InferenceEngine::Data Class Reference

This class represents the main Data representation node. More...

#include <ie_data.h>

Public Member Functions
	Data (const std::string &name, Precision _precision, Layout layout=NCHW)
	An empty constructor (dimensionless) More...
	Data (const std::string &name, const SizeVector &a_dims, Precision _precision, Layout layout=NCHW)
	A full constructor (with dimensions) More...
	Data (const std::string &name, const TensorDesc &desc)
	A constructor with tensor descriptor. More...
virtual	~Data ()=default
	A virtual destructor.
bool	isInitialized () const
	Checks if the current node is resolved. More...
void	setDims (const SizeVector &a_dims)
	Sets the data dimensions. More...
void	setLayout (Layout layout)
	Sets the layout value for this Data instance. More...
void	reshape (const SizeVector &dims, Layout layout)
	changes dims and layout at same time More...
Layout	getLayout () const
	Gets the layout value for this Data instance.
const TensorDesc &	getTensorDesc () const
	Gets Tensor descriptor reference. More...
const Precision &	getPrecision () const
	Gets a precision type of this Data instance. More...
void	setPrecision (const Precision &precision)
	Sets a precision type of this Data instance. More...
const SizeVector &	getDims () const
virtual CNNLayerWeakPtr &	getCreatorLayer ()
	Returns an owner of this data layer, parent layer in di-graph. More...
const std::string &	getName () const
void	setName (const std::string &newName)
	Sets a name the Data object. More...
virtual std::map< std::string, CNNLayerPtr > &	getInputTo ()
	Privates child layers in di-graph. More...
const UserValue &	getUserObject () const

Detailed Description

This class represents the main Data representation node.

The NN graphs are di-graphs consisting of data nodes and layer nodes.

Constructor & Destructor Documentation

Data() [1/3]

InferenceEngine::Data::Data	(	const std::string &	name,
		Precision	_precision,
		Layout	layout = NCHW
	)

An empty constructor (dimensionless)

Parameters

name	Name of the data node
_precision	Precision of the data
layout	Data layout

Data() [2/3]

InferenceEngine::Data::Data	(	const std::string &	name,
		const SizeVector &	a_dims,
		Precision	_precision,
		Layout	layout = NCHW
	)

A full constructor (with dimensions)

Deprecated:

Use Data(const std::string &name, const TensorDesc& desc)

Parameters

name	Name of the data node
a_dims	Data tensor dimensions
_precision	Precision of the data
layout	Data layout

Data() [3/3]

InferenceEngine::Data::Data	(	const std::string &	name,
		const TensorDesc &	desc
	)

A constructor with tensor descriptor.

Parameters

name	Name of the data node
desc	Tensor descriptor

Member Function Documentation

getCreatorLayer()

virtual CNNLayerWeakPtr& InferenceEngine::Data::getCreatorLayer ( )

virtual

Returns an owner of this data layer, parent layer in di-graph.

Deprecated:

Migrate to IR v10 and work with ngraph::Function directly. The method will be removed in 2021.1

Returns

A weak pointer to CNNLayer that creates this data

getDims()

const SizeVector& InferenceEngine::Data::getDims

(

)

const

Returns

data dimensions

getInputTo()

virtual std::map<std::string, CNNLayerPtr>& InferenceEngine::Data::getInputTo ( )

virtual

Privates child layers in di-graph.

Deprecated:

Migrate to IR v10 and work with ngraph::Function directly. The method will be removed in 2021.1

Returns

A map of child layers

getName()

const std::string& InferenceEngine::Data::getName

(

)

const

Returns

name of the data object

getPrecision()

const Precision& InferenceEngine::Data::getPrecision

(

)

const

Gets a precision type of this Data instance.

Returns

Precision type

getTensorDesc()

const TensorDesc& InferenceEngine::Data::getTensorDesc

(

)

const

Gets Tensor descriptor reference.

Returns

reference to TensorDesc

getUserObject()

const UserValue& InferenceEngine::Data::getUserObject

(

)

const

Returns

convenient arbitrary user data holder

isInitialized()

bool InferenceEngine::Data::isInitialized

(

)

const

Checks if the current node is resolved.

Returns

true if resolved, false otherwise.

reshape()

void InferenceEngine::Data::reshape	(	const SizeVector &	dims,
		Layout	layout
	)

changes dims and layout at same time

Parameters

dims	new dimensions
layout	new layout

setDims()

void InferenceEngine::Data::setDims

(

const SizeVector &

a_dims

)

Sets the data dimensions.

After the current node is marked as resolved.

Parameters

a_dims

Tensor dimensions to set

setLayout()

void InferenceEngine::Data::setLayout

(

Layout

layout

)

Sets the layout value for this Data instance.

Parameters

layout

Layout value to set

setName()

void InferenceEngine::Data::setName

(

const std::string &

newName

)

Sets a name the Data object.

Parameters

newName

Name of the data node

setPrecision()

void InferenceEngine::Data::setPrecision

(

const Precision &

precision

)

Sets a precision type of this Data instance.

Parameters

precision

Precision of the data

---

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

• ie_data.h