network instance from a serialized engine plan file.

Parameters

engine_filename	path to the serialized engine plan file.
input_blobs	List of names of the inputs blob data to the network.
output_blobs	List of names of the output blobs from the network.

◆ LoadEngine() [3/4]

bool tensorNet::LoadEngine	(	const char *	filename,
		char **	stream,
		size_t *	size
	)

Load a serialized engine plan file into memory.

◆ LoadEngine() [4/4]

bool tensorNet::LoadEngine	(	nvinfer1::ICudaEngine *	engine,
		const std::vector< std::string > &	input_blobs,
		const std::vector< std::string > &	output_blobs,
		deviceType	device = `DEVICE_GPU`,
		cudaStream_t	stream = `NULL`
	)

Load network resources from an existing TensorRT engine instance.

Parameters

engine_stream	Memory containing the serialized engine plan file.
engine_size	Size of the serialized engine stream (in bytes).
input_blobs	List of names of the inputs blob data to the network.
output_blobs	List of names of the output blobs from the network.

◆ LoadNetwork() [1/5]

bool tensorNet::LoadNetwork	(	const char *	prototxt,
		const char *	model,
		const char *	mean,
		const char *	input_blob,
		const Dims3 &	input_dims,
		const std::vector< std::string > &	output_blobs,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`,
		nvinfer1::IInt8Calibrator *	calibrator = `NULL`,
		cudaStream_t	stream = `NULL`
	)

Load a new network instance (this variant is used for UFF models)

Parameters

prototxt	File path to the deployable network prototxt
model	File path to the caffemodel
mean	File path to the mean value binary proto (NULL if none)
input_blob	The name of the input blob data to the network.
input_dims	The dimensions of the input blob (used for UFF).
output_blobs	List of names of the output blobs from the network.
maxBatchSize	The maximum batch size that the network will be optimized for.

◆ LoadNetwork() [2/5]

bool tensorNet::LoadNetwork	(	const char *	prototxt,
		const char *	model,
		const char *	mean,
		const char *	input_blob,
		const std::vector< std::string > &	output_blobs,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`,
		nvinfer1::IInt8Calibrator *	calibrator = `NULL`,
		cudaStream_t	stream = `NULL`
	)

Load a new network instance with multiple output layers.

Parameters

prototxt	File path to the deployable network prototxt
model	File path to the caffemodel
mean	File path to the mean value binary proto (NULL if none)
input_blob	The name of the input blob data to the network.
output_blobs	List of names of the output blobs from the network.
maxBatchSize	The maximum batch size that the network will be optimized for.

◆ LoadNetwork() [3/5]

bool tensorNet::LoadNetwork	(	const char *	prototxt,
		const char *	model,
		const char *	mean,
		const std::vector< std::string > &	input_blobs,
		const std::vector< Dims3 > &	input_dims,
		const std::vector< std::string > &	output_blobs,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`,
		nvinfer1::IInt8Calibrator *	calibrator = `NULL`,
		cudaStream_t	stream = `NULL`
	)

Load a new network instance with multiple input layers (used for UFF models)

Parameters

prototxt	File path to the deployable network prototxt
model	File path to the caffemodel
mean	File path to the mean value binary proto (NULL if none)
input_blobs	List of names of the inputs blob data to the network.
input_dims	List of the dimensions of the input blobs (used for UFF).
output_blobs	List of names of the output blobs from the network.
maxBatchSize	The maximum batch size that the network will be optimized for.

◆ LoadNetwork() [4/5]

bool tensorNet::LoadNetwork	(	const char *	prototxt,
		const char *	model,
		const char *	mean,
		const std::vector< std::string > &	input_blobs,
		const std::vector< std::string > &	output_blobs,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`,
		nvinfer1::IInt8Calibrator *	calibrator = `NULL`,
		cudaStream_t	stream = `NULL`
	)

Load a new network instance with multiple input layers.

Parameters

prototxt	File path to the deployable network prototxt
model	File path to the caffemodel
mean	File path to the mean value binary proto (NULL if none)
input_blobs	List of names of the inputs blob data to the network.
output_blobs	List of names of the output blobs from the network.
maxBatchSize	The maximum batch size that the network will be optimized for.

