This class is a main plugin interface. More...

#include <ie_plugin.hpp>

Inheritance diagram for InferenceEngine::IInferencePlugin:

[legend]

Collaboration diagram for InferenceEngine::IInferencePlugin:

Public Member Functions
virtual void	GetVersion (const Version *&versionInfo) noexcept=0
	Returns plugin version information. More...

virtual void	SetLogCallback (IErrorListener &listener) noexcept=0
	Sets logging callback Logging is used to track what is going on inside. More...

virtual StatusCode	LoadNetwork (ICNNNetwork &network, ResponseDesc *resp) noexcept=0
	Loads a pre-built network with weights to the engine. In case of success the plugin will be ready to infer. More...

virtual StatusCode	LoadNetwork (IExecutableNetwork::Ptr &ret, ICNNNetwork &network, const std::map< std::string, std::string > &config, ResponseDesc *resp) noexcept=0
	Creates an executable network from a network object. User can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources) More...

virtual StatusCode	ImportNetwork (IExecutableNetwork::Ptr &ret, const std::string &modelFileName, const std::map< std::string, std::string > &config, ResponseDesc *resp) noexcept=0
	Creates an executable network from a previously exported network. More...

virtual StatusCode	Infer (const Blob &input, Blob &result, ResponseDesc *resp) noexcept=0
	Infers an image(s). Input and output dimensions depend on the topology. As an example for classification topologies use a 4D Blob as input (batch, channels, width, height) and get a 1D blob as output (scoring probability vector). To Infer a batch, use a 4D Blob as input and get a 2D blob as output in both cases the method will allocate the resulted blob. More...

virtual StatusCode	Infer (const BlobMap &input, BlobMap &result, ResponseDesc *resp) noexcept=0
	Infers tensors. Input and output dimensions depend on the topology. As an example for classification topologies use a 4D Blob as input (batch, channels, width, height) and get a 1D blob as output (scoring probability vector). To Infer a batch, use a 4D Blob as input and get a 2D blob as output in both cases the method will allocate the resulted blob. More...

virtual StatusCode	GetPerformanceCounts (std::map< std::string, InferenceEngineProfileInfo > &perfMap, ResponseDesc *resp) const noexcept=0
	Queries performance measures per layer to get feedback of what is the most time consuming layer Note: not all plugins provide meaningful data. More...

virtual StatusCode	AddExtension (InferenceEngine::IExtensionPtr extension, InferenceEngine::ResponseDesc *resp) noexcept=0
	Registers extension within the plugin. More...

virtual StatusCode	SetConfig (const std::map< std::string, std::string > &config, ResponseDesc *resp) noexcept=0
	Sets configuration for plugin, acceptable keys can be found in ie_plugin_config.hpp. More...

virtual void	QueryNetwork (const ICNNNetwork &, QueryNetworkResult &res) const noexcept
	Query plugin if it supports specified network. More...

virtual void	QueryNetwork (const ICNNNetwork &, const std::map< std::string, std::string > &, QueryNetworkResult &res) const noexcept
	Query plugin if it supports specified network with specified configuration. More...

Detailed Description

This class is a main plugin interface.

Member Function Documentation

§ AddExtension()

virtual StatusCode InferenceEngine::IInferencePlugin::AddExtension	(	InferenceEngine::IExtensionPtr	extension,
		InferenceEngine::ResponseDesc *	resp
	)

pure virtualnoexcept

Registers extension within the plugin.

Parameters

extension	Pointer to already loaded extension
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ GetPerformanceCounts()

virtual StatusCode InferenceEngine::IInferencePlugin::GetPerformanceCounts	(	std::map< std::string, InferenceEngineProfileInfo > &	perfMap,
		ResponseDesc *	resp
	)		const

pure virtualnoexcept

Queries performance measures per layer to get feedback of what is the most time consuming layer Note: not all plugins provide meaningful data.

Deprecated:: Uses IInferRequest to get performance measures

Parameters

perfMap	Map of layer names to profiling information for that layer
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ GetVersion()

virtual void InferenceEngine::IInferencePlugin::GetVersion ( const Version *& versionInfo )

pure virtualnoexcept

Returns plugin version information.

Parameters

versionInfo Pointer to version info. Is set by plugin

§ ImportNetwork()

virtual StatusCode InferenceEngine::IInferencePlugin::ImportNetwork	(	IExecutableNetwork::Ptr &	ret,
		const std::string &	modelFileName,
		const std::map< std::string, std::string > &	config,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Creates an executable network from a previously exported network.

