Action/activity recognition DNN. More...

Classes
class	actionNet
	Action/activity classification on a sequence of images or video, using TensorRT. More...

Macros
#define	ACTIONNET_DEFAULT_INPUT "input"
	Name of default input blob for actionNet model. More...

#define	ACTIONNET_DEFAULT_OUTPUT "output"
	Name of default output confidence values for actionNet model. More...

#define	ACTIONNET_MODEL_TYPE "action"
	The model type for actionNet in data/networks/models.json. More...

#define	ACTIONNET_USAGE_STRING
	Standard command-line options able to be passed to actionNet::Create() More...

Detailed Description

Action/activity recognition DNN.

Class Documentation

◆ actionNet

class actionNet

Action/activity classification on a sequence of images or video, using TensorRT.

Inheritance diagram for actionNet:

Public Member Functions
virtual	~actionNet ()
	Destroy. More...

template<typename T >
int	Classify (T image, uint32_t width, uint32_t height, float confidence=NULL)
	Append an image to the sequence and classify the action, returning the index of the top class. More...

int	Classify (void image, uint32_t width, uint32_t height, imageFormat format, float confidence=NULL)
	Append an image to the sequence and classify the action, returning the index of the top class. More...

uint32_t	GetNumClasses () const
	Retrieve the number of image recognition classes. More...

const char *	GetClassLabel (int index) const
	Retrieve the description of a particular class. More...

const char *	GetClassDesc (int index) const
	Retrieve the description of a particular class. More...

const char *	GetClassPath () const
	Retrieve the path to the file containing the class descriptions. More...

float	GetThreshold () const
	Return the confidence threshold used for classification. More...

void	SetThreshold (float threshold)
	Set the confidence threshold used for classification. More...

uint32_t	GetSkipFrames () const
	Return the number of frames that are skipped in between classifications. More...

void	SetSkipFrames (uint32_t frames)
	Set the number of frames that are skipped in between classifications. More...

Public Member Functions inherited from tensorNet
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 actionNet *	Create (const char *network="resnet-18", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load a pre-trained model, either "resnet-18" or "resnet-34". More...

static actionNet *	Create (const char model_path, const char class_labels, const char input=ACTIONNET_DEFAULT_INPUT, const char output=ACTIONNET_DEFAULT_OUTPUT, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load a new network instance. More...

static actionNet *	Create (int argc, char **argv)
	Load a new network instance by parsing the command line. More...

static actionNet *	Create (const commandLine &cmdLine)
	Load a new network instance by parsing the command line. More...

static const char *	Usage ()
	Usage string for command line arguments to Create() More...

Static Public Member Functions inherited from tensorNet
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
	actionNet ()

bool	init (const char model_path, const char class_path, const char input, const char output, uint32_t maxBatchSize, precisionType precision, deviceType device, bool allowGPUFallback)

bool	preProcess (void *image, uint32_t width, uint32_t height, imageFormat format)

Protected Member Functions inherited from tensorNet
	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
float *	mInputBuffers [2]

uint32_t	mNumClasses

uint32_t	mNumFrames

uint32_t	mSkipFrames

uint32_t	mFramesSkipped

uint32_t	mCurrentInputBuffer

uint32_t	mCurrentFrameIndex

float	mThreshold

float	mLastConfidence

int	mLastClassification

std::vector< std::string >	mClassDesc

std::string	mClassPath

Protected Attributes inherited from tensorNet
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

Constructor & Destructor Documentation

◆ ~actionNet()

virtual actionNet::~actionNet ( )

virtual

Destroy.

◆ actionNet()

actionNet::actionNet ( )

protected

Member Function Documentation

◆ Classify() [1/2]

template<typename T >

int actionNet::Classify	(	T *	image,
		uint32_t	width,
		uint32_t	height,
		float *	confidence = `NULL`
	)

inline

Append an image to the sequence and classify the action, returning the index of the top class.

Either the class with the maximum confidence will be returned, or -1 if no class meets the threshold set by SetThreshold() or the --threshold command-line argument.

