InferenceEngine Namespace Reference

Inference Engine API. More...

Namespaces
	Builder
	Neural network builder API.
	CLDNNConfigParams
	GPU plugin configuration.
	DLIAConfigParams
	DLIA plugin configuration.
	DliaMetrics
	DLIA plugin metrics.
	GNAConfigParams
	GNA plugin configuration.
	HeteroConfigParams
	Heterogeneous plugin configuration.
	Metrics
	Metrics
	MultiDeviceConfigParams
	Multi Device plugin configuration.
	PluginConfigParams
	Generic plugin configuration.
	VPUConfigParams
	VPU plugin configuration.

Data Structures
class	BatchNormalizationLayer
	This class represents a Batch Normalization Layer. More...
class	BinaryConvolutionLayer
	This class represents a standard binary convolution layer. More...
class	Blob
	This class represents a universal container in the Inference Engine. More...
class	BlockingDesc
	This class describes blocking layouts. More...
class	BroadcastLayer
	This class represents a standard Broadcast layer Broadcast modifies input tensor dimensions according parameters. More...
class	ClampLayer
	This class represents a Clamp activation layer Clamps all tensor elements into the range [min_value, max_value]. More...
class	CNNLayer
	This is a base abstraction Layer - all DNN Layers inherit from this class. More...
class	CNNNetReader
	This is a wrapper class used to build and parse a network from the given IR. All the methods here can throw exceptions. More...
class	CNNNetwork
	This class contains all the information about the Neural Network and the related binary information. More...
class	CompoundBlob
	This class represents a blob that contains other blobs. More...
class	ConcatLayer
	This class represents concatenation layer Takes as input several data elements and merges them to one using the supplied axis. More...
class	Connection
	This class is the main object to describe the Inference Engine connection. More...
class	Context
	This class implements object. More...
class	ConvolutionLayer
	This class represents a standard 3D Convolution Layer. More...
class	Core
	This class represents Inference Engine Core entity. It can throw exceptions safely for the application, where it is properly handled. More...
class	CropLayer
	This class represents a standard crop layer. More...
class	Data
	This class represents the main Data representation node. More...
struct	DataConfig
	This structure describes data configuration. More...
class	DeconvolutionLayer
	This class represents a standard deconvolution layer. More...
class	DeformableConvolutionLayer
	This class represents a standard deformable convolution layer. More...
class	DepthToSpaceLayer
	This class represents a standard Depth To Space layer Depth To Space picks from input tensor according parameters. More...
class	EltwiseLayer
	This class represents an element wise operation layer. More...
class	ExecutableNetwork
	wrapper over IExecutableNetwork More...
class	Extension
	This class is a C++ helper to work with objects created using extensions. More...
class	FillLayer
	This class represents a standard Fill layer RFill modifies input tensor according parameters. More...
struct	FindPluginRequest
	Defines a message that contains the InferenceEngine::TargetDevice object to find a plugin for. More...
struct	FindPluginResponse
	Defines a message that contains a list of appropriate plugin names. More...
class	FullyConnectedLayer
	This class represents a fully connected layer. More...
class	GatherLayer
	This class represents a standard Gather layer Gather slices from Dictionary according to Indexes. More...
class	GemmLayer
	This class represents a general matrix multiplication operation layer Formula is: dst := alpha*src1*src2 + beta*src3. More...
class	GeneralError
	This class represents StatusCode::GENERIC_ERROR exception. More...
class	GRNLayer
	This class represents standard GRN Layer. More...
class	GRUCell
	GRU Cell layer. More...
class	IAllocator
	Allocator concept to be used for memory management and is used as part of the Blob. More...
class	ICNNNetReader
	This class is the main interface to build and parse a network from a given IR. More...
class	ICNNNetwork
	This is the main interface to describe the NN topology. More...
class	ICNNNetworkStats
	This is the interface to describe the NN topology scoring statistics. More...
class	IErrorListener
	This class represents a custom error listener. Plugin consumers can provide it via InferenceEngine::SetLogCallback. More...
class	IExecutableNetwork
	This is an interface of an executable network. More...
class	IExtension
	This class is the main extension interface. More...
class	IHeteroDeviceLoader
	This interface describes a mechanism of custom loaders to be used in heterogeneous plugin during setting of affinity and loading of split sub-network to the plugins The custom loader can define addition settings for the plugins or network loading Examples of cases when this interface should be implemented in the application: More...
