#include <jevois/DNN/PreProcessor.H>

Pre-Processor for neural network pipeline.

This is the first step in a deep neural network processing Pipeline.

Derived classes must implement the pure virtual methods:

process(): process an input image and generate some tensors (blobs)
report(): describe what process() did to humans
freeze(): freeze/unfreeze parameters that users should not change at runtime

They should keep some internal state about what to report, since report() is always called on every frame, but process() may be called less often if the network is slow.

Definition at line 108 of file PreProcessor.H.

Inheritance diagram for jevois::dnn::PreProcessor:

[legend]

Collaboration diagram for jevois::dnn::PreProcessor:

[legend]

Public Member Functions
	PreProcessor (std::string const &instance)
	Constructor.

virtual	~PreProcessor ()
	Destructor.

virtual void	freeze (bool doit)=0
	Freeze/unfreeze parameters that users should not change while running.

std::vector< cv::Mat >	process (jevois::RawImage const &img, std::vector< vsi_nn_tensor_attr_t > const &attrs)
	Extract blobs from input image.

virtual void	sendreport (jevois::StdModule mod, jevois::RawImage outimg=nullptr, jevois::OptGUIhelper *helper=nullptr, bool overlay=true, bool idle=false)
	Report what happened in last process() to console/output video/GUI.

cv::Size const &	imagesize () const
	Access the last processed image size.

std::vector< cv::Mat > const &	blobs () const
	Access the last computed blobs (or empty if process() has not yet been called)

cv::Size	blobsize (size_t num) const
	Access the width and height of a given blob, accounting for NCHW or NHWC.

void	b2i (float &x, float &y, size_t blobnum=0)
	Convert coordinates from blob back to original image.

void	b2i (float &x, float &y, cv::Size const &bsiz, bool letterboxed)
	Convert coordinates from blob back to original image, given a known blob size.

void	b2is (float &sx, float &sy, size_t blobnum=0)
	Convert box size from blob back to original image.

void	b2is (float &sx, float &sy, cv::Size const &bsiz, bool letterboxed)
	Convert box size from blob back to original image, given a known blob size.

cv::Rect	getUnscaledCropRect (size_t blobnum=0)
	Get unscaled crop rectangle in image coordinates.

void	getUnscaledCropRect (size_t blobnum, int &tlx, int &tly, int &brx, int &bry)
	Get unscaled crop rectangle in image coordinates.

void	i2b (float &x, float &y, size_t blobnum=0)
	Convert coordinates from image to blob.

void	i2b (float &x, float &y, cv::Size const &bsiz, bool letterboxed)
	Convert coordinates from image to blob.

std::shared_ptr< PreProcessorForPython >	getPreProcForPy () const
	Get a pointer to our python-friendly interface.

Public Member Functions inherited from jevois::Component
	Component (std::string const &instance)
	Constructor.

virtual	~Component ()
	Virtual destructor for safe inheritance.

template<class Comp , typename... Args>
std::shared_ptr< Comp >	addSubComponent (std::string const &instance, Args &&...args)
	Pseudo-constructor: construct and add another component as a subcomponent of this one.

template<class Comp >
void	removeSubComponent (std::shared_ptr< Comp > &component)
	Remove a sub-Component from this Component, by shared_ptr.

void	removeSubComponent (std::string const &instance, bool warnIfNotFound=true)
	Remove a sub-Component from this Component, by instance name.

template<class Comp = jevois::Component>
std::shared_ptr< Comp >	getSubComponent (std::string const &instance) const
	Get a sub-component by instance name.

bool	isTopLevel () const
	Returns true if this component is top-level, i.e., its parent is jevois::Manager.

bool	initialized () const
	Has this component been initialized yet?

std::string const &	className () const
	The class name of this component.

std::string const &	instanceName () const
	The instance name of this component.

template<typename T >
std::vector< std::string >	setParamVal (std::string const &paramdescriptor, T const &val)
	Set a parameter value.

template<typename T >
void	setParamValUnique (std::string const &paramdescriptor, T const &val)
	Set a parameter value, simple version assuming only one parameter match.

template<typename T >
std::vector< std::pair< std::string, T > >	getParamVal (std::string const &paramdescriptor) const
	Get parameter(s) value(s) by descriptor.

template<typename T >
T	getParamValUnique (std::string const &paramdescriptor) const
	Get a parameter value, simple version assuming only one parameter match.

