Minimum implementation of IExecutableNetworkInternal interface. Must not be used as a base class in plugins As base classes, use ExecutableNetworkThreadSafeDefault or ExecutableNetworkThreadSafeAsyncOnly. More...

#include <ie_executable_network_internal.hpp>

Inheritance diagram for InferenceEngine::ExecutableNetworkInternal:

Public Types
typedef std::shared_ptr< ExecutableNetworkInternal >	Ptr
	A shared pointer to ExecutableNetworkInternal object.

Public Types inherited from InferenceEngine::IExecutableNetworkInternal
typedef std::shared_ptr< IExecutableNetworkInternal >	Ptr
	A shared pointer to IExecutableNetworkInternal interface.

Public Member Functions
virtual void	setNetworkInputs (const InferenceEngine::InputsDataMap networkInputs)
	Sets the network inputs info. More...

virtual void	setNetworkOutputs (const InferenceEngine::OutputsDataMap networkOutputs)
	Sets the network outputs data. More...

ConstOutputsDataMap	GetOutputsInfo () const override
	Gets the Executable network output Data node information. The received info is stored in the given Data node. This method need to be called to find output names for using them later during filling of a map of blobs passed later to InferenceEngine::IInferencePlugin::Infer() More...

ConstInputsDataMap	GetInputsInfo () const override
	Gets the Executable network input Data node information. The received info is stored in the given InputsDataMap object. This method need to be called to find out input names for using them later during filling of a map of blobs passed later to InferenceEngine::IInferencePlugin::Infer() More...

void	Export (const std::string &modelFileName) override
	Export the current created executable network so it can be used later in the Import() main API. More...

void	Export (std::ostream &networkModel) override
	Export the current created executable network so it can be used later in the Import() main API. More...

CNNNetwork	GetExecGraphInfo () override
	Get executable graph information from a device. More...

void	SetPointerToPlugin (IInferencePlugin::Ptr plugin)
	Sets the pointer to plugin internal. More...

std::vector< IVariableStateInternal::Ptr >	QueryState () override
	Queries memory states. More...

void	SetConfig (const std::map< std::string, Parameter > &config) override
	Sets configuration for current executable network. More...

Parameter	GetConfig (const std::string &name) const override
	Gets configuration dedicated to plugin behaviour. More...

Parameter	GetMetric (const std::string &name) const override
	Gets general runtime metric for dedicated hardware. More...

RemoteContext::Ptr	GetContext () const override
	Gets the remote context. More...

Public Member Functions inherited from InferenceEngine::IExecutableNetworkInternal
virtual	~IExecutableNetworkInternal ()=default
	Destroys the object.

virtual IInferRequest::Ptr	CreateInferRequest ()=0
	Create an inference request object used to infer the network Note: the returned request will have allocated input and output blobs (that can be changed later) More...

Protected Member Functions
virtual void	ExportImpl (std::ostream &networkModel)
	Exports an internal hardware-dependent model to a stream. More...

Protected Attributes
InferenceEngine::InputsDataMap	_networkInputs
	Holds infromation about network inputs info.

InferenceEngine::OutputsDataMap	_networkOutputs
	Holds information about network outputs data.

IInferencePlugin::Ptr	_plugin
	A pointer to a IInferencePlugin interface. More...

Detailed Description

Minimum implementation of IExecutableNetworkInternal interface. Must not be used as a base class in plugins As base classes, use ExecutableNetworkThreadSafeDefault or ExecutableNetworkThreadSafeAsyncOnly.

Member Function Documentation

◆ Export() [1/2]

void InferenceEngine::ExecutableNetworkInternal::Export ( const std::string & modelFileName )

inlineoverridevirtual

Export the current created executable network so it can be used later in the Import() main API.

Deprecated:: Use IExecutableNetworkInternal::Export(std::ostream& networkModel)

Parameters

modelFileName - path to the location of the exported file

Implements InferenceEngine::IExecutableNetworkInternal.

◆ Export() [2/2]

void InferenceEngine::ExecutableNetworkInternal::Export ( std::ostream & networkModel )

inlineoverridevirtual

Export the current created executable network so it can be used later in the Import() main API.

Parameters

networkModel - Reference to network model output stream

Implements InferenceEngine::IExecutableNetworkInternal.

◆ ExportImpl()

virtual void InferenceEngine::ExecutableNetworkInternal::ExportImpl ( std::ostream & networkModel )

inlineprotectedvirtual

Exports an internal hardware-dependent model to a stream.

Note: The function is called from ExecutableNetworkInternal::Export(std::ostream&), which performs common export first and calls this plugin-dependent implementation after.

Parameters

networkModel A stream to export network to.