class	IHeteroInferencePlugin
	This interface extends regular plugin interface for heterogeneous case. Not all plugins implements it. The main purpose of this interface - to register loaders and have an ability to get default settings for affinity on certain devices. More...
class	IInferencePlugin
	This class is a main plugin interface. More...
class	IInferRequest
	This is an interface of asynchronous infer request. More...
class	ILayer
	This class is the main interface to describe the Inference Engine layer. All methods here are constant and do not throw exceptions. More...
class	ILayerExecImpl
	This class provides interface for the implementation with the custom execution code. More...
class	ILayerImpl
	This class provides interface for extension implementations. More...
class	ILayerImplFactory
	This class provides interface for extension factories. More...
class	IMemoryState
	manages data for reset operations More...
class	INetwork
	This class is the main interface to describe the Inference Engine network. More...
class	INetwotkIterator
struct	InferenceEngineProfileInfo
	Represents basic inference profiling information per layer. If the layer is executed using tiling, the sum time per each tile is indicated as the total execution time. Due to parallel execution, the total execution time for all layers might be greater than the total inference time. More...
class	InferencePlugin
	This class is a C++ API wrapper for IInferencePlugin. It can throw exceptions safely for the application, where it is properly handled. More...
class	InferNotStarted
	This class represents StatusCode::INFER_NOT_STARTED exception. More...
class	InferRequest
	This class is a wrapper of IInferRequest to provide setters/getters of input/output which operates with BlobMaps. It can throw exceptions safely for the application, where it is properly handled. More...
class	InputInfo
	This class contains information about each input of the network. More...
class	IShapeInferExtension
	This class is the reader extension interface to provide implementation for shape propagation. More...
class	IShapeInferImpl
	This class provides interface for the implementation with the custom execution code. More...
struct	LayerComplexity
	Contains information about floating point operations and common size of parameter blobs. More...
struct	LayerConfig
	This structure describes Layer configuration. More...
struct	LayerParams
	This is an internal common Layer parameter parsing arguments. More...
class	LayoutOffsetCounter
	This class helps calculating offset in different layouts. More...
class	LockedMemory
	This class represents locked memory for read/write memory. More...
class	LockedMemory< const T >
	This class is for read-only segments. More...
class	LockedMemory< void >
	This class is for <void*> data and allows casting to any pointers. More...
class	LSTMCell
	LSTM Cell layer. More...
class	MathLayer
	This class represents a standard Math layers Math modifies input tensor dimensions according parameters. More...
class	MemoryBlob
	This class implements a container object that represents a tensor in memory (host and remote/accelerated) More...
class	MemoryState
	c++ exception based error reporting wrapper of API class IMemoryState More...
class	MVNLayer
	This class represents standard MVN Layer. More...
class	NetworkNodeStats
	This class implements a container which stores statistics for a layer. More...
class	NetworkNotLoaded
	This class represents StatusCode::NETWORK_NOT_LOADED exception. More...
class	NonMaxSuppressionLayer
	This class represents a standard NonMaxSuppression layer. More...
class	NormLayer
	This class represents a Linear Response Normalization (LRN) Layer. More...
class	NotAllocated
	This class represents StatusCode::NOT_ALLOCATED exception. More...
class	NotFound
	This class represents StatusCode::NOT_FOUND exception. More...
class	NotImplemented
	This class represents StatusCode::NOT_IMPLEMENTED exception. More...
class	NV12Blob
	Represents a blob that contains two planes (Y and UV) in NV12 color format. More...
class	OneHotLayer
	This class represents a OneHot layer Converts input into OneHot representation. More...
class	OutOfBounds
	This class represents StatusCode::OUT_OF_BOUNDS exception. More...
class	PadLayer
	This class represents a standard Pad layer Adds paddings to input tensor. More...
class	Parameter
	This class represents an object to work with different parameters. More...
class	ParameterMismatch
	This class represents StatusCode::PARAMETER_MISMATCH exception. More...
class	PluginDispatcher
	This is a class to load a suitable plugin. More...
class	PoolingLayer
	This class represents a standard pooling layer. More...
class	Port
	This class is the main object to describe the Inference Engine port. More...
