Image recognition DNN (GoogleNet, AlexNet, ResNet) More...

Classes
class	imageNet
	Image recognition with classification networks, using TensorRT. More...

Macros
#define	IMAGENET_DEFAULT_INPUT "data"
	Name of default input blob for imageNet model. More...

#define	IMAGENET_DEFAULT_OUTPUT "prob"
	Name of default output confidence values for imageNet model. More...

#define	IMAGENET_DEFAULT_THRESHOLD 0.01f
	Default value of the minimum confidence threshold for classification. More...

#define	IMAGENET_MODEL_TYPE "classification"
	The model type for imageNet in data/networks/models.json. More...

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

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

Detailed Description

Image recognition DNN (GoogleNet, AlexNet, ResNet)

Class Documentation

◆ imageNet

class imageNet

Image recognition with classification networks, using TensorRT.

Inheritance diagram for imageNet:

Public Types
typedef std::vector< std::pair< uint32_t, float > >	Classifications
	List of classification results where each entry represents a (classID, confidence) pair. More...

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

template<typename T >
int	Classify (T image, uint32_t width, uint32_t height, float confidence=NULL)
	Predict the maximum-likelihood image class whose confidence meets the minimum threshold. More...

int	Classify (void image, uint32_t width, uint32_t height, imageFormat format, float confidence=NULL)
	Predict the maximum-likelihood image class whose confidence meets the minimum threshold. More...

int	Classify (float rgba, uint32_t width, uint32_t height, float confidence=NULL, imageFormat format=IMAGE_RGBA32F)
	Predict the maximum-likelihood image class whose confidence meets the minimum threshold. More...

template<typename T >
int	Classify (T *image, uint32_t width, uint32_t height, Classifications &classifications, int topK=1)
	Classify the image and return the topK image classification results that meet the minimum confidence threshold set by SetThreshold() or the `--threshold` command-line argument. More...

int	Classify (void *image, uint32_t width, uint32_t height, imageFormat format, Classifications &classifications, int topK=1)
	Classify the image and return the topK image classification results that meet the minimum confidence threshold set by SetThreshold() or the `--threshold` command-line argument. More...

uint32_t	GetNumClasses () const
	Retrieve the number of image recognition classes (typically 1000) 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 *	GetClassSynset (int index) const
	Retrieve the class synset category 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...

float	GetSmoothing () const
	Return the temporal smoothing weight or number of frames in the smoothing window. More...

void	SetSmoothing (float factor)
	Enable temporal smoothing of the results using EWMA (exponentially-weighted moving average). 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 imageNet *	Create (const char *network="googlenet", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load one of the following pre-trained models: More...

static imageNet *	Create (const char prototxt_path, const char model_path, const char mean_binary, const char class_labels, const char input=IMAGENET_DEFAULT_INPUT, const char output=IMAGENET_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 imageNet *	Create (int argc, char **argv)
	Load a new network instance by parsing the command line. More...

static imageNet *	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
	imageNet ()

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

bool	loadClassInfo (const char *filename, int expectedClasses=-1)

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

float *	applySmoothing ()

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
uint32_t	mNumClasses

std::vector< std::string >	mClassSynset

std::vector< std::string >	mClassDesc

std::string	mClassPath

float *	mSmoothingBuffer

float	mSmoothingFactor

float	mThreshold

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

Member Typedef Documentation

◆ Classifications

typedef std::vector<std::pair<uint32_t, float> > imageNet::Classifications

List of classification results where each entry represents a (classID, confidence) pair.

Constructor & Destructor Documentation

◆ ~imageNet()

virtual imageNet::~imageNet ( )

virtual

Destroy.

◆ imageNet()

imageNet::imageNet ( )

protected

Member Function Documentation

◆ applySmoothing()

float* imageNet::applySmoothing ( )

protected

◆ Classify() [1/5]

int imageNet::Classify	(	float *	rgba,
		uint32_t	width,
		uint32_t	height,
		float *	confidence = `NULL`,
		imageFormat	format = `IMAGE_RGBA32F`
	)

Predict the maximum-likelihood image class whose confidence meets the minimum threshold.

