Semantic segmentation DNN (FCN or Fully-Convolutional Networks) More...

Classes
class	segNet
	Image segmentation with FCN-Alexnet or custom models, using TensorRT. More...

Macros
#define	SEGNET_DEFAULT_INPUT "input_0"
	Name of default input blob for segmentation model. More...

#define	SEGNET_DEFAULT_OUTPUT "output_0"
	Name of default output blob for segmentation model. More...

#define	SEGNET_DEFAULT_ALPHA 150
	Default alpha blending value used during overlay. More...

#define	SEGNET_MODEL_TYPE "segmentation"
	The model type for segNet in data/networks/models.json. More...

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

Detailed Description

Semantic segmentation DNN (FCN or Fully-Convolutional Networks)

Class Documentation

◆ segNet

class segNet

Image segmentation with FCN-Alexnet or custom models, using TensorRT.

Inheritance diagram for segNet:

Public Types
enum	FilterMode { FILTER_POINT = 0, FILTER_LINEAR }
	Enumeration of mask/overlay filtering modes. More...

enum	VisualizationFlags { VISUALIZE_OVERLAY = (1 << 0), VISUALIZE_MASK = (1 << 1) }
	Visualization flags. More...

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

template<typename T >
bool	Process (T input, uint32_t width, uint32_t height, const char ignore_class="void")
	Perform the initial inferencing processing portion of the segmentation. More...

bool	Process (void input, uint32_t width, uint32_t height, imageFormat format, const char ignore_class="void")
	Perform the initial inferencing processing portion of the segmentation. More...

bool	Process (float input, uint32_t width, uint32_t height, const char ignore_class="void")
	Perform the initial inferencing processing portion of the segmentation. More...

template<typename T >
bool	Mask (T *output, uint32_t width, uint32_t height, FilterMode filter=FILTER_LINEAR)
	Produce a colorized segmentation mask. More...

bool	Mask (void *output, uint32_t width, uint32_t height, imageFormat format, FilterMode filter=FILTER_LINEAR)
	Produce a colorized segmentation mask. More...

bool	Mask (float *output, uint32_t width, uint32_t height, FilterMode filter=FILTER_LINEAR)
	Produce a colorized RGBA segmentation mask. More...

bool	Mask (uint8_t *output, uint32_t width, uint32_t height)
	Produce a grayscale binary segmentation mask, where the pixel values correspond to the class ID of the corresponding class type. More...

template<typename T >
bool	Overlay (T *output, uint32_t width, uint32_t height, FilterMode filter=FILTER_LINEAR)
	Produce the segmentation overlay alpha blended on top of the original image. More...

bool	Overlay (void *output, uint32_t width, uint32_t height, imageFormat format, FilterMode filter=FILTER_LINEAR)
	Produce the segmentation overlay alpha blended on top of the original image. More...

bool	Overlay (float *output, uint32_t width, uint32_t height, FilterMode filter=FILTER_LINEAR)
	Produce the segmentation overlay alpha blended on top of the original image. More...

int	FindClassID (const char *label_name)
	Find the ID of a particular class (by label name). More...

uint32_t	GetNumClasses () const
	Retrieve the number of object classes supported in the detector. More...

const char *	GetClassLabel (uint32_t id) const
	Retrieve the description of a particular class. More...

const char *	GetClassDesc (uint32_t id) const
	Retrieve the description of a particular class. More...

float4	GetClassColor (uint32_t id) const
	Retrieve the RGBA visualization color a particular class. More...

void	SetClassColor (uint32_t classIndex, const float4 &color)
	Set the visualization color of a particular class of object. More...

void	SetClassColor (uint32_t classIndex, float r, float g, float b, float a=255.0f)
	Set the visualization color of a particular class of object. More...

float	GetOverlayAlpha () const
	Retrieve the overlay alpha blending value for classes that don't have it explicitly set. More...

void	SetOverlayAlpha (float alpha, bool explicit_exempt=true)
	Set overlay alpha blending value for all classes (between 0-255), (optionally except for those that have been explicitly set). More...