std::vector< std::string >	setParamString (std::string const &paramdescriptor, std::string const &val)
	Set a parameter value, by string.

void	setParamStringUnique (std::string const &paramdescriptor, std::string const &val)
	Set a parameter value by string, simple version assuming only one parameter match.

std::vector< std::pair< std::string, std::string > >	getParamString (std::string const &paramdescriptor) const
	Get a parameter value, by string.

std::string	getParamStringUnique (std::string const &paramdescriptor) const
	Get a parameter value by string, simple version assuming only one parameter match.

void	freezeParam (std::string const &paramdescriptor, bool doit)
	Freeze/unfreeze a parameter, by name, see ParameterBase::freeze()

void	freezeAllParams (bool doit)
	Freeze all parameters.

void	hideParam (std::string const &paramdescriptor, bool doit)
	Hide/unhide a parameter, by name, see ParameterBase::hide()

void	hideAllParams (bool doit)
	Hide all parameters.

std::string	descriptor () const
	Get our full descriptor (including all parents) as [Instancename]:[...]:[...].

void	setParamsFromFile (std::string const &filename)
	Set some parameters from a file.

std::istream &	setParamsFromStream (std::istream &is, std::string const &absfile)
	Set some parameters from an open stream.

virtual void	paramInfo (std::shared_ptr< UserInterface > s, std::map< std::string, std::string > &categs, bool skipFrozen, std::string const &cname="", std::string const &pfx="")
	Get machine-oriented descriptions of all parameters.

void	foreachParam (std::function< void(std::string const &compname, ParameterBase *p)> func, std::string const &cname="")
	Run a function on every param we hold.

template<typename T >
std::shared_ptr< DynamicParameter< T > >	addDynamicParameter (std::string const &name, std::string const &description, T const &defaultValue, ParameterCategory const &category)
	Add a new parameter after the Component has already been constructed.

template<typename T , template< typename > class ValidValuesSpec>
std::shared_ptr< DynamicParameter< T > >	addDynamicParameter (std::string const &name, std::string const &description, T const &defaultValue, ValidValuesSpec< T > const &validValuesSpec, ParameterCategory const &category)
	Add a new parameter after the Component has already been constructed.

template<typename T >
void	setDynamicParameterCallback (std::string const &name, std::function< void(T const &)> cb, bool callnow=true)
	Register a callback with a previously created dynamic parameter.

void	removeDynamicParameter (std::string const &name, bool throw_if_not_found=true)
	Remove a previously added dynamic parameter.

void	setPath (std::string const &path)
	Assign a filesystem path to this component.

std::filesystem::path	absolutePath (std::filesystem::path const &path="")
	If given path is relative (not starting with /), prepend the Component path to it.

Public Member Functions inherited from jevois::ParameterRegistry
virtual	~ParameterRegistry ()
	Virtual destructor for safe inheritance.

Protected Member Functions
virtual std::vector< cv::Mat >	process (cv::Mat const &img, bool isrgb, std::vector< vsi_nn_tensor_attr_t > const &attrs, std::vector< cv::Rect > &crops)=0
	Extract blobs from input image.

virtual void	report (jevois::StdModule mod, jevois::RawImage outimg=nullptr, jevois::OptGUIhelper *helper=nullptr, bool overlay=true, bool idle=false)=0
	Report what happened in last process() to console/output video/GUI.

Protected Member Functions inherited from jevois::Component
virtual void	preInit ()
	Called before all sub-Components are init()ed.

virtual void	postInit ()
	Called after all sub-Components are init()ed.

virtual void	preUninit ()
	Called before all sub-Components are uninit()ed.

virtual void	postUninit ()
	Called after all sub-Components are uninit()ed.

Protected Member Functions inherited from jevois::ParameterRegistry
void	addParameter (ParameterBase *const param)
	The Parameter class uses this method to register itself on construction with its owning Component.

void	removeParameter (ParameterBase *const param)
	The Parameter class uses this method to un-register itself on destruction with its owning Component.

void	callbackInitCall ()
	For all parameters that have a callback which has never been called, call it with the default param value.

