Public Types | Public Member Functions | Protected Attributes
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:
Collaboration graph
[legend]

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 getInputPrecision () const
 Gets a precision of the input data provided by user. More...
 
void setInputPrecision (Precision p)
 Changes the precision of the input data provided by the user. This function should be called before loading the network to the plugin. More...
 
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. This function should be called before loading the network to the plugin. 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. This function should be called before loading the network to the plugin. More...
 
const std::string & name () const
 Gets the name of the input. More...
 
DataPtr getInputData ()
 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. 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. More...
 
SizeVector getDims () const
 Gets dimensions/shape of the input data with reversed order. More...
 
const TensorDescgetTensorDesc () const
 Returns the tensor descriptor.
 
PreProcessInfogetPreProcess ()
 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

§ getDims()

SizeVector InferenceEngine::InputInfo::getDims ( ) const
inline

Gets dimensions/shape of the input data with reversed order.

Deprecated:
Please use InputInfo::getTensorDesc for working with layouts and dimensions
Returns
A SizeVector object that contains dimensions of the input data. If the data is not set, the method returns an empty SizeVector object.

§ getInputData()

DataPtr InferenceEngine::InputInfo::getInputData ( )
inline

Gets the input data.

Returns
A smart pointer to the input data

§ getInputPrecision()

Precision InferenceEngine::InputInfo::getInputPrecision ( ) const
inline

Gets a precision of the input data provided by user.

Deprecated:
Use InputInfo::getPrecision

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

§ 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
inputPtrPointer to the input data to set

§ setInputPrecision()

void InferenceEngine::InputInfo::setInputPrecision ( 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.

Deprecated:
Use InputInfo::setPrecision
Parameters
pA new precision of 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
pA 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
pA new precision of the input data to set

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