This class represents a universal container in the Inference Engine. More...

#include <ie_blob.h>

Inheritance diagram for InferenceEngine::Blob:

[legend]

Collaboration diagram for InferenceEngine::Blob:

Public Types
using	Ptr = std::shared_ptr< Blob >
	A smart pointer containing Blob object.

using	CPtr = std::shared_ptr< const Blob >
	A smart pointer to the const Blob object.

Public Member Functions
Precision	type () const noexcept
	Returns the tensor precision of the current Blob object. More...

Precision	precision () const noexcept
	Returns the tensor precision of the current Blob object. More...

Layout	layout () const noexcept
	Returns the tensor layout of the current Blob object. More...

virtual	~Blob ()=default
	Blob virtual destructor.

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>
bool	is () noexcept
	Checks if the Blob object can be cast to the type T*. More...

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>
bool	is () const noexcept
	Checks if the Blob object can be cast to the type const T*. More...

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>
T *	as () noexcept
	Casts this Blob object to the type T*. Use InferenceEngine::as() to operate with shared Blob objects instead of raw pointers. More...

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>
const T *	as () const noexcept
	Casts this Blob object to the type const T*. Use InferenceEngine::as() to operate with shared Blob objects instead of raw pointers. More...

	Blob (const TensorDesc &tensorDesc)
	Constructor. Creates an empty Blob object with the specified precision. More...

	Blob (Precision p)
	Constructor. Creates an empty Blob object with the specified precision. More...

	Blob (Precision p, Layout l)
	The constructor creates an empty Blob object with the specified precision and layout. More...

	Blob (Precision p, const SizeVector &dims)
	The constructor creates an empty Blob object with the specified precision and dimensions. More...

	Blob (Precision p, Layout l, const SizeVector &dims)
	The constructor creates an empty Blob object with the specified precision, layout and dimensions. More...

size_t	Resize (const SizeVector &dims, Layout layout=Layout::ANY) noexcept
	Changes Tensor size to the specified dimensions. If it was allocated, the previous data is deallocated and lost. More...

size_t	Reshape (const SizeVector &dims, Layout layout=Layout::ANY) noexcept
	Changes tensor size to the specified dimensions without changing memory. The total size remains unchanged as well as the memory layout. More...

const SizeVector	dims () const noexcept
	Returns the tensor dimensions vector with reversed order. More...

virtual const TensorDesc &	getTensorDesc () const noexcept
	Returns the tensor description.

virtual TensorDesc &	getTensorDesc () noexcept
	Returns the tensor description.

virtual size_t	size () const noexcept
	By default, returns the total number of elements (a product of all the dims or 1 for scalar) More...

virtual size_t	byteSize () const noexcept
	Returns the size of the current Blob in bytes.

virtual size_t	element_size () const noexcept=0
	Returns the number of bytes per element. The overall Blob capacity is size() * element_size(). Abstract method.

virtual void	allocate () noexcept=0
	Allocates memory to store the data. Abstract method.

virtual bool	deallocate () noexcept=0
	Releases previously allocated data. Abstract method.

virtual LockedMemory< void >	buffer () noexcept=0
	Gets access to the allocated memory. Abstract method. More...

virtual LockedMemory< const void >	cbuffer () const noexcept=0
	Gets read-only access to the allocated memory. Abstract method. More...

Static Public Member Functions
static Ptr	CreateFromData (const DataPtr &data)
	Creates a TBlob<> object from a Data node. More...

Protected Member Functions
virtual const std::shared_ptr< IAllocator > &	getAllocator () const noexcept=0
	Gets an allocator for allocator-based blobs. More...

virtual void *	getHandle () const noexcept=0
	Gets a handle to allocated memory. More...

Static Protected Member Functions
static size_t	product (const SizeVector &dims) noexcept
	Multiplies the dimension vector's values. More...

Protected Attributes
TensorDesc	tensorDesc
	The tensor descriptor of the given blob.

Friends
template<typename >
class	TBlobProxy

Detailed Description

This class represents a universal container in the Inference Engine.