Related Symbols
(Note that these are not member symbols.)
	JEVOIS_DECLARE_PARAMETER (rgb, bool, "When true, model works with RGB input images instead BGR ones", true, ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (scale, float, "Value scaling factor applied to input pixels after mean subtraction, " "or 0.0 to extract an unscaled UINT8 blob, typically for use with quantized networks", 2.0F/255.0F, ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (mean, cv::Scalar, "Mean values subtracted from input image, in the same RGB/BGR " "order as the network's input", cv::Scalar(127.5F, 127.5F, 127.5F), ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (stdev, cv::Scalar, "Input image is divided by stdev after mean subtraction and scale " "factor are applied. This is rarely used. Same RGB/BGR order as the network's input", cv::Scalar(1.0F, 1.0F, 1.0F), ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (letterbox, bool, "When true, extract the largest possible box from the input image " "with same aspect ratio as the network's input tensor, and then rescale it to that " "tensor's width and height (hence with cropping but no distortion). Otherwise, use " "the whole image and rescale it to the network's input width and height with some " "possible stretching.", false, ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (showin, bool, "Show outline of cropped image fed to network", true, ParamCateg)
	Parameter.

	JEVOIS_DECLARE_PARAMETER (details, bool, "Show more details about the pre-processing steps", false, ParamCateg)
	Parameter.

	JEVOIS_DEFINE_ENUM_CLASS (InterpMode,(Nearest)(Linear)(Cubic)(Area)(Lanczos4))
	Enum for image resizing modes.

	JEVOIS_DECLARE_PARAMETER (interp, InterpMode, "Image interpolation to use when resizing the input image " "from camera to network input dims", InterpMode::Nearest, InterpMode_Values, ParamCateg)
	Parameter.

Constructor & Destructor Documentation

◆ PreProcessor()

jevois::dnn::PreProcessor::PreProcessor ( std::string const & instance )

Constructor.

Definition at line 26 of file PreProcessor.C.

◆ ~PreProcessor()

jevois::dnn::PreProcessor::~PreProcessor ( )

virtual

Destructor.

Definition at line 31 of file PreProcessor.C.

Member Function Documentation

◆ b2i() [1/2]

void jevois::dnn::PreProcessor::b2i	(	float &	x,
		float &	y,
		cv::Size const &	bsiz,
		bool	letterboxed
	)

Convert coordinates from blob back to original image, given a known blob size.

Given coords x,y should be in [0..w-1]x[0..h-1] where w,h are the blob's width and height. This is useful to convert detected boxes back into original input coordinates.

Definition at line 60 of file PreProcessor.C.

References LFATAL.

◆ b2i() [2/2]

void jevois::dnn::PreProcessor::b2i	(	float &	x,
		float &	y,
		size_t	blobnum = `0`
	)

Convert coordinates from blob back to original image.

Given coords x,y should be in [0..w-1]x[0..h-1] where w,h are the blob's width and height. This is useful to convert detected boxes back into original input coordinates.

Definition at line 50 of file PreProcessor.C.

References LFATAL.

Referenced by jevois::dnn::PostProcessorDetect::process(), jevois::dnn::PostProcessorDetectOBB::process(), jevois::dnn::PostProcessorPose::process(), and jevois::dnn::PostProcessorYuNet::process().

◆ b2is() [1/2]

void jevois::dnn::PreProcessor::b2is	(	float &	sx,
		float &	sy,
		cv::Size const &	bsiz,
		bool	letterboxed
	)

Convert box size from blob back to original image, given a known blob size.

Definition at line 91 of file PreProcessor.C.

References LFATAL.

◆ b2is() [2/2]

void jevois::dnn::PreProcessor::b2is	(	float &	sx,
		float &	sy,
		size_t	blobnum = `0`
	)

Convert box size from blob back to original image.

Definition at line 81 of file PreProcessor.C.

References LFATAL.

Referenced by jevois::dnn::PostProcessorDetectOBB::process().

◆ blobs()

std::vector< cv::Mat > const & jevois::dnn::PreProcessor::blobs ( ) const

Access the last computed blobs (or empty if process() has not yet been called)

Definition at line 35 of file PreProcessor.C.

◆ blobsize()

cv::Size jevois::dnn::PreProcessor::blobsize ( size_t num ) const

Access the width and height of a given blob, accounting for NCHW or NHWC.

Definition at line 43 of file PreProcessor.C.

References jevois::dnn::attrsize(), and LFATAL.

Referenced by jevois::dnn::PostProcessorDetect::process(), jevois::dnn::PostProcessorPose::process(), and jevois::dnn::PostProcessorYuNet::process().

◆ freeze()

virtual void jevois::dnn::PreProcessor::freeze ( bool doit )

pure virtual

Freeze/unfreeze parameters that users should not change while running.