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

uint32_t	GetGridWidth () const
	Retrieve the number of columns in the classification grid. More...

uint32_t	GetGridHeight () const
	Retrieve the number of rows in the classification grid. 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 uint32_t	VisualizationFlagsFromStr (const char *str, uint32_t default_value=VISUALIZE_OVERLAY)
	Parse a string of one of more VisualizationMode values. More...

static FilterMode	FilterModeFromStr (const char *str, FilterMode default_value=FILTER_LINEAR)
	Parse a string from one of the FilterMode values. More...

static segNet *	Create (const char *network="fcn-resnet18-voc", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load a pre-trained model. More...

static segNet *	Create (const char prototxt_path, const char model_path, const char class_labels, const char class_colors=NULL, const char input=SEGNET_DEFAULT_INPUT, const char output=SEGNET_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 segNet *	Create (int argc, char **argv)
	Load a new network instance by parsing the command line. More...

static segNet *	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
	segNet ()

bool	classify (const char *ignore_class)

bool	overlayPoint (void input, uint32_t in_width, uint32_t in_height, imageFormat in_format, void output, uint32_t out_width, uint32_t out_height, imageFormat out_format, bool mask_only)

bool	overlayLinear (void input, uint32_t in_width, uint32_t in_height, imageFormat in_format, void output, uint32_t out_width, uint32_t out_height, imageFormat out_format, bool mask_only)

bool	loadClassColors (const char *filename)

bool	loadClassLabels (const char *filename)

bool	saveClassLegend (const char *filename)

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
std::vector< std::string >	mClassLabels

std::string	mClassPath

bool *	mColorsAlphaSet
	true if class color had been explicitly set from file or user More...

float4 *	mClassColors
	array of overlay colors in shared CPU/GPU memory More...

uint8_t *	mClassMap
	runtime buffer for the argmax-classified class index of each tile More...

void *	mLastInputImg
	last input image to be processed, stored for overlay More...

uint32_t	mLastInputWidth
	width in pixels of last input image to be processed More...

uint32_t	mLastInputHeight
	height in pixels of last input image to be processed More...

imageFormat	mLastInputFormat
	pixel format of last input image More...

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 Enumeration Documentation

◆ FilterMode

enum segNet::FilterMode

Enumeration of mask/overlay filtering modes.

Enumerator
FILTER_POINT	Nearest point sampling.
FILTER_LINEAR	Bilinear filtering.

◆ VisualizationFlags

enum segNet::VisualizationFlags

Visualization flags.

Enumerator
VISUALIZE_OVERLAY	Overlay the segmentation class colors with alpha blending.
VISUALIZE_MASK	View just the colorized segmentation class mask.

Constructor & Destructor Documentation

◆ ~segNet()

virtual segNet::~segNet ( )

virtual

Destroy.

◆ segNet()

segNet::segNet ( )

protected

Member Function Documentation

◆ classify()

bool segNet::classify ( const char * ignore_class )

protected

◆ Create() [1/4]

static segNet* segNet::Create	(	const char *	network = `"fcn-resnet18-voc"`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`
	)

static

Load a pre-trained model.

See also: SEGNET_USAGE_STRING for the models available.

◆ Create() [2/4]

static segNet* segNet::Create	(	const char *	prototxt_path,
		const char *	model_path,
		const char *	class_labels,
		const char *	class_colors = `NULL`,
		const char *	input = `SEGNET_DEFAULT_INPUT`,
		const char *	output = `SEGNET_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
class_labels	File path to list of class name labels
class_colors	File path to list of class colors
input	Name of the input layer blob.

See also: SEGNET_DEFAULT_INPUT

Parameters

output Name of the output layer blob.

See also: SEGNET_DEFAULT_OUTPUT

Parameters

maxBatchSize The maximum batch size that the network will support and be optimized for.

◆ Create() [3/4]

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

static

Load a new network instance by parsing the command line.

◆ Create() [4/4]

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

static

Load a new network instance by parsing the command line.

◆ FilterModeFromStr()

static FilterMode segNet::FilterModeFromStr	(	const char *	str,
		FilterMode	default_value = `FILTER_LINEAR`
	)

static

Parse a string from one of the FilterMode values.