class	PortData
class	PortInfo
	This class contains a pair from layerId and port index. More...
class	PowerLayer
	This class represents a standard Power Layer Formula is: output = (offset + scale * input) ^ power. More...
class	Precision
	This class holds precision value and provides precision related operations. More...
struct	PrecisionTrait
	Particular precision traits. More...
class	PReLULayer
	This class represents a Layer which performs Scale and Shift. More...
struct	PreProcessChannel
	This structure stores info about pre-processing of network inputs (scale, mean image, ...) More...
class	PreProcessInfo
	This class stores pre-process information for the input. More...
struct	PrimitiveInfo
	Structure with information about Primitive. More...
class	PropertyVector
class	QuantizeLayer
	This class represents a quantization operation layer Element-wise linear quantization of floating point input values into a descrete set of floating point values. More...
struct	QueryNetworkResult
	Responce structure encapsulating information about supported layer. More...
class	RangeLayer
	This class represents a standard RangeLayer layer RangeLayer modifies input tensor dimensions according parameters. More...
class	ReduceLayer
	This class represents a standard Reduce layers Reduce modifies input tensor according parameters. More...
class	ReLU6Layer
	This class represents a ReLU6 activation layer Clamps all tensor elements into the range [0, 6.0]. More...
class	ReLULayer
	This class represents a Rectified Linear activation layer. More...
class	RequestBusy
	This class represents StatusCode::REQUEST_BUSY exception. More...
class	ReshapeLayer
	This class represents a standard reshape layer. More...
struct	ResponseDesc
	Represents detailed information for an error. More...
class	ResultNotReady
	This class represents StatusCode::RESULT_NOT_READY exception. More...
class	ReverseSequenceLayer
	This class represents a standard Reverse Sequence layer Reverse Sequence modifies input tensor according parameters. More...
class	RNNCell
	RNN Cell layer. More...
class	RNNCellBase
	Base class for recurrent cell layers. More...
class	RNNSequenceLayer
	Sequence of recurrent cells. More...
struct	ROI
	This structure describes ROI data. More...
class	ScaleShiftLayer
	This class represents a Layer which performs Scale and Shift. More...
class	ScatterLayer
	This class represents a standard Scatter layer. More...
class	SelectLayer
	This class represents a SelectLayer layer SelectLayer layer takes elements from the second (“then”) or the third (“else”) input based on condition mask (“cond”) provided in the first input. The “cond” tensor is broadcasted to “then” and “else” tensors. The output tensor shape is equal to broadcasted shape of “cond”, “then” and “else”. More...
class	ShapeInferExtension
	This class is a C++ helper to work with objects created using extensions. More...
class	ShuffleChannelsLayer
	This class represents a standard Shuffle Channels layer Shuffle Channels picks from input tensor according parameters. More...
class	SoftMaxLayer
	This class represents standard softmax Layer. More...
class	SpaceToDepthLayer
	This class represents a standard Space To Depth layer Depth To Space picks from input tensor according parameters. More...
class	SparseFillEmptyRowsLayer
	This class represents SparseFillEmptyRows layer SparseFillEmptyRows fills empty rows in a sparse tensor. More...
class	SplitLayer
	This class represents a layer that evenly splits the input into the supplied outputs. More...
class	StridedSliceLayer
	This class represents a standard Strided Slice layer Strided Slice picks from input tensor according parameters. More...
class	TargetDeviceInfo
	Describes the relationship between the enumerator type and the actual device's name. More...
class	TBlob
	Represents real host memory allocated for a Tensor/Blob per C type. More...
class	TensorDesc
	This class defines Tensor description. More...
struct	TensorInfo
	This structure describes tensor information. More...
class	TensorIterator
	This class represents TensorIterator layer. More...
class	TileLayer
	This class represents a standard Tile Layer. More...
class	TopKLayer
	This class represents a standard TopK layer TopK picks top K values from input tensor according parameters. More...
class	Unexpected
	This class represents StatusCode::UNEXPECTED exception. More...
class	UniqueLayer
	This class represents Unique layer. The Unique operation searches for unique elements in 1-D input. More...
union	UserValue
	The method holds the user values to enable binding of data per graph node. More...
struct	Version
	Represents version information that describes plugins and the inference engine runtime library. More...
class	WeightableLayer
	This class represents a layer with Weights and/or Biases (e.g. Convolution/Fully Connected, etc.) More...

