InferenceEngine::IAsyncInferRequestInternal Interface Reference

An internal API of asynchronous inference request to be implemented by plugin, which is used in InferRequestBase forwarding mechanism. More...

#include <ie_iinfer_async_request_internal.hpp>

Inheritance diagram for InferenceEngine::IAsyncInferRequestInternal:

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

Public Member Functions
virtual	~IAsyncInferRequestInternal ()=default
	A virtual destructor.
virtual void	StartAsync ()=0
	Start inference of specified input(s) in asynchronous mode. More...
virtual StatusCode	Wait (int64_t millis_timeout)=0
	Waits for the result to become available. Blocks until specified millis_timeout has elapsed or the result becomes available, whichever comes first. More...
virtual void	GetUserData (void **data)=0
	Get arbitrary data for the request. More...
virtual void	SetUserData (void *data)=0
	Set arbitrary data for the request. More...
virtual void	SetCompletionCallback (IInferRequest::CompletionCallback callback)=0
	Set callback function which will be called on success or failure of asynchronous request. More...
Public Member Functions inherited from InferenceEngine::IInferRequestInternal
virtual	~IInferRequestInternal ()=default
	Destroys the object.
virtual void	Infer ()=0
	Infers specified input(s) in synchronous mode. More...
virtual void	Cancel ()=0
	Cancel current inference request execution.
virtual std::map< std::string, InferenceEngineProfileInfo >	GetPerformanceCounts () const =0
	Queries performance measures per layer to get feedback of what is the most time consuming layer. Note: not all plugins may provide meaningful data. More...
virtual void	SetBlob (const std::string &name, const Blob::Ptr &data)=0
	Set input/output data to infer. More...
virtual Blob::Ptr	GetBlob (const std::string &name)=0
	Get input/output data to infer. More...
virtual void	SetBlob (const std::string &name, const Blob::Ptr &data, const PreProcessInfo &info)=0
	Sets pre-process for input data. More...
virtual const PreProcessInfo &	GetPreProcess (const std::string &name) const =0
	Gets pre-process for input data. More...
virtual void	SetBatch (int batch)=0
	Sets new batch size when dynamic batching is enabled in executable network that created this request. More...
virtual std::vector< IVariableStateInternal::Ptr >	QueryState ()=0
	Queries memory states. More...

Detailed Description

An internal API of asynchronous inference request to be implemented by plugin, which is used in InferRequestBase forwarding mechanism.

Member Function Documentation

GetUserData()

virtual void InferenceEngine::IAsyncInferRequestInternal::GetUserData ( void **  data )

pure virtual

Get arbitrary data for the request.

Parameters

data	A pointer to a pointer to arbitrary data

Implemented in InferenceEngine::AsyncInferRequestThreadSafeDefault, and InferenceEngine::AsyncInferRequestInternal.

SetCompletionCallback()

virtual void InferenceEngine::IAsyncInferRequestInternal::SetCompletionCallback ( IInferRequest::CompletionCallback  callback )

pure virtual

Set callback function which will be called on success or failure of asynchronous request.

Parameters

callback

- function to be called with the following description:

Implemented in InferenceEngine::AsyncInferRequestThreadSafeDefault, and InferenceEngine::AsyncInferRequestInternal.

SetUserData()

virtual void InferenceEngine::IAsyncInferRequestInternal::SetUserData ( void *  data )

pure virtual

Set arbitrary data for the request.

Parameters

data	A pointer to a pointer to arbitrary data

Implemented in InferenceEngine::AsyncInferRequestThreadSafeDefault, and InferenceEngine::AsyncInferRequestInternal.

StartAsync()

virtual void InferenceEngine::IAsyncInferRequestInternal::StartAsync ( )

pure virtual

Start inference of specified input(s) in asynchronous mode.

Note

The method returns immediately. Inference starts also immediately.

Implemented in InferenceEngine::AsyncInferRequestThreadSafeDefault, and InferenceEngine::AsyncInferRequestInternal.

Wait()

virtual StatusCode InferenceEngine::IAsyncInferRequestInternal::Wait ( int64_t  millis_timeout )

pure virtual

Waits for the result to become available. Blocks until specified millis_timeout has elapsed or the result becomes available, whichever comes first.

Parameters

millis_timeout

- maximum duration in milliseconds to block for

Note

There are special cases when millis_timeout is equal some value of WaitMode enum:

• STATUS_ONLY - immediately returns request status (IInferRequest::RequestStatus). It doesn't block or interrupt current thread.
• RESULT_READY - waits until inference result becomes available

Returns

A status code

Implemented in InferenceEngine::AsyncInferRequestThreadSafeDefault.

---

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

• cpp_interfaces/interface/ie_iinfer_async_request_internal.hpp