Valid strings are "point", and "linear"

Returns: one of the segNet::FilterMode enums, or default segNet::FILTER_LINEAR on an error.

◆ FindClassID()

int segNet::FindClassID ( const char * label_name )

Find the ID of a particular class (by label name).

◆ GetClassColor()

float4 segNet::GetClassColor ( uint32_t id ) const

inline

Retrieve the RGBA visualization color a particular class.

◆ GetClassDesc()

const char* segNet::GetClassDesc ( uint32_t id ) const

inline

Retrieve the description of a particular class.

◆ GetClassLabel()

const char* segNet::GetClassLabel ( uint32_t id ) const

inline

Retrieve the description of a particular class.

◆ GetClassPath()

const char* segNet::GetClassPath ( ) const

inline

Retrieve the path to the file containing the class label descriptions.

◆ GetGridHeight()

uint32_t segNet::GetGridHeight ( ) const

inline

Retrieve the number of rows in the classification grid.

This indicates the resolution of the raw segmentation output.

◆ GetGridWidth()

uint32_t segNet::GetGridWidth ( ) const

inline

Retrieve the number of columns in the classification grid.

This indicates the resolution of the raw segmentation output.

◆ GetNumClasses()

uint32_t segNet::GetNumClasses ( ) const

inline

Retrieve the number of object classes supported in the detector.

◆ GetOverlayAlpha()

float segNet::GetOverlayAlpha ( ) const

Retrieve the overlay alpha blending value for classes that don't have it explicitly set.

◆ loadClassColors()

bool segNet::loadClassColors ( const char * filename )

protected

◆ loadClassLabels()

bool segNet::loadClassLabels ( const char * filename )

protected

◆ Mask() [1/4]

bool segNet::Mask	(	float *	output,
		uint32_t	width,
		uint32_t	height,
		FilterMode	filter = `FILTER_LINEAR`
	)

Produce a colorized RGBA segmentation mask.

Deprecated:: this overload is for legacy compatibility. It expects float4 RGBA image.

◆ Mask() [2/4]

template<typename T >

bool segNet::Mask	(	T *	output,
		uint32_t	width,
		uint32_t	height,
		FilterMode	filter = `FILTER_LINEAR`
	)

inline

Produce a colorized segmentation mask.

◆ Mask() [3/4]

bool segNet::Mask	(	uint8_t *	output,
		uint32_t	width,
		uint32_t	height
	)

Produce a grayscale binary segmentation mask, where the pixel values correspond to the class ID of the corresponding class type.

◆ Mask() [4/4]

bool segNet::Mask	(	void *	output,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		FilterMode	filter = `FILTER_LINEAR`
	)

Produce a colorized segmentation mask.

◆ Overlay() [1/3]

bool segNet::Overlay	(	float *	output,
		uint32_t	width,
		uint32_t	height,
		FilterMode	filter = `FILTER_LINEAR`
	)

Produce the segmentation overlay alpha blended on top of the original image.

Deprecated:: this overload is for legacy compatibility. It expects float4 RGBA image.

Parameters

input	float4 input image in CUDA device memory, RGBA colorspace with values 0-255.
output	float4 output image in CUDA device memory, RGBA colorspace with values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).
type	overlay visualization options

Returns: true on success, false on error.

◆ Overlay() [2/3]

template<typename T >

bool segNet::Overlay	(	T *	output,
		uint32_t	width,
		uint32_t	height,
		FilterMode	filter = `FILTER_LINEAR`
	)

inline

Produce the segmentation overlay alpha blended on top of the original image.

Parameters

output	output image in CUDA device memory, RGB/RGBA colorspace with values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).
type	overlay visualization options

Returns: true on success, false on error.

◆ Overlay() [3/3]

bool segNet::Overlay	(	void *	output,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		FilterMode	filter = `FILTER_LINEAR`
	)

Produce the segmentation overlay alpha blended on top of the original image.

Parameters

output	output image in CUDA device memory, RGB/RGBA colorspace with values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).
type	overlay visualization options

Returns: true on success, false on error.

