This structure provides functions that fill inference parameters for "OpenVINO Toolkit" model. More...

#include <opencv2/gapi/infer/ie.hpp>

Collaboration diagram for cv::gapi::ie::Params< Net >:

Public Member Functions
	Params (const std::string &model, const std::string &device)

	Params (const std::string &model, const std::string &weights, const std::string &device)
	Class constructor.

GBackend	backend () const

Params< Net > &	cfgBatchSize (const size_t size)
	Specifies the inference batch size.

Params &	cfgContextParams (const cv::util::any &ctx_cfg)
	Specifies configuration for RemoteContext in InferenceEngine.

Params &	cfgContextParams (cv::util::any &&ctx_cfg)

Params< Net > &	cfgInferMode (InferMode mode)
	Specifies which api will be used to run inference.

Params< Net > &	cfgInputLayers (const typename PortCfg< Net >::In &layer_names)
	Specifies sequence of network input layers names for inference.

Params< Net > &	cfgInputLayout (detail::AttrMap< std::string > layout_map)

Params< Net > &	cfgInputLayout (std::string layout)
	Specifies the input layout for model.

Params< Net > &	cfgInputReshape (const std::map< std::string, std::vector< std::size_t > > &reshape_table)
	Specifies new input shapes for the network inputs.

Params< Net > &	cfgInputReshape (const std::string &layer_name, const std::vector< size_t > &layer_dims)

Params< Net > &	cfgInputReshape (const std::unordered_set< std::string > &layer_names)

Params< Net > &	cfgInputReshape (std::map< std::string, std::vector< std::size_t > > &&reshape_table)

Params< Net > &	cfgInputReshape (std::string &&layer_name, std::vector< size_t > &&layer_dims)

Params< Net > &	cfgInputReshape (std::unordered_set< std::string > &&layer_names)

Params &	cfgNumRequests (size_t nireq)
	Specifies number of asynchronous inference requests.

Params< Net > &	cfgOutputLayers (const typename PortCfg< Net >::Out &layer_names)
	Specifies sequence of network output layers names for inference.

Params< Net > &	cfgOutputLayout (detail::AttrMap< std::string > layout_map)

Params< Net > &	cfgOutputLayout (std::string layout)
	Specifies the output layout for model.

Params< Net > &	cfgOutputPrecision (detail::ParamDesc::PrecisionMapT precision_map)

Params< Net > &	cfgOutputPrecision (detail::ParamDesc::PrecisionT precision)
	Specifies the output precision for model.

Params< Net > &	cfgPreprocessingParams (const cv::gapi::wip::onevpl::Device &device, const cv::gapi::wip::onevpl::Context &ctx)

Params< Net > &	cfgResize (detail::AttrMap< int > interpolation)

Params< Net > &	cfgResize (int interpolation)
	Specifies resize interpolation algorithm.

Params< Net > &	constInput (const std::string &layer_name, const cv::Mat &data, TraitAs hint=TraitAs::TENSOR)
	Specifies a constant input.

cv::util::any	params () const

Params &	pluginConfig (const IEConfig &cfg)
	Specifies OpenVINO plugin configuration.

Params &	pluginConfig (IEConfig &&cfg)

std::string	tag () const

Protected Attributes
detail::ParamDesc	desc

Detailed Description

template<typename Net>
class cv::gapi::ie::Params< Net >

This structure provides functions that fill inference parameters for "OpenVINO Toolkit" model.

Constructor & Destructor Documentation

◆ Params() [1/2]

template<typename Net >

cv::gapi::ie::Params< Net >::Params	(	const std::string &	model,
		const std::string &	weights,
		const std::string &	device
	)

inline

Class constructor.

Constructs Params based on model information and specifies default values for other inference description parameters. Model is loaded and compiled using "OpenVINO Toolkit".

Parameters

model	Path to topology IR (.xml file).
weights	Path to weights (.bin file).
device	target device to use.

◆ Params() [2/2]

template<typename Net >

cv::gapi::ie::Params< Net >::Params	(	const std::string &	model,
		const std::string &	device
	)

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Use this constructor to work with pre-compiled network. Model is imported from a pre-compiled blob.

Parameters

model	Path to model.
device	target device to use.

Member Function Documentation

◆ backend()

template<typename Net >

GBackend cv::gapi::ie::Params< Net >::backend ( ) const

inline

Here is the call graph for this function:

◆ cfgBatchSize()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgBatchSize ( const size_t size )

inline

Specifies the inference batch size.

The function is used to specify inference batch size. Follow https://docs.openvinotoolkit.org/latest/classInferenceEngine_1_1CNNNetwork.html#a8e9d19270a48aab50cb5b1c43eecb8e9 for additional information

Parameters

size	batch size which will be used.

Returns: reference to this parameter structure.

Here is the call graph for this function:

◆ cfgContextParams() [1/2]

template<typename Net >

Params & cv::gapi::ie::Params< Net >::cfgContextParams ( const cv::util::any & ctx_cfg )

inline

Specifies configuration for RemoteContext in InferenceEngine.