◆ GetConfig()

Parameter InferenceEngine::ExecutableNetworkInternal::GetConfig ( const std::string & name ) const

inlineoverridevirtual

Gets configuration dedicated to plugin behaviour.

Parameters

name	A config key, can be found in ie_plugin_config.hpp

Returns: A value of config corresponding to config key

Implements InferenceEngine::IExecutableNetworkInternal.

◆ GetContext()

RemoteContext::Ptr InferenceEngine::ExecutableNetworkInternal::GetContext ( ) const

inlineoverridevirtual

Gets the remote context.

Returns: A reference to a context

Implements InferenceEngine::IExecutableNetworkInternal.

◆ GetExecGraphInfo()

CNNNetwork InferenceEngine::ExecutableNetworkInternal::GetExecGraphInfo ( )

inlineoverridevirtual

Get executable graph information from a device.

Returns: A network object to store executable graph information

Implements InferenceEngine::IExecutableNetworkInternal.

◆ GetInputsInfo()

ConstInputsDataMap InferenceEngine::ExecutableNetworkInternal::GetInputsInfo ( ) const

inlineoverridevirtual

Gets the Executable network input Data node information. The received info is stored in the given InputsDataMap object. This method need to be called to find out input names for using them later during filling of a map of blobs passed later to InferenceEngine::IInferencePlugin::Infer()

Returns: inputs Reference to ConstInputsDataMap object.

Implements InferenceEngine::IExecutableNetworkInternal.

◆ GetMetric()

Parameter InferenceEngine::ExecutableNetworkInternal::GetMetric ( const std::string & name ) const

inlineoverridevirtual

Gets general runtime metric for dedicated hardware.

Parameters

name	A metric name to request

Returns: A metric value corresponding to metric key

Implements InferenceEngine::IExecutableNetworkInternal.

◆ GetOutputsInfo()

ConstOutputsDataMap InferenceEngine::ExecutableNetworkInternal::GetOutputsInfo ( ) const

inlineoverridevirtual

Gets the Executable network output Data node information. The received info is stored in the given Data node. This method need to be called to find output names for using them later during filling of a map of blobs passed later to InferenceEngine::IInferencePlugin::Infer()

Returns: out Reference to the ConstOutputsDataMap object

Implements InferenceEngine::IExecutableNetworkInternal.

◆ QueryState()

std::vector<IVariableStateInternal::Ptr> InferenceEngine::ExecutableNetworkInternal::QueryState ( )

inlineoverridevirtual

Queries memory states.

Deprecated:: Need to implement GetVariablesInfo for ExecutableNetwork

Returns: Returns memory states

Implements InferenceEngine::IExecutableNetworkInternal.

◆ SetConfig()

void InferenceEngine::ExecutableNetworkInternal::SetConfig ( const std::map< std::string, Parameter > & config )

inlineoverridevirtual

Sets configuration for current executable network.

Parameters

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

Implements InferenceEngine::IExecutableNetworkInternal.

◆ setNetworkInputs()

virtual void InferenceEngine::ExecutableNetworkInternal::setNetworkInputs ( const InferenceEngine::InputsDataMap networkInputs )

inlinevirtual

Sets the network inputs info.

Parameters

[in] networkInputs The network inputs info

◆ setNetworkOutputs()

virtual void InferenceEngine::ExecutableNetworkInternal::setNetworkOutputs ( const InferenceEngine::OutputsDataMap networkOutputs )

inlinevirtual

Sets the network outputs data.

Parameters

[in] networkOutputs The network outputs

◆ SetPointerToPlugin()

void InferenceEngine::ExecutableNetworkInternal::SetPointerToPlugin ( IInferencePlugin::Ptr plugin )

inline

Sets the pointer to plugin internal.

Parameters

[in] plugin The plugin

Note: Needed to correctly handle ownership between objects.

Field Documentation

◆ _plugin

IInferencePlugin::Ptr InferenceEngine::ExecutableNetworkInternal::_plugin

protected

A pointer to a IInferencePlugin interface.

Note: Needed to correctly handle ownership between objects.

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

cpp_interfaces/impl/ie_executable_network_internal.hpp

Public Types

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Member Function Documentation

◆ Export() [1/2]

◆ Export() [2/2]

◆ ExportImpl()

◆ GetConfig()

◆ GetContext()

◆ GetExecGraphInfo()

◆ GetInputsInfo()

◆ GetMetric()

◆ GetOutputsInfo()

◆ QueryState()

◆ SetConfig()

◆ setNetworkInputs()

◆ setNetworkOutputs()

◆ SetPointerToPlugin()

Field Documentation

◆ _plugin