◆ overlayLinear()

bool segNet::overlayLinear	(	void *	input,
		uint32_t	in_width,
		uint32_t	in_height,
		imageFormat	in_format,
		void *	output,
		uint32_t	out_width,
		uint32_t	out_height,
		imageFormat	out_format,
		bool	mask_only
	)

protected

◆ overlayPoint()

bool segNet::overlayPoint	(	void *	input,
		uint32_t	in_width,
		uint32_t	in_height,
		imageFormat	in_format,
		void *	output,
		uint32_t	out_width,
		uint32_t	out_height,
		imageFormat	out_format,
		bool	mask_only
	)

protected

◆ Process() [1/3]

bool segNet::Process	(	float *	input,
		uint32_t	width,
		uint32_t	height,
		const char *	ignore_class = `"void"`
	)

Perform the initial inferencing processing portion of the segmentation.

The results can then be visualized using the Overlay() and Mask() functions.

Deprecated:: this overload is for legacy compatibility. It expects float4 RGBA image.

Parameters

input	float4 input image in CUDA device memory, RGBA colorspace with values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).

◆ Process() [2/3]

template<typename T >

bool segNet::Process	(	T *	input,
		uint32_t	width,
		uint32_t	height,
		const char *	ignore_class = `"void"`
	)

inline

Perform the initial inferencing processing portion of the segmentation.

The results can then be visualized using the Overlay() and Mask() functions.

Parameters

input	the input image in CUDA device memory, with pixel values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).

◆ Process() [3/3]

bool segNet::Process	(	void *	input,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		const char *	ignore_class = `"void"`
	)

Perform the initial inferencing processing portion of the segmentation.

The results can then be visualized using the Overlay() and Mask() functions.

Parameters

input	the input image in CUDA device memory, with pixel values 0-255.
width	width of the input image in pixels.
height	height of the input image in pixels.
ignore_class	label name of class to ignore in the classification (or NULL to process all).

◆ saveClassLegend()

bool segNet::saveClassLegend ( const char * filename )

protected

◆ SetClassColor() [1/2]

void segNet::SetClassColor	(	uint32_t	classIndex,
		const float4 &	color
	)

Set the visualization color of a particular class of object.

◆ SetClassColor() [2/2]

void segNet::SetClassColor	(	uint32_t	classIndex,
		float	r,
		float	g,
		float	b,
		float	a = `255.0f`
	)

Set the visualization color of a particular class of object.

◆ SetOverlayAlpha()

void segNet::SetOverlayAlpha	(	float	alpha,
		bool	explicit_exempt = `true`
	)

Set overlay alpha blending value for all classes (between 0-255), (optionally except for those that have been explicitly set).

◆ Usage()

static const char* segNet::Usage ( )

inlinestatic

Usage string for command line arguments to Create()

◆ VisualizationFlagsFromStr()

static uint32_t segNet::VisualizationFlagsFromStr	(	const char *	str,
		uint32_t	default_value = `VISUALIZE_OVERLAY`
	)

static

Parse a string of one of more VisualizationMode values.

Valid strings are "overlay" "mask" "overlay|mask" "overlay,mask" ect.

Member Data Documentation

◆ mClassColors

float4* segNet::mClassColors

protected

array of overlay colors in shared CPU/GPU memory

◆ mClassLabels

std::vector<std::string> segNet::mClassLabels

protected

◆ mClassMap

uint8_t* segNet::mClassMap

protected

runtime buffer for the argmax-classified class index of each tile

◆ mClassPath

std::string segNet::mClassPath

protected

◆ mColorsAlphaSet

bool* segNet::mColorsAlphaSet

protected

true if class color had been explicitly set from file or user

◆ mLastInputFormat

imageFormat segNet::mLastInputFormat

protected

pixel format of last input image

◆ mLastInputHeight

uint32_t segNet::mLastInputHeight

protected

height in pixels of last input image to be processed

◆ mLastInputImg

void* segNet::mLastInputImg

protected

last input image to be processed, stored for overlay

◆ mLastInputWidth

uint32_t segNet::mLastInputWidth

protected

width in pixels of last input image to be processed

Macro Definition Documentation

◆ SEGNET_DEFAULT_ALPHA

#define SEGNET_DEFAULT_ALPHA 150

Default alpha blending value used during overlay.