Typedefs
using	BlobMap = std::map< std::string, Blob::Ptr >
	This is a convenient type for working with a map containing pairs(string, pointer to a Blob instance).
using	SizeVector = std::vector< size_t >
	Represents tensor size. The order is opposite to the order in Caffe*: (w,h,n,b) where the most frequently changing element in memory is first.
using	CNNLayerPtr = std::shared_ptr< CNNLayer >
	A smart pointer to the CNNLayer.
using	CNNLayerWeakPtr = std::weak_ptr< CNNLayer >
	A smart weak pointer to the CNNLayer.
using	DataPtr = std::shared_ptr< Data >
	Smart pointer to Data.
using	CDataPtr = std::shared_ptr< const Data >
	Smart pointer to constant Data.
using	DataWeakPtr = std::weak_ptr< Data >
	Smart weak pointer to Data.
using	OutputsDataMap = std::map< std::string, DataPtr >
	A collection that contains string as key, and Data smart pointer as value.
using	NetworkNodeStatsPtr = std::shared_ptr< NetworkNodeStats >
	A shared pointer to the NetworkNodeStats object.
using	NetworkNodeStatsWeakPtr = std::weak_ptr< NetworkNodeStats >
	A smart pointer to the NetworkNodeStats object.
using	NetworkStatsMap = std::map< std::string, NetworkNodeStatsPtr >
	A map of pairs: name of a layer and related statistics.
using	ConstOutputsDataMap = std::map< std::string, CDataPtr >
	A collection that contains string as key, and const Data smart pointer as value.
using	IExtensionPtr = std::shared_ptr< IExtension >
using	IShapeInferExtensionPtr = std::shared_ptr< IShapeInferExtension >
using	MapDeviceLoaders = std::map< std::string, InferenceEngine::IHeteroDeviceLoader::Ptr >
	Represents map from device name to device-specific loader.
using	InputsDataMap = std::map< std::string, InputInfo::Ptr >
	A collection that contains string as key, and InputInfo smart pointer as value.
using	ConstInputsDataMap = std::map< std::string, InputInfo::CPtr >
	A collection that contains string as key, and const InputInfo smart pointer as value.
using	GenericLayer = class CNNLayer
	Alias for CNNLayer object.
using	idx_t = size_t
	A type of network objects indexes.
using	InferenceEnginePluginPtr = InferenceEngine::details::SOPointer< IInferencePlugin >
	A C++ helper to work with objects created by the plugin. Implements different interfaces.
using	HeteroPluginPtr = InferenceEngine::details::SOPointer< IHeteroInferencePlugin >
	A C++ helper to work with objects created by the plugin. Implements different interfaces.

