cv::gapi::ie::Params< cv::gapi::Generic > Class Reference

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

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

Public Member Functions
	Params (const std::string &tag, const std::string &model, const std::string &device)
	Params (const std::string &tag, const std::string &model, const std::string &weights, const std::string &device)
	Class constructor.
GBackend	backend () const
Params &	cfgBatchSize (const size_t size)
Params &	cfgContextParams (const cv::util::any &ctx_cfg)
	Specifies configuration for RemoteContext in InferenceEngine.
Params &	cfgInferMode (InferMode mode)
Params< cv::gapi::Generic > &	cfgInputLayers (const typename PortCfg< cv::gapi::Generic >::In &layer_names)
	Specifies sequence of network input layers names for inference.
Params &	cfgInputLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgInputLayout (std::string layout)
Params &	cfgInputReshape (const std::map< std::string, std::vector< std::size_t > > &reshape_table)
Params &	cfgInputReshape (const std::string &layer_name, const std::vector< size_t > &layer_dims)
Params &	cfgInputReshape (const std::unordered_set< std::string > &layer_names)
Params &	cfgInputReshape (std::map< std::string, std::vector< std::size_t > > &&reshape_table)
Params &	cfgInputReshape (std::string &&layer_name, std::vector< size_t > &&layer_dims)
Params &	cfgInputReshape (std::unordered_set< std::string > &&layer_names)
Params &	cfgNumRequests (size_t nireq)
Params< cv::gapi::Generic > &	cfgOutputLayers (const typename PortCfg< cv::gapi::Generic >::Out &layer_names)
	Specifies sequence of network output layers names for inference.
Params &	cfgOutputLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgOutputLayout (std::string layout)
Params &	cfgOutputPrecision (detail::ParamDesc::PrecisionMapT precision_map)
Params &	cfgOutputPrecision (detail::ParamDesc::PrecisionT precision)
Params< cv::gapi::Generic > &	cfgPreprocessingParams (const cv::gapi::wip::onevpl::Device &device, const cv::gapi::wip::onevpl::Context &ctx)
Params &	cfgResize (detail::AttrMap< int > interpolation)
Params &	cfgResize (int interpolation)
Params &	constInput (const std::string &layer_name, const cv::Mat &data, TraitAs hint=TraitAs::TENSOR)
cv::util::any	params () const
Params &	pluginConfig (const IEConfig &cfg)
Params &	pluginConfig (IEConfig &&cfg)
std::string	tag () const

Protected Attributes
detail::ParamDesc	desc
std::string	m_tag

Constructor & Destructor Documentation

Params() [1/2]

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

inline

Class constructor.

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

Parameters

tag	string tag of the network for which these parameters are intended.
model	path to topology IR (.xml file).
weights	path to weights (.bin file).
device	target device to use.

Here is the call graph for this function:

Params() [2/2]

cv::gapi::ie::Params< cv::gapi::Generic >::Params ( const std::string & tag, 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.

This constructor for pre-compiled networks. Model is imported from pre-compiled blob.

Parameters

tag	string tag of the network for which these parameters are intended.
model	path to model.
device	target device to use.

Here is the call graph for this function:

Member Function Documentation

backend()

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

inline

Here is the call graph for this function:

cfgBatchSize()

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

inline

See also

ie::Params::cfgBatchSize

Here is the call graph for this function:

cfgContextParams()

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

cfgInferMode()

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

inline

See also

ie::Params::cfgInferAPI

Here is the call graph for this function:

cfgInputLayers()

Params< cv::gapi::Generic > & cv::gapi::ie::Params< cv::gapi::Generic >::cfgInputLayers ( const typename PortCfg< cv::gapi::Generic >::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]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

cfgInputLayout() [2/2]

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

inline

See also

ie::Params::cfgInputLayout

Here is the call graph for this function:

cfgInputReshape() [1/6]

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

inline

See also

ie::Params::cfgInputReshape

Here is the call graph for this function:

cfgInputReshape() [2/6]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgInputReshape() [3/6]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgInputReshape() [4/6]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgInputReshape() [5/6]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgInputReshape() [6/6]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgNumRequests()

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

inline

See also

ie::Params::cfgNumRequests.

Here is the call graph for this function:

cfgOutputLayers()

Params< cv::gapi::Generic > & cv::gapi::ie::Params< cv::gapi::Generic >::cfgOutputLayers ( const typename PortCfg< cv::gapi::Generic >::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]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

cfgOutputLayout() [2/2]

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

inline

See also

ie::Params::cfgOutputLayout

Here is the call graph for this function:

cfgOutputPrecision() [1/2]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

cfgOutputPrecision() [2/2]

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

inline

See also

ie::Params::cfgOutputPrecision

Here is the call graph for this function:

cfgPreprocessingParams()

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

inline

cfgResize() [1/2]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

cfgResize() [2/2]

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

inline

See also

ie::Params::cfgResize

Here is the call graph for this function:

constInput()

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

inline

See also

ie::Params::constInput.

Here is the call graph for this function:

params()

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

inline

pluginConfig() [1/2]

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

inline

See also

ie::Params::pluginConfig.

Here is the call graph for this function:

pluginConfig() [2/2]

Params & cv::gapi::ie::Params< cv::gapi::Generic >::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.

Here is the call graph for this function:

tag()

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

inline

Member Data Documentation

desc

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

protected

m_tag

std::string cv::gapi::ie::Params< cv::gapi::Generic >::m_tag

protected

---

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

• opencv2/gapi/infer/ie.hpp