◆ LoadNetwork() [5/5]

bool tensorNet::LoadNetwork	(	const char *	prototxt,
		const char *	model,
		const char *	mean = `NULL`,
		const char *	input_blob = `"data"`,
		const char *	output_blob = `"prob"`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`,
		nvinfer1::IInt8Calibrator *	calibrator = `NULL`,
		cudaStream_t	stream = `NULL`
	)

Load a new network instance.

Parameters

prototxt	File path to the deployable network prototxt
model	File path to the caffemodel
mean	File path to the mean value binary proto (NULL if none)
input_blob	The name of the input blob data to the network.
output_blob	The name of the output blob data from the network.
maxBatchSize	The maximum batch size that the network will be optimized for.

◆ PrintProfilerTimes()

void tensorNet::PrintProfilerTimes ( )

inline

Print the profiler times (in millseconds).

◆ ProcessNetwork()

bool tensorNet::ProcessNetwork ( bool sync = true )

protected

Execute processing of the network.

Parameters

sync	if true (default), the device will be synchronized after processing and the thread/function will block until processing is complete. if false, the function will return immediately after the processing has been enqueued to the CUDA stream indicated by GetStream().

◆ ProfileModel()

bool tensorNet::ProfileModel	(	const std::string &	deployFile,
		const std::string &	modelFile,
		const std::vector< std::string > &	inputs,
		const std::vector< Dims3 > &	inputDims,
		const std::vector< std::string > &	outputs,
		uint32_t	maxBatchSize,
		precisionType	precision,
		deviceType	device,
		bool	allowGPUFallback,
		nvinfer1::IInt8Calibrator *	calibrator,
		char **	engineStream,
		size_t *	engineSize
	)

protected

Create and output an optimized network model.

Note: this function is automatically used by LoadNetwork, but also can be used individually to perform the network operations offline.

Parameters

deployFile	name for network prototxt
modelFile	name for model
outputs	network outputs
maxBatchSize	maximum batch size
modelStream	output model stream

◆ PROFILER_BEGIN()

void tensorNet::PROFILER_BEGIN ( profilerQuery query )

inlineprotected

Begin a profiling query, before network is run.

◆ PROFILER_END()

void tensorNet::PROFILER_END ( profilerQuery query )

inlineprotected

End a profiling query, after the network is run.

◆ PROFILER_QUERY()

bool tensorNet::PROFILER_QUERY ( profilerQuery query )

inlineprotected

Query the CUDA part of a profiler query.

◆ SelectPrecision()

static precisionType tensorNet::SelectPrecision	(	precisionType	precision,
		deviceType	device = `DEVICE_GPU`,
		bool	allowInt8 = `true`
	)

static

Resolve a desired precision to a specific one that's available.

◆ SetStream()

void tensorNet::SetStream ( cudaStream_t stream )

Set the stream that the device is operating on.

◆ ValidateEngine()

bool tensorNet::ValidateEngine	(	const char *	model_path,
		const char *	cache_path,
		const char *	checksum_path
	)

protected

Validate that the model already has a built TensorRT engine that exists and doesn't need updating.

Member Data Documentation

◆ gLogger

tensorNet::Logger tensorNet::gLogger

protected

◆ gProfiler

tensorNet::Profiler tensorNet::gProfiler

protected

◆ mAllowGPUFallback

bool tensorNet::mAllowGPUFallback

protected

◆ mBindings

void** tensorNet::mBindings

protected

◆ mCacheCalibrationPath

std::string tensorNet::mCacheCalibrationPath

protected

◆ mCacheEnginePath

std::string tensorNet::mCacheEnginePath

protected

◆ mChecksumPath

std::string tensorNet::mChecksumPath

protected

◆ mContext

nvinfer1::IExecutionContext* tensorNet::mContext

protected

◆ mDevice

deviceType tensorNet::mDevice

protected

◆ mEnableDebug

bool tensorNet::mEnableDebug

protected

◆ mEnableProfiler

bool tensorNet::mEnableProfiler

protected

◆ mEngine

nvinfer1::ICudaEngine* tensorNet::mEngine

protected

◆ mEventsCPU

timespec tensorNet::mEventsCPU[PROFILER_TOTAL *2]

