InferenceEngine::InputInfo Class Reference

This class contains information about each input of the network. More...

#include <ie_input_info.hpp>

Collaboration diagram for InferenceEngine::InputInfo:

Public Types
using	Ptr = std::shared_ptr< InputInfo >
	A smart pointer to the InputInfo instance.
using	CPtr = std::shared_ptr< const InputInfo >
	A smart pointer to the constant InputInfo instance.

Public Member Functions
Precision	getPrecision () const
	Gets a precision of the input data provided by user. More...
void	setPrecision (Precision p)
	Changes the precision of the input data provided by the user. More...
Layout	getLayout ()
	Gets a layout of the input data provided by user. More...
void	setLayout (Layout l)
	Changes the layout of the input data provided by the user. More...
const std::string &	name () const
	Gets the name of the input. More...
DataPtr	getInputData () const
	Gets the input data. More...
void	setInputData (DataPtr inputPtr)
	Initializes the pointer to the input data that stores the main input parameters like dims, etc. More...
const TensorDesc &	getTensorDesc () const
	Returns the tensor descriptor.
PreProcessInfo &	getPreProcess ()
	Gets pre-process info for the input. More...

Protected Attributes
PreProcessInfo	_preProcessInfo
	Pre-process info for the input.
DataPtr	_inputData
	A smart pointer to the input data.

Detailed Description

This class contains information about each input of the network.

Member Function Documentation

getInputData()

DataPtr InferenceEngine::InputInfo::getInputData ( ) const

inline

Gets the input data.

Returns

A smart pointer to the input data

getLayout()

Layout InferenceEngine::InputInfo::getLayout ( )

inline

Gets a layout of the input data provided by user.

By default it matches the layers precision and depends on number of its dimensions: C - for 1-dimensional, NC - for 2-dimensional, CHW - for 3-dimensional, NCHW - for 4-dimensional The default input layout might be changed preferred one using setLayout() function.

Returns

The precision used for input blob creation

getPrecision()

Precision InferenceEngine::InputInfo::getPrecision ( ) const

inline

Gets a precision of the input data provided by user.

By default it matches the layers precision, but there are exceptions of this rule For Q78 precision networks the input is expected in I16 by default For FP16 precision networks the input is expected in FP32 by default

By default it matches the layers precision, but there are exceptions of this rule. For Q78 precision networks the input is expected in I16 by default. For FP16 precision networks the input is expected in FP32 by default. The default input precision might be changed preferred one using InputInfo::setPrecision() function. For example, for a Q78 precision network you can pass FP32 input data

Returns

The precision used for input blob creation

getPreProcess()

PreProcessInfo& InferenceEngine::InputInfo::getPreProcess ( )

inline

Gets pre-process info for the input.

Returns

A reference to the PreProcessInfo instance that contains pre-process info for this input

name()

const std::string& InferenceEngine::InputInfo::name ( ) const

inline

Gets the name of the input.

Returns

A string - the name of the input

setInputData()

void InferenceEngine::InputInfo::setInputData ( DataPtr  inputPtr )

inline

Initializes the pointer to the input data that stores the main input parameters like dims, etc.

This method initializes the precision with the information from the inputPtr if it was not set explicitly through InputInfo::setPrecision. If InputInfo::setPrecision is called, this method does not overwrite the precision.

Parameters

inputPtr

Pointer to the input data to set

setLayout()

void InferenceEngine::InputInfo::setLayout ( Layout  l )

inline

Changes the layout of the input data provided by the user.

This function should be called before loading the network to the plugin

Parameters

p	A new layout of the input data to set

setPrecision()

void InferenceEngine::InputInfo::setPrecision ( Precision  p )

inline

Changes the precision of the input data provided by the user.

This function should be called before loading the network to the plugin

Parameters

p	A new precision of the input data to set

---

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

• ie_input_info.hpp