Enumerations
enum	LockOp { LOCK_FOR_READ = 0, LOCK_FOR_WRITE }
	Allocator handle mapping type.
enum	Layout : uint8_t {   ANY = 0, NCHW = 1, NHWC = 2, NCDHW = 3,   NDHWC = 4, OIHW = 64, SCALAR = 95, C = 96,   CHW = 128, HW = 192, NC = 193, CN = 194,   BLOCKED = 200 }
	Layouts that the inference engine supports.
enum	ColorFormat : uint32_t {   RAW = 0u, RGB, BGR, RGBX,   BGRX, NV12 }
	Extra information about input color format for preprocessing. More...
enum	StatusCode : int {   OK = 0, GENERAL_ERROR = -1, NOT_IMPLEMENTED = -2, NETWORK_NOT_LOADED = -3,   PARAMETER_MISMATCH = -4, NOT_FOUND = -5, OUT_OF_BOUNDS = -6, UNEXPECTED = -7,   REQUEST_BUSY = -8, RESULT_NOT_READY = -9, NOT_ALLOCATED = -10, INFER_NOT_STARTED = -11,   NETWORK_NOT_READ = -12 }
	This enum contains codes for all possible return values of the interface functions.
enum	TargetDevice : uint8_t {   eDefault = 0, eBalanced = 1, eCPU = 2, eGPU = 3,   eFPGA = 4, eMYRIAD = 5, eHDDL = 6, eGNA = 7,   eHETERO = 8, eMULTI = 10 }
	Describes known device types. More...
enum	eDIMS_AXIS : uint8_t { X_AXIS = 0, Y_AXIS, Z_AXIS }
enum	MeanVariant { MEAN_IMAGE, MEAN_VALUE, NONE }
	Defines available types of mean. More...
enum	ResizeAlgorithm { NO_RESIZE = 0, RESIZE_BILINEAR, RESIZE_AREA }
	Represents the list of supported resize algorithms.