When RemoteContext is configured the backend imports the networks using the context. It also expects cv::MediaFrames to be actually remote, to operate with blobs via the context.

Parameters

ctx_cfg cv::util::any value which holds InferenceEngine::ParamMap.

Returns: reference to this parameter structure.

◆ cfgContextParams() [2/2]

template<typename Net >

Params & cv::gapi::ie::Params< Net >::cfgContextParams ( cv::util::any && ctx_cfg )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Function with an rvalue parameter.

Parameters

ctx_cfg cv::util::any value which holds InferenceEngine::ParamMap.

Returns: reference to this parameter structure.

◆ cfgInferMode()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInferMode ( InferMode mode )

inline

Specifies which api will be used to run inference.

The function is used to specify mode for OpenVINO inference. OpenVINO has two options to run inference:

Asynchronous (using StartAsync: https://docs.openvino.ai/latest/classInferenceEngine_1_1InferRequest.html#doxid-class-inference-engine-1-1-infer-request-1a405293e8423d82a5b45f642a3bef0d24)
Synchronous (using Infer: https://docs.openvino.ai/latest/classInferenceEngine_1_1InferRequest.html#doxid-class-inference-engine-1-1-infer-request-1a3391ce30894abde730523e9ca9371ce8) By default asynchronous mode is used.

Parameters

mode	Inference mode which will be used.

Returns: reference to this parameter structure.

◆ cfgInputLayers()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputLayers ( const typename PortCfg< Net >::In & layer_names )

inline

Specifies sequence of network input layers names for inference.

The function is used to associate cv::gapi::infer<> inputs with the model inputs. Number of names has to match the number of network inputs as defined in G_API_NET(). In case a network has only single input layer, there is no need to specify name manually.

Parameters

layer_names std::array<std::string, N> where N is the number of inputs as defined in the G_API_NET. Contains names of input layers.

Returns: reference to this parameter structure.

◆ cfgInputLayout() [1/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputLayout ( detail::AttrMap< std::string > layout_map )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

layout_map Map of pairs: name of corresponding input layer and its layout in string representation ("NCHW", "NHWC", etc)

Returns: reference to this parameter structure.

◆ cfgInputLayout() [2/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputLayout ( std::string layout )

inline

Specifies the input layout for model.

The function is used to set an input layout for model.

Parameters

layout Layout in string representation ("NCHW", "NHWC", etc) will be applied to all input layers.

Returns: reference to this parameter structure.

◆ cfgInputReshape() [1/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape ( const std::map< std::string, std::vector< std::size_t > > & reshape_table )

inline

Specifies new input shapes for the network inputs.

The function is used to specify new input shapes for the network inputs. Follow https://docs.openvinotoolkit.org/latest/classInferenceEngine_1_1networkNetwork.html for additional information.

Parameters

reshape_table Map of pairs: name of corresponding data and its dimension.

Returns: reference to this parameter structure.

◆ cfgInputReshape() [2/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape	(	const std::string &	layer_name,
		const std::vector< size_t > &	layer_dims
	)

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

layer_name	Name of layer.
layer_dims	New dimensions for this layer.

Returns: reference to this parameter structure.

◆ cfgInputReshape() [3/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape ( const std::unordered_set< std::string > & layer_names )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

layer_names set of names of network layers that will be used for network reshape.

Returns: reference to this parameter structure.

◆ cfgInputReshape() [4/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape ( std::map< std::string, std::vector< std::size_t > > && reshape_table )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

◆ cfgInputReshape() [5/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape	(	std::string &&	layer_name,
		std::vector< size_t > &&	layer_dims
	)

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

◆ cfgInputReshape() [6/6]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgInputReshape ( std::unordered_set< std::string > && layer_names )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

layer_names rvalue set of the selected layers will be reshaped automatically its input image size.

Returns: reference to this parameter structure.

◆ cfgNumRequests()

template<typename Net >

Params & cv::gapi::ie::Params< Net >::cfgNumRequests ( size_t nireq )

inline

Specifies number of asynchronous inference requests.

Parameters

nireq Number of inference asynchronous requests.

Returns: reference to this parameter structure.

◆ cfgOutputLayers()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgOutputLayers ( const typename PortCfg< Net >::Out & layer_names )

inline

Specifies sequence of network output layers names for inference.

The function is used to associate cv::gapi::infer<> outputs with the model outputs. Number of names has to match the number of network outputs as defined in G_API_NET(). In case a network has only single output layer, there is no need to specify name manually.

Parameters

layer_names std::array<std::string, N> where N is the number of outputs as defined in the G_API_NET. Contains names of output layers.

Returns: reference to this parameter structure.