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

Parameters

rgba	float4 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.
format	format of the image (rgb8, rgba8, rgb32f, rgba32f are supported)

Returns: ID of the class with the highest confidence, or -1 if no classes met the threshold. If a runtime error occurred during processing, then a value of -2 will be returned.

Deprecated:: this overload of Classify() provides legacy compatibility with float* type (RGBA32F).

◆ Classify() [2/5]

template<typename T >

int imageNet::Classify	(	T *	image,
		uint32_t	width,
		uint32_t	height,
		Classifications &	classifications,
		int	topK = `1`
	)

inline

Classify the image and return the topK image classification results that meet the minimum confidence threshold set by SetThreshold() or the --threshold command-line argument.

Parameters

image	input image in CUDA device memory.
width	width of the input image in pixels.
height	height of the input image in pixels.
classifications	returns a list of the topK (classID, confidence) classification resuts, sorted from highest to lowest confidence.
topK	the number of predictions to return (it can be less than this number if there weren't that many valid predictions) The default value of topK is 1, in which case only the highest-confidence result wil be returned. If the value of topK is <= 0, then all the valid predictions with confidence >= threshold will be returned.

Returns: ID of the class with the highest confidence, or -1 if no classes met the threshold. If a runtime error occurred during processing, then a value of -2 will be returned.

◆ Classify() [3/5]

template<typename T >

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

inline

Predict the maximum-likelihood image class whose confidence meets the minimum threshold.

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

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: ID of the class with the highest confidence, or -1 if no classes met the threshold. If a runtime error occurred during processing, then a value of -2 will be returned.

◆ Classify() [4/5]

int imageNet::Classify	(	void *	image,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		Classifications &	classifications,
		int	topK = `1`
	)

Classify the image and return the topK image classification results that meet the minimum confidence threshold set by SetThreshold() or the --threshold command-line argument.

Parameters

image	input image in CUDA device memory.
width	width of the input image in pixels.
height	height of the input image in pixels.
format	format of the image (rgb8, rgba8, rgb32f, rgba32f are supported)
classifications	returns a list of the topK (classID, confidence) classification resuts, sorted from highest to lowest confidence.
topK	the number of predictions to return (it can be less than this number if there weren't that many valid predictions) The default value of topK is 1, in which case only the highest-confidence result wil be returned. If the value of topK is <= 0, then all the valid predictions with confidence >= threshold will be returned.

Returns: ID of the class with the highest confidence, or -1 if no classes met the threshold. If a runtime error occurred during processing, then a value of -2 will be returned.

◆ Classify() [5/5]

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

Predict the maximum-likelihood image class whose confidence meets the minimum threshold.

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

Parameters

image	input image in CUDA device memory.
width	width of the input image in pixels.
height	height of the input image in pixels.
format	format of the image (rgb8, rgba8, rgb32f, rgba32f are supported)
confidence	optional pointer to float filled with confidence value.

Returns: ID of the class with the highest confidence, or -1 if no classes met the threshold. If a runtime error occurred during processing, then a value of -2 will be returned.

◆ Create() [1/4]

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

static

Load one of the following pre-trained models:

alexnet, googlenet, googlenet-12,
resnet-18, resnet-50, resnet-101, resnet-152,
vgg-16, vgg-19, inception-v4

These are all 1000-class models trained on ImageNet ILSVRC, except for googlenet-12 which is a 12-class subset of ILSVRC.

◆ Create() [2/4]

static imageNet* imageNet::Create	(	const char *	prototxt_path,
		const char *	model_path,
		const char *	mean_binary,
		const char *	class_labels,
		const char *	input = `IMAGENET_DEFAULT_INPUT`,
		const char *	output = `IMAGENET_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() [3/4]

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

static

Load a new network instance by parsing the command line.

◆ Create() [4/4]

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

static

Load a new network instance by parsing the command line.

◆ GetClassDesc()

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

inline

Retrieve the description of a particular class.

◆ GetClassLabel()

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

inline

Retrieve the description of a particular class.