Functions
template<class T >
std::shared_ptr< T >	make_so_pointer (const file_name_t &name)=delete
	Creates a special shared_pointer wrapper for the given type from a specific shared module. More...
InferenceEngine::IAllocator *	CreateDefaultAllocator () noexcept
	Creates the default implementation of the Inference Engine allocator per plugin. 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>
std::shared_ptr< T >	as (const Blob::Ptr &blob) noexcept
	Helper cast function to work with shared Blob objects. 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>
std::shared_ptr< const T >	as (const Blob::CPtr &blob) noexcept
	Helper cast function to work with shared Blob objects. More...
template<class Type >
TBlob< Type >::Ptr	make_shared_blob (Precision p, Layout l, const SizeVector &dims)
	Creates a blob with given precision and dimensions. More...
template<class Type >
TBlob< Type >::Ptr	make_shared_blob (Precision p, const SizeVector &dims)
	Creates a blob with the NCHW layout, given precision, and given dimensions. More...
template<typename Type , class TArg >
InferenceEngine::TBlob< Type >::Ptr	make_shared_blob (Precision p, Layout l, const TArg &arg)
	Creates a blob with the given precision. More...
template<typename Type , class TArg >
InferenceEngine::TBlob< Type >::Ptr	make_shared_blob (Precision p, const TArg &arg)
	Creates a blob with the NCHW layout and given tensor precision. More...
template<typename Type >
InferenceEngine::TBlob< Type >::Ptr	make_shared_blob (const TensorDesc &tensorDesc)
	Creates a blob with the given tensor descriptor. More...
template<typename Type >
InferenceEngine::TBlob< Type >::Ptr	make_shared_blob (const TensorDesc &tensorDesc, Type *ptr, size_t size=0)
	Creates a blob with the given tensor descriptor from the pointer to the pre-allocated memory. More...
template<typename Type >
InferenceEngine::TBlob< Type >::Ptr	make_shared_blob (const TensorDesc &tensorDesc, const std::shared_ptr< InferenceEngine::IAllocator > &alloc)
	Creates a blob with the given tensor descriptor and allocator. More...
template<typename TypeTo >
InferenceEngine::TBlob< TypeTo >::Ptr	make_shared_blob (TBlob< TypeTo > &&arg)
	Gets a shared pointer for the new TBlob instance. The created instance is based on move semantics from the given TBlob instance. More...
template<typename TypeTo >
InferenceEngine::TBlob< TypeTo >::Ptr	make_shared_blob (const TBlob< TypeTo > &arg)
	Creates a copy of given TBlob instance. More...
template<typename TypeTo >
InferenceEngine::TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, Layout l=NCHW)
	Creates a blob with the given precision. More...
template<typename TypeTo >
TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, Layout l, SizeVector dims, const std::vector< TypeTo > &arg)
	Creates a blob with the given precision, layout and dimensions from the vector of values. More...
template<typename TypeTo >
TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, Layout l, const std::vector< TypeTo > &arg)
	Creates a blob with the given precision from the vector of values. More...
template<typename TypeTo >
TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, const std::vector< TypeTo > &arg)
	Creates a blob with the NCHW layout and the given precision from the vector of values. More...
template<typename TypeTo >
TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, Layout l, const SizeVector &dims, TypeTo *ptr, size_t size=0)
	Creates a blob with the given precision from the pointer to the pre-allocated memory. More...
template<typename TypeTo >
TBlob< TypeTo >::Ptr	make_shared_blob (Precision p, const SizeVector &dims, TypeTo *ptr, size_t size=0)
	Creates a blob with the NCHW layout and the given precision from the pointer to the pre-allocated memory. More...
template<typename T , typename ... Args, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>
std::shared_ptr< T >	make_shared_blob (Args &&...args)
	Creates a Blob object of the specified type. More...
Blob::Ptr	make_shared_blob (const Blob::Ptr &inputBlob, const ROI &roi)
	Creates a blob describing given ROI object based on the given blob with pre-allocated memory. More...
std::ostream &	operator<< (std::ostream &out, const Layout &p)
std::ostream &	operator<< (std::ostream &out, const ColorFormat &fmt)
const char *	getDeviceName (TargetDevice device)
	Returns the device name. More...
FindPluginResponse	findPlugin (const FindPluginRequest &req)
	Finds an appropriate plugin for requested target device. More...
StatusCode	findPlugin (const FindPluginRequest &req, FindPluginResponse &result, ResponseDesc *resp) noexcept
	Finds an appropriate plugin for requested target device. More...
template<>
std::shared_ptr< IShapeInferExtension >	make_so_pointer (const file_name_t &name)
	Creates a special shared_pointer wrapper for the given type from a specific shared module. More...
template<>
std::shared_ptr< IExtension >	make_so_pointer (const file_name_t &name)
	Creates a special shared_pointer wrapper for the given type from a specific shared module. More...
ICNNNetReader *	CreateCNNNetReader () noexcept
	Creates a CNNNetReader instance. More...
