cv::gapi::ie Namespace Reference

This namespace contains G-API OpenVINO backend functions, structures, and symbols. More...

Namespaces
namespace	detail

Classes
class	Params
	This structure provides functions that fill inference parameters for "OpenVINO Toolkit" model. More...
class	Params< cv::gapi::Generic >
struct	PortCfg
class	PyParams

Typedefs
using	IEConfig = std::map<std::string, std::string>

Enumerations
enum	InferMode {   Sync ,   Async }
enum class	TraitAs : int {   TENSOR ,   IMAGE }

Functions
cv::gapi::GBackend	backend ()
PyParams	params (const std::string &tag, const std::string &model, const std::string &device)
PyParams	params (const std::string &tag, const std::string &model, const std::string &weights, const std::string &device)

Detailed Description

This namespace contains G-API OpenVINO backend functions, structures, and symbols.

Typedef Documentation

IEConfig

using cv::gapi::ie::IEConfig = std::map<std::string, std::string>

Enumeration Type Documentation

InferMode

enum cv::gapi::ie::InferMode

Enumerator
Sync  Python: cv.gapi.ie.Sync
Async  Python: cv.gapi.ie.Async

TraitAs

enum class cv::gapi::ie::TraitAs : int

strong

Specifies how G-API and IE should trait input data

In OpenCV, the same cv::Mat is used to represent both image and tensor data. Sometimes those are hardly distinguishable, so this extra parameter is used to give G-API a hint.

This hint controls how G-API reinterprets the data when converting it to IE Blob format (and which layout/etc is assigned to this data).

Enumerator
TENSOR	G-API traits an associated cv::Mat as a raw tensor and passes dimensions as-is.
IMAGE	G-API traits an associated cv::Mat as an image so creates an "image" blob (NCHW/NHWC, etc)

Function Documentation

backend()

cv::gapi::GBackend cv::gapi::ie::backend

(

)

params() [1/2]

PyParams cv::gapi::ie::params	(	const std::string &	tag,
		const std::string &	model,
		const std::string &	device )

Python:
	cv.gapi.ie.params(	tag, model, weights, device	) ->	retval
	cv.gapi.ie.params(	tag, model, device	) ->	retval

params() [2/2]

PyParams cv::gapi::ie::params	(	const std::string &	tag,
		const std::string &	model,
		const std::string &	weights,
		const std::string &	device )

Python:
	cv.gapi.ie.params(	tag, model, weights, device	) ->	retval
	cv.gapi.ie.params(	tag, model, device	) ->	retval