If this frame was skipped due to SetSkipFrames() being used, then the last frame's results will be returned. By default, every other frame is skipped in order to lengthen the action's window.

Parameters

image	input image in CUDA device memory.
width	width of the input image in pixels.
height	height of the input image in pixels.
confidence	optional pointer to float filled with confidence value.

Returns: Index of the maximum likelihood class, or -1 on error.

◆ Classify() [2/2]

int actionNet::Classify	(	void *	image,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		float *	confidence = `NULL`
	)

Append an image to the sequence and classify the action, returning the index of the top class.

Either the class with the maximum confidence will be returned, or -1 if no class meets the threshold set by SetThreshold() or the --threshold command-line argument.

If this frame was skipped due to SetSkipFrames() being used, then the last frame's results will be returned. By default, every other frame is skipped in order to lengthen the action's window.

Parameters

image	input image in CUDA device memory.
width	width of the input image in pixels.
height	height of the input image in pixels.
confidence	optional pointer to float filled with confidence value.

Returns: Index of the maximum likelihood class, or -1 on error.

◆ Create() [1/4]

static actionNet* actionNet::Create	(	const char *	model_path,
		const char *	class_labels,
		const char *	input = `ACTIONNET_DEFAULT_INPUT`,
		const char *	output = `ACTIONNET_DEFAULT_OUTPUT`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`
	)

static

Load a new network instance.

Parameters

prototxt_path	File path to the deployable network prototxt
model_path	File path to the caffemodel
mean_binary	File path to the mean value binary proto (can be NULL)
class_labels	File path to list of class name labels
input	Name of the input layer blob.
output	Name of the output layer blob.
maxBatchSize	The maximum batch size that the network will support and be optimized for.

◆ Create() [2/4]

static actionNet* actionNet::Create	(	const char *	network = `"resnet-18"`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`
	)

static

Load a pre-trained model, either "resnet-18" or "resnet-34".

◆ Create() [3/4]

static actionNet* actionNet::Create ( const commandLine & cmdLine )

static

Load a new network instance by parsing the command line.

◆ Create() [4/4]

static actionNet* actionNet::Create	(	int	argc,
		char **	argv
	)

static

Load a new network instance by parsing the command line.

◆ GetClassDesc()

const char* actionNet::GetClassDesc ( int index ) const

inline

Retrieve the description of a particular class.

◆ GetClassLabel()

const char* actionNet::GetClassLabel ( int index ) const

inline

Retrieve the description of a particular class.

◆ GetClassPath()

const char* actionNet::GetClassPath ( ) const

inline

Retrieve the path to the file containing the class descriptions.

◆ GetNumClasses()

uint32_t actionNet::GetNumClasses ( ) const

inline

Retrieve the number of image recognition classes.

◆ GetSkipFrames()

uint32_t actionNet::GetSkipFrames ( ) const

inline

Return the number of frames that are skipped in between classifications.

See also: SetFrameSkip for more info.

◆ GetThreshold()

float actionNet::GetThreshold ( ) const

inline

Return the confidence threshold used for classification.

◆ init()

bool actionNet::init	(	const char *	model_path,
		const char *	class_path,
		const char *	input,
		const char *	output,
		uint32_t	maxBatchSize,
		precisionType	precision,
		deviceType	device,
		bool	allowGPUFallback
	)

protected

◆ preProcess()

bool actionNet::preProcess	(	void *	image,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format
	)

protected

◆ SetSkipFrames()

void actionNet::SetSkipFrames ( uint32_t frames )

inline

Set the number of frames that are skipped in between classifications.

Since actionNet operates on video sequences, it's often helpful to skip frames to lengthen the window of time the model gets to 'see' an action being performed.

The default setting is 1, where every other frame is skipped. Setting this to 0 will disable it, and every frame will be processed. When a frame is skipped, the classification results from the last frame are returned.

◆ SetThreshold()

void actionNet::SetThreshold ( float threshold )

inline

Set the confidence threshold used for classification.

Classes with a confidence below this threshold will be ignored.