Parameters

ret	Reference to a shared ptr of the returned network interface
modelFileName	Path to the location of the exported file
config	Map of pairs: (config parameter name, config parameter value) relevant only for this load operation*
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ Infer() [1/2]

virtual StatusCode InferenceEngine::IInferencePlugin::Infer	(	const Blob &	input,
		Blob &	result,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Infers an image(s). Input and output dimensions depend on the topology. As an example for classification topologies use a 4D Blob as input (batch, channels, width, height) and get a 1D blob as output (scoring probability vector). To Infer a batch, use a 4D Blob as input and get a 2D blob as output in both cases the method will allocate the resulted blob.

Deprecated:: Uses Infer() working with multiple inputs and outputs

Parameters

input	Any TBlob<> object that contains the data to infer. The type of TBlob must match the network input precision and size.
result	Related TBlob<> object that contains the result of the inference action, typically this is a float blob. The blob does not need to be allocated or initialized, the engine allocates the relevant data.
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ Infer() [2/2]

virtual StatusCode InferenceEngine::IInferencePlugin::Infer	(	const BlobMap &	input,
		BlobMap &	result,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Infers tensors. Input and output dimensions depend on the topology. As an example for classification topologies use a 4D Blob as input (batch, channels, width, height) and get a 1D blob as output (scoring probability vector). To Infer a batch, use a 4D Blob as input and get a 2D blob as output in both cases the method will allocate the resulted blob.

Deprecated:: Loads IExecutableNetwork to create IInferRequest.

Parameters

input	Map of input blobs accessed by input names
result	Map of output blobs accessed by output names
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ LoadNetwork() [1/2]

virtual StatusCode InferenceEngine::IInferencePlugin::LoadNetwork	(	ICNNNetwork &	network,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Loads a pre-built network with weights to the engine. In case of success the plugin will be ready to infer.

Deprecated:: use LoadNetwork with four parameters (executable network, cnn network, config, response)

Parameters

network	Network object acquired from CNNNetReader
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ LoadNetwork() [2/2]

virtual StatusCode InferenceEngine::IInferencePlugin::LoadNetwork	(	IExecutableNetwork::Ptr &	ret,
		ICNNNetwork &	network,
		const std::map< std::string, std::string > &	config,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Creates an executable network from a network object. User can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources)

Parameters

ret	Reference to a shared ptr of the returned network interface
network	Network object acquired from CNNNetReader
config	Map of pairs: (config parameter name, config parameter value) relevant only for this load operation
resp	Pointer to the response message that holds a description of an error if any occurred

Returns: Status code of the operation. OK if succeeded

§ QueryNetwork() [1/2]

virtual void InferenceEngine::IInferencePlugin::QueryNetwork	(	const ICNNNetwork &	,
		QueryNetworkResult &	res
	)		const

inlinevirtualnoexcept

Query plugin if it supports specified network.

Use the version with config parameter

Parameters

network	Network object to query
resp	Pointer to the response message that holds a description of an error if any occurred

§ QueryNetwork() [2/2]

virtual void InferenceEngine::IInferencePlugin::QueryNetwork	(	const ICNNNetwork &	,
		const std::map< std::string, std::string > &	,
		QueryNetworkResult &	res
	)		const

inlinevirtualnoexcept

Query plugin if it supports specified network with specified configuration.

Parameters

network	Network object to query
config	Map of pairs: (config parameter name, config parameter value)
resp	Pointer to the response message that holds a description of an error if any occurred

§ SetConfig()

virtual StatusCode InferenceEngine::IInferencePlugin::SetConfig	(	const std::map< std::string, std::string > &	config,
		ResponseDesc *	resp
	)

pure virtualnoexcept

Sets configuration for plugin, acceptable keys can be found in ie_plugin_config.hpp.

Parameters

config	Map of pairs: (config parameter name, config parameter value)
resp	Pointer to the response message that holds a description of an error if any occurred

§ SetLogCallback()

virtual void InferenceEngine::IInferencePlugin::SetLogCallback ( IErrorListener & listener )

pure virtualnoexcept

Sets logging callback Logging is used to track what is going on inside.

Parameters

listener Logging sink

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

tmp_docs/inference-engine/include/ie_plugin.hpp

Public Member Functions

Detailed Description

Member Function Documentation

§ AddExtension()

§ GetPerformanceCounts()

§ GetVersion()

§ ImportNetwork()

§ Infer() [1/2]

§ Infer() [2/2]

§ LoadNetwork() [1/2]

§ LoadNetwork() [2/2]

§ QueryNetwork() [1/2]

§ QueryNetwork() [2/2]

§ SetConfig()

§ SetLogCallback()