protected

◆ mEventsGPU

cudaEvent_t tensorNet::mEventsGPU[PROFILER_TOTAL *2]

protected

◆ mInfer

nvinfer1::IRuntime* tensorNet::mInfer

protected

◆ mInputs

std::vector<layerInfo> tensorNet::mInputs

protected

◆ mMaxBatchSize

uint32_t tensorNet::mMaxBatchSize

protected

◆ mMeanPath

std::string tensorNet::mMeanPath

protected

◆ mModelFile

std::string tensorNet::mModelFile

protected

◆ mModelPath

std::string tensorNet::mModelPath

protected

◆ mModelType

modelType tensorNet::mModelType

protected

◆ mOutputs

std::vector<layerInfo> tensorNet::mOutputs

protected

◆ mPrecision

precisionType tensorNet::mPrecision

protected

◆ mProfilerQueriesDone

uint32_t tensorNet::mProfilerQueriesDone

protected

◆ mProfilerQueriesUsed

uint32_t tensorNet::mProfilerQueriesUsed

protected

◆ mProfilerTimes

float2 tensorNet::mProfilerTimes[PROFILER_TOTAL+1]

protected

◆ mPrototxtPath

std::string tensorNet::mPrototxtPath

protected

◆ mStream

cudaStream_t tensorNet::mStream

protected

◆ mWorkspaceSize

uint32_t tensorNet::mWorkspaceSize

protected

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

jetson-inference/tensorNet.h

Classes

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ ~tensorNet()

◆ tensorNet()

Member Function Documentation

◆ AllowGPUFallback()

◆ ConfigureBuilder()

◆ CreateStream()

◆ DetectNativePrecision() [1/2]

◆ DetectNativePrecision() [2/2]

◆ DetectNativePrecisions()

◆ EnableDebug()

◆ EnableLayerProfiler()

◆ FindFastestPrecision()

◆ GenerateColor()

◆ GetDevice()

◆ GetInputDims()

◆ GetInputHeight()

◆ GetInputLayers()

◆ GetInputPtr()

◆ GetInputSize()

◆ GetInputWidth()

◆ GetModelFilename()

◆ GetModelPath()

◆ GetModelType()

◆ GetNetworkFPS()

◆ GetNetworkName()

◆ GetNetworkTime()

◆ GetOutputDims()

◆ GetOutputHeight()

◆ GetOutputLayers()

◆ GetOutputPtr()

◆ GetOutputSize()

◆ GetOutputWidth()

◆ GetPrecision()

◆ GetProfilerTime() [1/2]

◆ GetProfilerTime() [2/2]

◆ GetPrototxtPath()

◆ GetStream()

◆ IsModelType()

◆ IsPrecision()

◆ LoadClassColors() [1/2]

◆ LoadClassColors() [2/2]

◆ LoadClassLabels() [1/2]

◆ LoadClassLabels() [2/2]

◆ LoadEngine() [1/4]

◆ LoadEngine() [2/4]

◆ LoadEngine() [3/4]

◆ LoadEngine() [4/4]

◆ LoadNetwork() [1/5]

◆ LoadNetwork() [2/5]

◆ LoadNetwork() [3/5]

◆ LoadNetwork() [4/5]

◆ LoadNetwork() [5/5]

◆ PrintProfilerTimes()

◆ ProcessNetwork()

◆ ProfileModel()

◆ PROFILER_BEGIN()

◆ PROFILER_END()

◆ PROFILER_QUERY()

◆ SelectPrecision()

◆ SetStream()

◆ ValidateEngine()

Member Data Documentation

◆ gLogger

◆ gProfiler

◆ mAllowGPUFallback

◆ mBindings

◆ mCacheCalibrationPath

◆ mCacheEnginePath

◆ mChecksumPath

◆ mContext

◆ mDevice

◆ mEnableDebug

◆ mEnableProfiler