Note: Each Blob implementation must be derived from this Blob class directly or indirectly

Constructor & Destructor Documentation

§ Blob() [1/5]

InferenceEngine::Blob::Blob ( const TensorDesc & tensorDesc )

inlineexplicit

Constructor. Creates an empty Blob object with the specified precision.

Parameters

tensorDesc Defines the layout and dims of the blob

§ Blob() [2/5]

InferenceEngine::Blob::Blob ( Precision p )

inlineexplicit

Constructor. Creates an empty Blob object with the specified precision.

Deprecated:: Use Blob::Blob(const TensorDesc &).

Parameters

p	Precision type

§ Blob() [3/5]

InferenceEngine::Blob::Blob	(	Precision	p,
		Layout	l
	)

inline

The constructor creates an empty Blob object with the specified precision and layout.

Deprecated:: Use Blob::Blob(const TensorDesc &).

Parameters

p	Precision type
l	Layout

§ Blob() [4/5]

InferenceEngine::Blob::Blob	(	Precision	p,
		const SizeVector &	dims
	)

inline

The constructor creates an empty Blob object with the specified precision and dimensions.

Deprecated:: Use Blob::Blob(const TensorDesc &).

Parameters

p	Tensor precision type
dims	Tensor dimensions vector

§ Blob() [5/5]

InferenceEngine::Blob::Blob	(	Precision	p,
		Layout	l,
		const SizeVector &	dims
	)

inline

The constructor creates an empty Blob object with the specified precision, layout and dimensions.

Deprecated:: Use Blob::Blob(const TensorDesc &).

Parameters

p	tensor precision type
l	tensor layout
dims	Tensor dimensions vector with reversed order

Member Function Documentation

§ as() [1/2]

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>

T* InferenceEngine::Blob::as ( )

inlinenoexcept

Casts this Blob object to the type T*. Use InferenceEngine::as() to operate with shared Blob objects instead of raw pointers.

Template Parameters

T	Type to cast to. Must represent a class derived from the Blob

Returns: Raw pointer to the object of the type T or nullptr on error

§ as() [2/2]

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>

const T* InferenceEngine::Blob::as ( ) const

inlinenoexcept

Casts this Blob object to the type const T*. Use InferenceEngine::as() to operate with shared Blob objects instead of raw pointers.

Template Parameters

T	Type to cast to. Must represent a class derived from the Blob

Returns: Raw pointer to the object of the type const T or nullptr on error

§ buffer()

virtual LockedMemory<void> InferenceEngine::Blob::buffer ( )

pure virtualnoexcept

Gets access to the allocated memory. Abstract method.

Returns: A LockedMemory object

Implemented in InferenceEngine::TBlob< T, typename >, InferenceEngine::MemoryBlob, and InferenceEngine::CompoundBlob.

§ cbuffer()

virtual LockedMemory<const void> InferenceEngine::Blob::cbuffer ( ) const

pure virtualnoexcept

Gets read-only access to the allocated memory. Abstract method.

Returns: A LockedMemory object

Implemented in InferenceEngine::TBlob< T, typename >, InferenceEngine::MemoryBlob, and InferenceEngine::CompoundBlob.

§ CreateFromData()

static Ptr InferenceEngine::Blob::CreateFromData ( const DataPtr & data )

static

Creates a TBlob<> object from a Data node.

Parameters

Data	reference to a smart pointer of the Data node

Returns: Smart pointer to TBlob<> with the relevant C type to the precision of the data node

§ dims()

const SizeVector InferenceEngine::Blob::dims ( ) const

inlinenoexcept

Returns the tensor dimensions vector with reversed order.

Deprecated:: Use Blob::getTensorDesc and InferenceEngine::TensorDesc::getDims.

§ getAllocator()

virtual const std::shared_ptr<IAllocator>& InferenceEngine::Blob::getAllocator ( ) const

protectedpure virtualnoexcept

Gets an allocator for allocator-based blobs.

Returns: The allocator for allocator-based blobs or nullptr if there is none

Implemented in InferenceEngine::TBlob< T, typename >, InferenceEngine::MemoryBlob, and InferenceEngine::CompoundBlob.