◆ SEGNET_DEFAULT_INPUT

#define SEGNET_DEFAULT_INPUT "input_0"

Name of default input blob for segmentation model.

◆ SEGNET_DEFAULT_OUTPUT

#define SEGNET_DEFAULT_OUTPUT "output_0"

Name of default output blob for segmentation model.

◆ SEGNET_MODEL_TYPE

#define SEGNET_MODEL_TYPE "segmentation"

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

◆ SEGNET_USAGE_STRING

#define SEGNET_USAGE_STRING

Value:

                  "segNet arguments: \n"                                                        \
                  "  --network=NETWORK    pre-trained model to load, one of the following:\n"   \
                  "                           * fcn-resnet18-cityscapes-512x256\n"                      \
                  "                           * fcn-resnet18-cityscapes-1024x512\n"                     \
                  "                           * fcn-resnet18-cityscapes-2048x1024\n"                    \
                  "                           * fcn-resnet18-deepscene-576x320\n"                       \
                  "                           * fcn-resnet18-deepscene-864x480\n"                       \
                  "                           * fcn-resnet18-mhp-512x320\n"                                     \
                  "                           * fcn-resnet18-mhp-640x360\n"                                     \
                  "                           * fcn-resnet18-voc-320x320 (default)\n"                   \
                  "                           * fcn-resnet18-voc-512x320\n"                                     \
                  "                           * fcn-resnet18-sun-512x400\n"                                     \
                  "                           * fcn-resnet18-sun-640x512\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"                             \
                  "  --colors=COLORS      path to text file containing the colors for each class\n"                             \
                  "  --input-blob=INPUT   name of the input layer (default: '" SEGNET_DEFAULT_INPUT "')\n"              \
                  "  --output-blob=OUTPUT name of the output layer (default: '" SEGNET_DEFAULT_OUTPUT "')\n"            \
            "  --alpha=ALPHA        overlay alpha blending value, range 0-255 (default: 150)\n"                 \
                  "  --visualize=VISUAL   visualization flags (e.g. --visualize=overlay,mask)\n"                                \
                  "                       valid combinations are:  'overlay', 'mask'\n"                                         \
                  "  --profile            enable layer profiling in TensorRT\n\n"

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

Classes

Macros

Detailed Description

Class Documentation

◆ segNet

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Member Enumeration Documentation

◆ FilterMode

◆ VisualizationFlags

Constructor & Destructor Documentation

◆ ~segNet()

◆ segNet()

Member Function Documentation

◆ classify()

◆ Create() [1/4]

◆ Create() [2/4]

◆ Create() [3/4]

◆ Create() [4/4]

◆ FilterModeFromStr()

◆ FindClassID()

◆ GetClassColor()

◆ GetClassDesc()

◆ GetClassLabel()

◆ GetClassPath()

◆ GetGridHeight()

◆ GetGridWidth()

◆ GetNumClasses()

◆ GetOverlayAlpha()

◆ loadClassColors()

◆ loadClassLabels()

◆ Mask() [1/4]

◆ Mask() [2/4]

◆ Mask() [3/4]

◆ Mask() [4/4]

◆ Overlay() [1/3]

◆ Overlay() [2/3]

◆ Overlay() [3/3]

◆ overlayLinear()

◆ overlayPoint()

◆ Process() [1/3]

◆ Process() [2/3]

◆ Process() [3/3]

◆ saveClassLegend()

◆ SetClassColor() [1/2]

◆ SetClassColor() [2/2]

◆ SetOverlayAlpha()

◆ Usage()

◆ VisualizationFlagsFromStr()

Member Data Documentation

◆ mClassColors

◆ mClassLabels

◆ mClassMap

◆ mClassPath

◆ mColorsAlphaSet

◆ mLastInputFormat

◆ mLastInputHeight

◆ mLastInputImg

◆ mLastInputWidth

Macro Definition Documentation

◆ SEGNET_DEFAULT_ALPHA

◆ SEGNET_DEFAULT_INPUT

◆ SEGNET_DEFAULT_OUTPUT

◆ SEGNET_MODEL_TYPE

◆ SEGNET_USAGE_STRING