Note: this can also be set using the --threshold=N command-line argument.

◆ Usage()

static const char* actionNet::Usage ( )

inlinestatic

Usage string for command line arguments to Create()

Member Data Documentation

◆ mClassDesc

std::vector<std::string> actionNet::mClassDesc

protected

◆ mClassPath

std::string actionNet::mClassPath

protected

◆ mCurrentFrameIndex

uint32_t actionNet::mCurrentFrameIndex

protected

◆ mCurrentInputBuffer

uint32_t actionNet::mCurrentInputBuffer

protected

◆ mFramesSkipped

uint32_t actionNet::mFramesSkipped

protected

◆ mInputBuffers

float* actionNet::mInputBuffers[2]

protected

◆ mLastClassification

int actionNet::mLastClassification

protected

◆ mLastConfidence

float actionNet::mLastConfidence

protected

◆ mNumClasses

uint32_t actionNet::mNumClasses

protected

◆ mNumFrames

uint32_t actionNet::mNumFrames

protected

◆ mSkipFrames

uint32_t actionNet::mSkipFrames

protected

◆ mThreshold

float actionNet::mThreshold

protected

Macro Definition Documentation

◆ ACTIONNET_DEFAULT_INPUT

#define ACTIONNET_DEFAULT_INPUT "input"

Name of default input blob for actionNet model.

◆ ACTIONNET_DEFAULT_OUTPUT

#define ACTIONNET_DEFAULT_OUTPUT "output"

Name of default output confidence values for actionNet model.

◆ ACTIONNET_MODEL_TYPE

#define ACTIONNET_MODEL_TYPE "action"

The model type for actionNet in data/networks/models.json.

◆ ACTIONNET_USAGE_STRING

#define ACTIONNET_USAGE_STRING

Value:

                  "actionNet arguments: \n"                                                     \
                  "  --network=NETWORK    pre-trained model to load, one of the following:\n"   \
                  "                           * resnet-18 (default)\n"                                          \
                  "                           * resnet-34\n"                                                    \
                  "  --model=MODEL        path to custom model to load (.onnx)\n"                       \
                  "  --labels=LABELS      path to text file containing the labels for each class\n"                             \
                  "  --input-blob=INPUT   name of the input layer (default is '" ACTIONNET_DEFAULT_INPUT "')\n"         \
                  "  --output-blob=OUTPUT name of the output layer (default is '" ACTIONNET_DEFAULT_OUTPUT "')\n"       \
                  "  --threshold=CONF     minimum confidence threshold for classification (default is 0.01)\n"  \
                  "  --skip-frames=SKIP   how many frames to skip between classifications (default is 1)\n"         \
                  "  --profile            enable layer profiling in TensorRT\n\n"

Standard command-line options able to be passed to actionNet::Create()

Classes

Macros

Detailed Description

Class Documentation

◆ actionNet

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Constructor & Destructor Documentation

◆ ~actionNet()

◆ actionNet()

Member Function Documentation

◆ Classify() [1/2]

◆ Classify() [2/2]

◆ Create() [1/4]

◆ Create() [2/4]

◆ Create() [3/4]

◆ Create() [4/4]

◆ GetClassDesc()

◆ GetClassLabel()

◆ GetClassPath()

◆ GetNumClasses()

◆ GetSkipFrames()

◆ GetThreshold()

◆ init()

◆ preProcess()

◆ SetSkipFrames()

◆ SetThreshold()

◆ Usage()

Member Data Documentation

◆ mClassDesc

◆ mClassPath

◆ mCurrentFrameIndex

◆ mCurrentInputBuffer

◆ mFramesSkipped

◆ mInputBuffers

◆ mLastClassification

◆ mLastConfidence

◆ mNumClasses

◆ mNumFrames

◆ mSkipFrames

◆ mThreshold

Macro Definition Documentation

◆ ACTIONNET_DEFAULT_INPUT

◆ ACTIONNET_DEFAULT_OUTPUT

◆ ACTIONNET_MODEL_TYPE

◆ ACTIONNET_USAGE_STRING