This class contains all the information about the Neural Network and the related binary information. More...

#include <ie_cnn_network.h>

Collaboration diagram for InferenceEngine::CNNNetwork:

[legend]

Public Member Functions
	CNNNetwork ()
	A default constructor.

	CNNNetwork (std::shared_ptr< ICNNNetwork > network)
	Allows helper class to manage lifetime of network object. More...

	CNNNetwork (const std::shared_ptr< ngraph::Function > &network, const std::vector< IExtensionPtr > &exts={})
	A constructor from ngraph::Function object This constructor wraps existing ngraph::Function If you want to avoid modification of original Function, please create a copy. More...

OutputsDataMap	getOutputsInfo () const
	Gets the network output Data node information. The received info is stored in the given Data node. More...

InputsDataMap	getInputsInfo () const
	Gets the network input Data node information. The received info is stored in the given InputsDataMap object. More...

size_t	layerCount () const
	Returns the number of layers in the network as an integer value. More...

const std::string &	getName () const
	Returns the network name. More...

void	setBatchSize (const size_t size)
	Changes the inference batch size. More...

size_t	getBatchSize () const
	Gets the inference batch size. More...

	operator ICNNNetwork::Ptr ()
	An overloaded operator cast to get pointer on current network. More...

	operator ICNNNetwork & ()
	An overloaded operator & to get current network. More...

	operator const ICNNNetwork & () const
	An overloaded operator & to get current network. More...

std::shared_ptr< ngraph::Function >	getFunction ()
	Returns constant nGraph function. More...

std::shared_ptr< const ngraph::Function >	getFunction () const
	Returns constant nGraph function. More...

void	addOutput (const std::string &layerName, size_t outputIndex=0)
	Adds output to the layer. More...

ICNNNetwork::InputShapes	getInputShapes () const
	Helper method to get collect all input shapes with names of corresponding Data objects. More...

void	reshape (const ICNNNetwork::InputShapes &inputShapes)
	Run shape inference with new input shapes for the network. More...

void	serialize (const std::string &xmlPath, const std::string &binPath={}) const
	Serialize network to IR and weights files. More...

std::string	getOVNameForTensor (const std::string &orig_name) const
	Method maps framework tensor name to OpenVINO name. More...

Protected Attributes
std::shared_ptr< ICNNNetwork >	network
	Network extra interface, might be nullptr.

ICNNNetwork *	actual = nullptr
	A pointer to the current network.

DataPtr	output
	A pointer to output data.

Detailed Description

This class contains all the information about the Neural Network and the related binary information.

Constructor & Destructor Documentation

◆ CNNNetwork() [1/2]

InferenceEngine::CNNNetwork::CNNNetwork ( std::shared_ptr< ICNNNetwork > network )

explicit

Allows helper class to manage lifetime of network object.

Parameters

network Pointer to the network object

◆ CNNNetwork() [2/2]

InferenceEngine::CNNNetwork::CNNNetwork	(	const std::shared_ptr< ngraph::Function > &	network,
		const std::vector< IExtensionPtr > &	exts = `{}`
	)

explicit

A constructor from ngraph::Function object This constructor wraps existing ngraph::Function If you want to avoid modification of original Function, please create a copy.

Parameters

network	Pointer to the ngraph::Function object
exts	Vector of pointers to IE extension objects

Member Function Documentation

◆ addOutput()

void InferenceEngine::CNNNetwork::addOutput	(	const std::string &	layerName,
		size_t	outputIndex = `0`
	)

Adds output to the layer.

Wraps ICNNNetwork::addOutput

Parameters

layerName	Name of the layer
outputIndex	Index of the output

◆ getBatchSize()

size_t InferenceEngine::CNNNetwork::getBatchSize ( ) const

Gets the inference batch size.

Wraps ICNNNetwork::getBatchSize

Returns: The size of batch as a size_t value

◆ getFunction() [1/2]

std::shared_ptr<ngraph::Function> InferenceEngine::CNNNetwork::getFunction ( )

Returns constant nGraph function.