Implemented in jevois::dnn::PreProcessorBlob, and jevois::dnn::PreProcessorPython.

◆ getPreProcForPy()

std::shared_ptr< jevois::dnn::PreProcessorForPython > jevois::dnn::PreProcessor::getPreProcForPy ( ) const

Get a pointer to our python-friendly interface.

Definition at line 156 of file PreProcessor.C.

Referenced by jevois::dnn::PostProcessorPythonImpl::process().

◆ getUnscaledCropRect() [1/2]

void jevois::dnn::PreProcessor::getUnscaledCropRect	(	size_t	blobnum,
		int &	tlx,
		int &	tly,
		int &	brx,
		int &	bry
	)

Get unscaled crop rectangle in image coordinates.

This is useful to display an image overlay on top of the input image.

Definition at line 117 of file PreProcessor.C.

◆ getUnscaledCropRect() [2/2]

cv::Rect jevois::dnn::PreProcessor::getUnscaledCropRect ( size_t blobnum = 0 )

Get unscaled crop rectangle in image coordinates.

This is useful to display an image overlay on top of the input image.

Definition at line 110 of file PreProcessor.C.

References LFATAL.

Referenced by jevois::dnn::PostProcessorSegment::process().

◆ i2b() [1/2]

void jevois::dnn::PreProcessor::i2b	(	float &	x,
		float &	y,
		cv::Size const &	bsiz,
		bool	letterboxed
	)

Convert coordinates from image to blob.

Given coords x,y should be in [0..w-1]x[0..h-1] where w,h are the image's width and height. This is useful to convert mouse coordinates (after they have been converted from screen to image coords) to locations within an input blob.

Definition at line 134 of file PreProcessor.C.

References LFATAL.

◆ i2b() [2/2]

void jevois::dnn::PreProcessor::i2b	(	float &	x,
		float &	y,
		size_t	blobnum = `0`
	)

Convert coordinates from image to blob.

Given coords x,y should be in [0..w-1]x[0..h-1] where w,h are the image's width and height. This is useful to convert mouse coordinates (after they have been converted from screen to image coords) to locations within an input blob.

Definition at line 124 of file PreProcessor.C.

References LFATAL.

◆ imagesize()

cv::Size const & jevois::dnn::PreProcessor::imagesize ( ) const

Access the last processed image size.

Definition at line 39 of file PreProcessor.C.

Referenced by jevois::dnn::PostProcessorDetect::process(), jevois::dnn::PostProcessorDetectOBB::process(), jevois::dnn::PostProcessorPose::process(), and jevois::dnn::PostProcessorYuNet::process().

◆ process() [1/2]

virtual std::vector< cv::Mat > jevois::dnn::PreProcessor::process	(	cv::Mat const &	img,
		bool	isrgb,
		std::vector< vsi_nn_tensor_attr_t > const &	attrs,
		std::vector< cv::Rect > &	crops
	)

protectedpure virtual

Extract blobs from input image.

isrgb should be true if the given img has RGB color order, or false for BGR. Only 3-channel byte images are supported as input.

Implemented in jevois::dnn::PreProcessorBlob, and jevois::dnn::PreProcessorPython.

◆ process() [2/2]

std::vector< cv::Mat > jevois::dnn::PreProcessor::process	(	jevois::RawImage const &	img,
		std::vector< vsi_nn_tensor_attr_t > const &	attrs
	)

Extract blobs from input image.

Definition at line 160 of file PreProcessor.C.

References jevois::rawimage::convertToCvBGR(), jevois::rawimage::convertToCvRGB(), jevois::rawimage::cvImage(), jevois::RawImage::fmt, jevois::RawImage::height, LFATAL, and jevois::RawImage::width.

◆ report()

virtual void jevois::dnn::PreProcessor::report	(	jevois::StdModule *	mod,
		jevois::RawImage *	outimg = `nullptr`,
		jevois::OptGUIhelper *	helper = `nullptr`,
		bool	overlay = `true`,
		bool	idle = `false`
	)

protectedpure virtual

Report what happened in last process() to console/output video/GUI.

Implemented in jevois::dnn::PreProcessorBlob, and jevois::dnn::PreProcessorPython.

◆ sendreport()

void jevois::dnn::PreProcessor::sendreport	(	jevois::StdModule *	mod,
		jevois::RawImage *	outimg = `nullptr`,
		jevois::OptGUIhelper *	helper = `nullptr`,
		bool	overlay = `true`,
		bool	idle = `false`
	)

virtual

Report what happened in last process() to console/output video/GUI.