§ getHandle()

virtual void* InferenceEngine::Blob::getHandle ( ) const

protectedpure virtualnoexcept

Gets a handle to allocated memory.

Returns: The handle to allocated memory for allocator-based blobs or nullptr if there is none

Implemented in InferenceEngine::TBlob< T, typename >, InferenceEngine::MemoryBlob, and InferenceEngine::CompoundBlob.

§ is() [1/2]

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>

bool InferenceEngine::Blob::is ( )

inlinenoexcept

Checks if the Blob object can be cast to the type T*.

Template Parameters

T	Type to be checked. Must represent a class derived from the Blob

Returns: true if this object can be dynamically cast to the type T*. Otherwise, false

§ is() [2/2]

template<typename T , typename std::enable_if< !std::is_pointer< T >::value &&!std::is_reference< T >::value, int >::type = 0, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>

bool InferenceEngine::Blob::is ( ) const

inlinenoexcept

Checks if the Blob object can be cast to the type const T*.

Template Parameters

T	Type to be checked. Must represent a class derived from the Blob

Returns: true if this object can be dynamically cast to the type const T*. Otherwise, false

§ layout()

Layout InferenceEngine::Blob::layout ( ) const

inlinenoexcept

Returns the tensor layout of the current Blob object.

Deprecated:: Use Blob::getTensorDesc and InferenceEngine::TensorDesc::getLayout to get the current layout

§ precision()

Precision InferenceEngine::Blob::precision ( ) const

inlinenoexcept

Returns the tensor precision of the current Blob object.

Deprecated:: Use Blob::getTensorDesc and InferenceEngine::TensorDesc::getPrecision to get the precision

§ product()

static size_t InferenceEngine::Blob::product ( const SizeVector & dims )

inlinestaticprotectednoexcept

Multiplies the dimension vector's values.

Parameters

dims	Reference to a vector with dimension values of type size_t

Returns: Result of multiplication

§ Reshape()

size_t InferenceEngine::Blob::Reshape	(	const SizeVector &	dims,
		Layout	layout = `Layout::ANY`
	)

inlinenoexcept

Changes tensor size to the specified dimensions without changing memory. The total size remains unchanged as well as the memory layout.

Deprecated:: The method works with reversed dimensions. Use Blob::getTensorDesc and InferenceEngine::TensorDesc::reshape.

Parameters

dims	New dimensions to set
layout	New layout to set

Returns: The total number of elements (a product of all the dims)

§ Resize()

size_t InferenceEngine::Blob::Resize	(	const SizeVector &	dims,
		Layout	layout = `Layout::ANY`
	)

inlinenoexcept

Changes Tensor size to the specified dimensions. If it was allocated, the previous data is deallocated and lost.

Deprecated:: The method works with reversed dimensions. Create a new blob if you want to change a size.

Parameters

dims	New dimensions to set
layout	New layout to set

Returns: Total number of elements (a product of all the dimensions)

§ size()

virtual size_t InferenceEngine::Blob::size ( ) const

inlinevirtualnoexcept

By default, returns the total number of elements (a product of all the dims or 1 for scalar)

Return value and its interpretation heavily depend on the blob type

Reimplemented in InferenceEngine::MemoryBlob, and InferenceEngine::CompoundBlob.

§ type()

Precision InferenceEngine::Blob::type ( ) const

inlinenoexcept

Returns the tensor precision of the current Blob object.

Deprecated:: Use Blob::getTensorDesc and InferenceEngine::TensorDesc::getPrecision to get the precision

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

tmp_docs/inference-engine/include/ie_blob.h

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Static Protected Member Functions

Protected Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

§ Blob() [1/5]

§ Blob() [2/5]

§ Blob() [3/5]

§ Blob() [4/5]

§ Blob() [5/5]

Member Function Documentation

§ as() [1/2]

§ as() [2/2]

§ buffer()

§ cbuffer()

§ CreateFromData()

§ dims()

§ getAllocator()

§ getHandle()

§ is() [1/2]

§ is() [2/2]

§ layout()

§ precision()

§ product()

§ Reshape()

§ Resize()

§ size()

§ type()