Returns: constant nGraph function

◆ getFunction() [2/2]

std::shared_ptr<const ngraph::Function> InferenceEngine::CNNNetwork::getFunction ( ) const

Returns constant nGraph function.

Returns: constant nGraph function

◆ getInputShapes()

ICNNNetwork::InputShapes InferenceEngine::CNNNetwork::getInputShapes ( ) const

Helper method to get collect all input shapes with names of corresponding Data objects.

Returns: Map of pairs: input name and its dimension.

◆ getInputsInfo()

InputsDataMap InferenceEngine::CNNNetwork::getInputsInfo ( ) const

Gets the network input Data node information. The received info is stored in the given InputsDataMap object.

Wraps ICNNNetwork::getInputsInfo

Returns: inputs Reference to InputsDataMap object

◆ getName()

const std::string& InferenceEngine::CNNNetwork::getName ( ) const

Returns the network name.

Wraps ICNNNetwork::getName

Returns: Network name

◆ getOutputsInfo()

OutputsDataMap InferenceEngine::CNNNetwork::getOutputsInfo ( ) const

Gets the network output Data node information. The received info is stored in the given Data node.

Wraps ICNNNetwork::getOutputsInfo

Returns: outputs Reference to the OutputsDataMap object

◆ getOVNameForTensor()

std::string InferenceEngine::CNNNetwork::getOVNameForTensor ( const std::string & orig_name ) const

inline

Method maps framework tensor name to OpenVINO name.

Parameters

orig_name Framework tensor name

Returns: OpenVINO name

◆ layerCount()

size_t InferenceEngine::CNNNetwork::layerCount ( ) const

Returns the number of layers in the network as an integer value.

Wraps ICNNNetwork::layerCount

Returns: The number of layers as an integer value

◆ operator const ICNNNetwork &()

InferenceEngine::CNNNetwork::operator const ICNNNetwork & ( ) const

An overloaded operator & to get current network.

Deprecated:: InferenceEngine::ICNNNetwork interface is deprecated

Returns: A const reference of the current network

◆ operator ICNNNetwork &()

InferenceEngine::CNNNetwork::operator ICNNNetwork & ( )

An overloaded operator & to get current network.

Deprecated:: InferenceEngine::ICNNNetwork interface is deprecated

Returns: An instance of the current network

◆ operator ICNNNetwork::Ptr()

InferenceEngine::CNNNetwork::operator ICNNNetwork::Ptr ( )

An overloaded operator cast to get pointer on current network.

Deprecated:: InferenceEngine::ICNNNetwork interface is deprecated

Returns: A shared pointer of the current network

◆ reshape()

void InferenceEngine::CNNNetwork::reshape ( const ICNNNetwork::InputShapes & inputShapes )

Run shape inference with new input shapes for the network.

Parameters

inputShapes - map of pairs: name of corresponding data and its dimension.

◆ serialize()

void InferenceEngine::CNNNetwork::serialize	(	const std::string &	xmlPath,
		const std::string &	binPath = `{}`
	)		const

Serialize network to IR and weights files.

Parameters

xmlPath	Path to output IR file.
binPath	Path to output weights file. The parameter is skipped in case of executable graph info serialization.

◆ setBatchSize()

void InferenceEngine::CNNNetwork::setBatchSize ( const size_t size )

Changes the inference batch size.

Wraps ICNNNetwork::setBatchSize

Parameters

size	Size of batch to set

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

cpp/ie_cnn_network.h

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ CNNNetwork() [1/2]

◆ CNNNetwork() [2/2]

Member Function Documentation

◆ addOutput()

◆ getBatchSize()

◆ getFunction() [1/2]

◆ getFunction() [2/2]

◆ getInputShapes()

◆ getInputsInfo()

◆ getName()

◆ getOutputsInfo()

◆ getOVNameForTensor()

◆ layerCount()

◆ operator const ICNNNetwork &()

◆ operator ICNNNetwork &()

◆ operator ICNNNetwork::Ptr()

◆ reshape()

◆ serialize()

◆ setBatchSize()