◆ GetClassPath()

const char* imageNet::GetClassPath ( ) const

inline

Retrieve the path to the file containing the class descriptions.

◆ GetClassSynset()

const char* imageNet::GetClassSynset ( int index ) const

inline

Retrieve the class synset category of a particular class.

◆ GetNumClasses()

uint32_t imageNet::GetNumClasses ( ) const

inline

Retrieve the number of image recognition classes (typically 1000)

◆ GetSmoothing()

float imageNet::GetSmoothing ( ) const

inline

Return the temporal smoothing weight or number of frames in the smoothing window.

See also: SetSmoothing

◆ GetThreshold()

float imageNet::GetThreshold ( ) const

inline

Return the confidence threshold used for classification.

◆ init()

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

protected

◆ loadClassInfo()

bool imageNet::loadClassInfo	(	const char *	filename,
		int	expectedClasses = `-1`
	)

protected

◆ preProcess()

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

protected

◆ SetSmoothing()

void imageNet::SetSmoothing ( float factor )

inline

Enable temporal smoothing of the results using EWMA (exponentially-weighted moving average).

This filters the confidence values of each class over ~N frames to reduce noise and jitter. In lieu of storing a history of past data, this uses an accumulated approximation of EMA:

EMA(x,t) = EMA(x, t-1) + w * (x - EMA(x, t-1))

where x is a class softmax output logit, t is the timestep, and w is the smoothing weight.

Parameters

factor either a weight between [0,1] that's placed on the latest confidence values, or the smoothing window as a number of frames (where the weight will be 1/N).
For example, a factor of N=5 would average over approximately the last 5 frames, and would be equivalent to specifying a weight of 0.2 (either can be used). A weight closer to 1 will be more responsive to changes, but also more noisy.
Setting this to 0 or 1 will disable smoothing and use the unfiltered outputs.

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

◆ SetThreshold()

void imageNet::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* imageNet::Usage ( )

inlinestatic

Usage string for command line arguments to Create()

Member Data Documentation

◆ mClassDesc

std::vector<std::string> imageNet::mClassDesc

protected

◆ mClassPath

std::string imageNet::mClassPath

protected

◆ mClassSynset

std::vector<std::string> imageNet::mClassSynset

protected

◆ mNumClasses

uint32_t imageNet::mNumClasses

protected

◆ mSmoothingBuffer

float* imageNet::mSmoothingBuffer

protected

◆ mSmoothingFactor

float imageNet::mSmoothingFactor

protected

◆ mThreshold

float imageNet::mThreshold

protected

Macro Definition Documentation

◆ IMAGENET_DEFAULT_INPUT

#define IMAGENET_DEFAULT_INPUT "data"

Name of default input blob for imageNet model.

◆ IMAGENET_DEFAULT_OUTPUT

#define IMAGENET_DEFAULT_OUTPUT "prob"

Name of default output confidence values for imageNet model.

◆ IMAGENET_DEFAULT_THRESHOLD

#define IMAGENET_DEFAULT_THRESHOLD 0.01f

Default value of the minimum confidence threshold for classification.

◆ IMAGENET_MODEL_TYPE

#define IMAGENET_MODEL_TYPE "classification"

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

◆ IMAGENET_USAGE_STRING

#define IMAGENET_USAGE_STRING

Value:

                  "imageNet arguments: \n"                                                      \
                  "  --network=NETWORK    pre-trained model to load, one of the following:\n"   \
                  "                           * alexnet\n"                                                              \
                  "                           * googlenet (default)\n"                                  \
                  "                           * googlenet-12\n"                                                         \
                  "                           * resnet-18\n"                                                    \
                  "                           * resnet-50\n"                                                    \
                  "                           * resnet-101\n"                                                   \
                  "                           * resnet-152\n"                                                   \
                  "                           * vgg-16\n"                                                               \
                  "                           * vgg-19\n"                                                               \
                  "                           * inception-v4\n"                                                         \
                  "  --model=MODEL        path to custom model to load (caffemodel, uff, or onnx)\n"                    \
                  "  --prototxt=PROTOTXT  path to custom prototxt to load (for .caffemodel only)\n"                             \
                  "  --labels=LABELS      path to text file containing the labels for each class\n"                             \
                  "  --input-blob=INPUT   name of the input layer (default is '" IMAGENET_DEFAULT_INPUT "')\n"  \
                  "  --output-blob=OUTPUT name of the output layer (default is '" IMAGENET_DEFAULT_OUTPUT "')\n"        \
                  "  --threshold=CONF     minimum confidence threshold for classification (default is 0.01)\n"  \
                  "  --smoothing=WEIGHT   weight between [0,1] or number of frames (disabled by default)\n"             \
                  "  --profile            enable layer profiling in TensorRT\n\n"

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

◆ POSENET_USAGE_STRING

#define POSENET_USAGE_STRING

Value:

                  "poseNet arguments: \n"                                                               \
                  "  --network=NETWORK     pre-trained model to load, one of the following:\n"  \
                  "                            * resnet18-body (default)\n"                             \
                  "                            * resnet18-hand\n"                                               \
                  "                            * densenet121-body\n"                                            \
                  "  --model=MODEL         path to custom model to load (caffemodel, uff, or onnx)\n"                                   \
                  "  --prototxt=PROTOTXT   path to custom prototxt to load (for .caffemodel only)\n"                                    \
                  "  --labels=LABELS       path to text file containing the labels for each class\n"                                    \
                  "  --input-blob=INPUT    name of the input layer (default is '" POSENET_DEFAULT_INPUT "')\n"                  \
                  "  --output-cvg=COVERAGE name of the coverge output layer (default is '" POSENET_DEFAULT_CMAP "')\n"  \
                  "  --output-bbox=BOXES   name of the bounding output layer (default is '" POSENET_DEFAULT_PAF "')\n"  \
                  "  --mean-pixel=PIXEL    mean pixel value to subtract from input (default is 0.0)\n"                                  \
                  "  --threshold=THRESHOLD minimum threshold for detection (default is 0.5)\n"                                                  \
                  "  --overlay=OVERLAY     detection overlay flags (e.g. --overlay=links,keypoints)\n"                                  \
                  "                        valid combinations are:  'box', 'links', 'keypoints', 'none'\n"                              \
                  "  --keypoint-scale=X    radius scale for keypoints, relative to image (default: 0.0052)\n"                           \
                  "  --link-scale=X        line width scale for links, relative to image (default: 0.0013)\n"                           \
                  "  --profile             enable layer profiling in TensorRT\n\n"

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

Classes

Macros

Detailed Description

Class Documentation

◆ imageNet

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Member Typedef Documentation

◆ Classifications

Constructor & Destructor Documentation

◆ ~imageNet()

◆ imageNet()

Member Function Documentation

◆ applySmoothing()

◆ Classify() [1/5]

◆ Classify() [2/5]

◆ Classify() [3/5]

◆ Classify() [4/5]

◆ Classify() [5/5]

◆ Create() [1/4]

◆ Create() [2/4]

◆ Create() [3/4]

◆ Create() [4/4]

◆ GetClassDesc()

◆ GetClassLabel()

◆ GetClassPath()

◆ GetClassSynset()

◆ GetNumClasses()

◆ GetSmoothing()

◆ GetThreshold()

◆ init()

◆ loadClassInfo()

◆ preProcess()

◆ SetSmoothing()

◆ SetThreshold()

◆ Usage()

Member Data Documentation

◆ mClassDesc

◆ mClassPath

◆ mClassSynset

◆ mNumClasses

◆ mSmoothingBuffer

◆ mSmoothingFactor

◆ mThreshold

Macro Definition Documentation

◆ IMAGENET_DEFAULT_INPUT

◆ IMAGENET_DEFAULT_OUTPUT

◆ IMAGENET_DEFAULT_THRESHOLD

◆ IMAGENET_MODEL_TYPE

◆ IMAGENET_USAGE_STRING

◆ POSENET_USAGE_STRING