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

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

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

Public Member Functions
	Params (const std::string &tag, const std::string &blob_path, const std::string &device)
	Params (const std::string &tag, const std::string &model_path, const std::string &bin_path, const std::string &device)
	Class constructor.
GBackend	backend () const
Params &	cfgClampOutputs (bool flag=true)
Params &	cfgEnsureNamedTensors (bool flag=true)
Params< cv::gapi::Generic > &	cfgInputLayers (const std::vector< std::string > &layer_names)
	Specifies sequence of network input layers names for inference.
Params &	cfgInputModelLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgInputModelLayout (std::string layout)
Params &	cfgInputTensorLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgInputTensorLayout (std::string layout)
Params &	cfgMean (detail::AttrMap< std::vector< float > > mean_map)
Params &	cfgMean (std::vector< float > mean_values)
Params &	cfgNumRequests (const size_t nireq)
Params< cv::gapi::Generic > &	cfgOutputLayers (const std::vector< std::string > &layer_names)
	Specifies sequence of network output layers names for inference.
Params &	cfgOutputModelLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgOutputModelLayout (std::string layout)
Params &	cfgOutputTensorLayout (detail::AttrMap< std::string > layout_map)
Params &	cfgOutputTensorLayout (std::string layout)
Params &	cfgOutputTensorPrecision (detail::AttrMap< int > precision_map)
Params &	cfgOutputTensorPrecision (int precision)
Params &	cfgPluginConfig (const detail::ParamDesc::PluginConfigT &config)
Params &	cfgReshape (detail::AttrMap< std::vector< size_t > > new_shape_map)
Params &	cfgReshape (std::vector< size_t > new_shape)
Params &	cfgResize (detail::AttrMap< int > interpolation)
Params &	cfgResize (int interpolation)
Params &	cfgScale (detail::AttrMap< std::vector< float > > scale_map)
Params &	cfgScale (std::vector< float > scale_values)
cv::util::any	params () const
std::string	tag () const

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

Constructor & Destructor Documentation

Params() [1/2]

cv::gapi::ov::Params< cv::gapi::Generic >::Params ( const std::string & tag, const std::string & model_path, const std::string & bin_path, 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

tag	string tag of the network for which these parameters are intended.
model_path	Path to a model.
bin_path	Path to a data file. For IR format (*.bin): If path is empty, will try to read a bin file with the same name as xml. If the bin file with the same name is not found, will load IR without weights. For PDPD (*.pdmodel) and ONNX (*.onnx) formats bin_path isn't used.
device	target device to use.

Here is the call graph for this function:

Params() [2/2]

cv::gapi::ov::Params< cv::gapi::Generic >::Params ( const std::string & tag, const std::string & blob_path, 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.
blob_path	path to the compiled model (*.blob).
device	target device to use.

Here is the call graph for this function:

Member Function Documentation

backend()

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

inline

Here is the call graph for this function:

cfgClampOutputs()

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgClampOutputs ( bool flag = true )

inline

See also

ov::Params::cfgClampOutputs.

Here is the call graph for this function:

cfgEnsureNamedTensors()

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgEnsureNamedTensors ( bool flag = true )

inline

See also

ov::Params::cfgEnsureNamedTensors.

Here is the call graph for this function:

cfgInputLayers()

Params< cv::gapi::Generic > & cv::gapi::ov::Params< cv::gapi::Generic >::cfgInputLayers ( const std::vector< std::string > & 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.

cfgInputModelLayout() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgInputModelLayout ( 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.

Here is the call graph for this function:

cfgInputModelLayout() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgInputModelLayout ( std::string layout )

inline

See also

ov::Params::cfgInputModelLayout.

Here is the call graph for this function:

cfgInputTensorLayout() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgInputTensorLayout ( 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.

Here is the call graph for this function:

cfgInputTensorLayout() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgInputTensorLayout ( std::string layout )

inline

See also

ov::Params::cfgInputTensorLayout.

Here is the call graph for this function:

cfgMean() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgMean ( detail::AttrMap< std::vector< float > > mean_map )

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:

cfgMean() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgMean ( std::vector< float > mean_values )

inline

See also

ov::Params::cfgMean.

Here is the call graph for this function:

cfgNumRequests()

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

inline

See also

ov::Params::cfgNumRequests.

Here is the call graph for this function:

cfgOutputLayers()

Params< cv::gapi::Generic > & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputLayers ( const std::vector< std::string > & 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.

cfgOutputModelLayout() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputModelLayout ( 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.

Here is the call graph for this function:

cfgOutputModelLayout() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputModelLayout ( std::string layout )

inline

See also

ov::Params::cfgOutputModelLayout.

Here is the call graph for this function:

cfgOutputTensorLayout() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputTensorLayout ( 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.

Here is the call graph for this function:

cfgOutputTensorLayout() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputTensorLayout ( std::string layout )

inline

See also

ov::Params::cfgOutputTensorLayout.

Here is the call graph for this function:

cfgOutputTensorPrecision() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputTensorPrecision ( detail::AttrMap< int > 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.

Here is the call graph for this function:

cfgOutputTensorPrecision() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgOutputTensorPrecision ( int precision )

inline

See also

ov::Params::cfgOutputTensorPrecision.

Here is the call graph for this function:

cfgPluginConfig()

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgPluginConfig ( const detail::ParamDesc::PluginConfigT & config )

inline

See also

ov::Params::cfgPluginConfig.

Here is the call graph for this function:

cfgReshape() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgReshape ( detail::AttrMap< std::vector< size_t > > new_shape_map )

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:

cfgReshape() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgReshape ( std::vector< size_t > new_shape )

inline

See also

ov::Params::cfgReshape.

Here is the call graph for this function:

cfgResize() [1/2]

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

inline

See also

ov::Params::cfgResize.

Here is the call graph for this function:

cfgScale() [1/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgScale ( detail::AttrMap< std::vector< float > > scale_map )

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:

cfgScale() [2/2]

Params & cv::gapi::ov::Params< cv::gapi::Generic >::cfgScale ( std::vector< float > scale_values )

inline

See also

ov::Params::cfgScale.

Here is the call graph for this function:

params()

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

inline

tag()

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

inline

Member Data Documentation

m_desc

detail::ParamDesc cv::gapi::ov::Params< cv::gapi::Generic >::m_desc

protected

m_tag

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

protected

---

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

• opencv2/gapi/infer/ov.hpp