◆ cfgOutputLayout() [1/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgOutputLayout ( detail::AttrMap< std::string > layout_map )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

layout_map Map of pairs: name of corresponding output layer and its layout in string representation ("NCHW", "NHWC", etc)

Returns: reference to this parameter structure.

◆ cfgOutputLayout() [2/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgOutputLayout ( std::string layout )

inline

Specifies the output layout for model.

The function is used to set an output layout for model.

Parameters

layout Layout in string representation ("NCHW", "NHWC", etc) will be applied to all output layers.

Returns: reference to this parameter structure.

◆ cfgOutputPrecision() [1/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgOutputPrecision ( detail::ParamDesc::PrecisionMapT precision_map )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

precision_map Map of pairs: name of corresponding output layer and its precision in OpenCV format (CV_8U, CV_32F, ...)

Returns: reference to this parameter structure.

◆ cfgOutputPrecision() [2/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgOutputPrecision ( detail::ParamDesc::PrecisionT precision )

inline

Specifies the output precision for model.

The function is used to set an output precision for model.

Parameters

precision Precision in OpenCV format (CV_8U, CV_32F, ...) will be applied to all output layers.

Returns: reference to this parameter structure.

◆ cfgPreprocessingParams()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgPreprocessingParams	(	const cv::gapi::wip::onevpl::Device &	device,
		const cv::gapi::wip::onevpl::Context &	ctx
	)

inline

Here is the call graph for this function:

◆ cfgResize() [1/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgResize ( detail::AttrMap< int > interpolation )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

interpolation Map of pairs: name of corresponding input layer and its resize algorithm.

Returns: reference to this parameter structure.

◆ cfgResize() [2/2]

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::cfgResize ( int interpolation )

inline

Specifies resize interpolation algorithm.

The function is used to configure resize preprocessing for input layer.

Parameters

interpolation Resize interpolation algorithm. Supported algorithms: INTER_LINEAR, INTER_AREA.

Returns: reference to this parameter structure.

◆ constInput()

template<typename Net >

Params< Net > & cv::gapi::ie::Params< Net >::constInput	(	const std::string &	layer_name,
		const cv::Mat &	data,
		TraitAs	hint = `TraitAs::TENSOR`
	)

inline

Specifies a constant input.

The function is used to set a constant input. This input has to be a preprocessed tensor if its type is TENSOR. Need to provide name of the network layer which will receive provided data.

Parameters

layer_name	Name of network layer.
data	cv::Mat that contains data which will be associated with network layer.
hint	Input type

See also: cv::gapi::ie::TraitAs.

Returns: reference to this parameter structure.

◆ params()

template<typename Net >

cv::util::any cv::gapi::ie::Params< Net >::params ( ) const

inline

◆ pluginConfig() [1/2]

template<typename Net >

Params & cv::gapi::ie::Params< Net >::pluginConfig ( const IEConfig & cfg )

inline

Specifies OpenVINO plugin configuration.

The function is used to set configuration for OpenVINO plugin. Some parameters can be different for each plugin. Please follow https://docs.openvinotoolkit.org/latest/index.html to check information about specific plugin.

Parameters

cfg	Map of pairs: (config parameter name, config parameter value).

Returns: reference to this parameter structure.

◆ pluginConfig() [2/2]

template<typename Net >

Params & cv::gapi::ie::Params< Net >::pluginConfig ( IEConfig && cfg )

inline

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Function with a rvalue parameter.

Parameters

cfg	rvalue map of pairs: (config parameter name, config parameter value).

Returns: reference to this parameter structure.

◆ tag()

template<typename Net >

std::string cv::gapi::ie::Params< Net >::tag ( ) const

inline

Member Data Documentation

◆ desc

template<typename Net >

detail::ParamDesc cv::gapi::ie::Params< Net >::desc

protected

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

opencv2/gapi/infer/ie.hpp

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ Params() [1/2]

◆ Params() [2/2]

Member Function Documentation

◆ backend()

◆ cfgBatchSize()

◆ cfgContextParams() [1/2]

◆ cfgContextParams() [2/2]

◆ cfgInferMode()

◆ cfgInputLayers()

◆ cfgInputLayout() [1/2]

◆ cfgInputLayout() [2/2]

◆ cfgInputReshape() [1/6]

◆ cfgInputReshape() [2/6]

◆ cfgInputReshape() [3/6]

◆ cfgInputReshape() [4/6]

◆ cfgInputReshape() [5/6]

◆ cfgInputReshape() [6/6]

◆ cfgNumRequests()

◆ cfgOutputLayers()

◆ cfgOutputLayout() [1/2]

◆ cfgOutputLayout() [2/2]

◆ cfgOutputPrecision() [1/2]

◆ cfgOutputPrecision() [2/2]

◆ cfgPreprocessingParams()

◆ cfgResize() [1/2]

◆ cfgResize() [2/2]

◆ constInput()

◆ params()

◆ pluginConfig() [1/2]

◆ pluginConfig() [2/2]

◆ tag()

Member Data Documentation

◆ desc