Definition at line 184 of file PreProcessor.C.

References jevois::rawimage::drawRect(), jevois::fccstr(), jevois::GUIhelper::i2d(), jevois::yuyv::MedGrey, jevois::dnn::shapestr(), and jevois::RawImage::width.

Friends And Related Symbol Documentation

◆ JEVOIS_DECLARE_PARAMETER() [1/8]

JEVOIS_DECLARE_PARAMETER	(	details	,
		bool	,
		"Show more details about the pre-processing steps"	,
		false	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [2/8]

JEVOIS_DECLARE_PARAMETER	(	interp	,
		InterpMode	,
		"Image interpolation to use when resizing the input image " "from camera to network input dims"	,
		InterpMode::Nearest	,
		InterpMode_Values	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [3/8]

JEVOIS_DECLARE_PARAMETER	(	letterbox	,
		bool	,
		"When	true,
		extract the largest possible box from the input image " "with same aspect ratio as the network 's input	tensor,
		and then rescale it to that " "tensor 's width and height(hence with cropping but no distortion).	Otherwise,
		use " "the whole image and rescale it to the network 's input width and height with some " "possible stretching."	,
		false	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [4/8]

JEVOIS_DECLARE_PARAMETER	(	mean	,
		cv::Scalar	,
		"Mean values subtracted from input	image,
		in the same RGB/BGR " "order as the network 's input"	,
		cv::Scalar(127.5F, 127.5F, 127.5F)	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [5/8]

JEVOIS_DECLARE_PARAMETER	(	rgb	,
		bool	,
		"When	true,
		model works with RGB input images instead BGR ones"	,
		true	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [6/8]

JEVOIS_DECLARE_PARAMETER	(	scale	,
		float	,
		"Value scaling factor applied to input pixels after mean	subtraction,
		" "or 0.0 to extract an unscaled UINT8	blob,
		typically for use with quantized networks"	,
		2.0F/255.	0F,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [7/8]

JEVOIS_DECLARE_PARAMETER	(	showin	,
		bool	,
		"Show outline of cropped image fed to network"	,
		true	,
		ParamCateg
	)

◆ JEVOIS_DECLARE_PARAMETER() [8/8]

JEVOIS_DECLARE_PARAMETER	(	stdev	,
		cv::Scalar	,
		"Input image is divided by stdev after mean subtraction and scale " "factor are applied. This is rarely used. Same RGB/BGR order as the network's input"	,
		cv::Scalar(1.0F, 1.0F, 1.0F)	,
		ParamCateg
	)

◆ JEVOIS_DEFINE_ENUM_CLASS()

JEVOIS_DEFINE_ENUM_CLASS	(	InterpMode	,
		(Nearest)(Linear)(Cubic)(Area)(Lanczos4)
	)

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

include/jevois/DNN/PreProcessor.H
src/jevois/DNN/PreProcessor.C

Public Member Functions

Protected Member Functions

Related Symbols

Constructor & Destructor Documentation

◆ PreProcessor()

◆ ~PreProcessor()

Member Function Documentation

◆ b2i() [1/2]

◆ b2i() [2/2]

◆ b2is() [1/2]

◆ b2is() [2/2]

◆ blobs()

◆ blobsize()

◆ freeze()

◆ getPreProcForPy()

◆ getUnscaledCropRect() [1/2]

◆ getUnscaledCropRect() [2/2]

◆ i2b() [1/2]

◆ i2b() [2/2]

◆ imagesize()

◆ process() [1/2]

◆ process() [2/2]

◆ report()

◆ sendreport()

Friends And Related Symbol Documentation

◆ JEVOIS_DECLARE_PARAMETER() [1/8]

◆ JEVOIS_DECLARE_PARAMETER() [2/8]

◆ JEVOIS_DECLARE_PARAMETER() [3/8]

◆ JEVOIS_DECLARE_PARAMETER() [4/8]

◆ JEVOIS_DECLARE_PARAMETER() [5/8]

◆ JEVOIS_DECLARE_PARAMETER() [6/8]

◆ JEVOIS_DECLARE_PARAMETER() [7/8]

◆ JEVOIS_DECLARE_PARAMETER() [8/8]

◆ JEVOIS_DEFINE_ENUM_CLASS()