StatusCode	CreateExtension (IExtension *&ext, ResponseDesc *resp) noexcept
	Creates the default instance of the extension. More...
StatusCode	CreateShapeInferExtension (IShapeInferExtension *&ext, ResponseDesc *resp) noexcept
	Creates the default instance of the shape infer extension. More...
template<typename T >
void	ConvertLayout (Layout sourceLayout, Layout destLayout, const T *sourceBuffer, T *destBuffer, SizeVector dims)
template<typename F >
void	parallel_nt (int nthr, const F &func)
template<typename F >
void	parallel_nt_static (int nthr, const F &func)
template<typename I , typename F >
void	parallel_sort (I begin, I end, const F &comparator)
template<typename T0 , typename R , typename F >
R	parallel_sum (const T0 &D0, const R &input, const F &func)
template<typename T0 , typename T1 , typename R , typename F >
R	parallel_sum2d (const T0 &D0, const T1 &D1, const R &input, const F &func)
template<typename T0 , typename T1 , typename T2 , typename R , typename F >
R	parallel_sum3d (const T0 &D0, const T1 &D1, const T2 &D2, const R &input, const F &func)
template<typename T >
T	parallel_it_init (T start)
template<typename T , typename Q , typename R , typename... Args>
T	parallel_it_init (T start, Q &x, const R &X, Args &&... tuple)
bool	parallel_it_step ()
template<typename Q , typename R , typename... Args>
bool	parallel_it_step (Q &x, const R &X, Args &&... tuple)
template<typename T , typename Q >
void	splitter (const T &n, const Q &team, const Q &tid, T &n_start, T &n_end)
template<typename T0 , typename F >
void	for_1d (const int &ithr, const int &nthr, const T0 &D0, const F &func)
template<typename T0 , typename F >
void	parallel_for (const T0 &D0, const F &func)
template<typename T0 , typename T1 , typename F >
void	for_2d (const int &ithr, const int &nthr, const T0 &D0, const T1 &D1, const F &func)
template<typename T0 , typename T1 , typename F >
void	parallel_for2d (const T0 &D0, const T1 &D1, const F &func)
template<typename T0 , typename T1 , typename T2 , typename F >
void	for_3d (const int &ithr, const int &nthr, const T0 &D0, const T1 &D1, const T2 &D2, const F &func)
template<typename T0 , typename T1 , typename T2 , typename F >
void	parallel_for3d (const T0 &D0, const T1 &D1, const T2 &D2, const F &func)
template<typename T0 , typename T1 , typename T2 , typename T3 , typename F >
void	for_4d (const int &ithr, const int &nthr, const T0 &D0, const T1 &D1, const T2 &D2, const T3 &D3, const F &func)
template<typename T0 , typename T1 , typename T2 , typename T3 , typename F >
void	parallel_for4d (const T0 &D0, const T1 &D1, const T2 &D2, const T3 &D3, const F &func)
template<typename T0 , typename T1 , typename T2 , typename T3 , typename T4 , typename F >
void	for_5d (const int &ithr, const int &nthr, const T0 &D0, const T1 &D1, const T2 &D2, const T3 &D3, const T4 &D4, const F &func)
template<typename T0 , typename T1 , typename T2 , typename T3 , typename T4 , typename F >
void	parallel_for5d (const T0 &D0, const T1 &D1, const T2 &D2, const T3 &D3, const T4 &D4, const F &func)
StatusCode	CreatePluginEngine (IInferencePlugin *&plugin, ResponseDesc *resp) noexcept
	Creates the default instance of the interface (per plugin) More...
std::string	fileNameToString (const file_name_t &str)
	Conversion from possibly-wide character string to a single-byte chain.
file_name_t	stringToFileName (const std::string &str)
	Conversion from single-byte character string to a possibly-wide one.
std::unordered_map< std::string, LayerComplexity >	getNetworkComplexity (const InferenceEngine::ICNNNetwork &network)
	Computes per layer theoretical computational and memory complexity. More...
const Version *	GetInferenceEngineVersion () noexcept
	Gets the current Inference Engine version. More...
template<class T >
void	TopResults (unsigned int n, TBlob< T > &input, std::vector< unsigned > &output)
	Gets the top n results from a tblob. More...
void	TopResults (unsigned int n, Blob &input, std::vector< unsigned > &output)
	Gets the top n results from a blob. More...
template<typename data_t >
void	copyFromRGB8 (uint8_t *RGB8, size_t RGB8_size, InferenceEngine::TBlob< data_t > *blob)
	Copies a 8-bit RGB image to the blob. Throws an exception in case of dimensions or input size mismatch. More...
void	ConvertImageToInput (unsigned char *imgBufRGB8, size_t lengthbytesSize, Blob &input)
	Splits the RGB channels to either I16 Blob or float blob. The image buffer is assumed to be packed with no support for strides. More...
template<typename T >
void	copyToFloat (float *dst, const InferenceEngine::Blob *src)
	Copies data from a certain precision to float. More...

Variables
constexpr const int	MAX_DIMS_NUMBER = 12
static const size_t	I_N = 3
static const size_t	I_C = 2
static const size_t	I_H = 1
static const size_t	I_W = 0

Detailed Description

Inference Engine API.

Enumeration Type Documentation

ColorFormat

enum InferenceEngine::ColorFormat : uint32_t

Extra information about input color format for preprocessing.

Enumerator
RAW	Plain blob (default), no extra color processing required.
RGB	RGB color format.
BGR	BGR color format, default in DLDT.
RGBX	RGBX color format with X ignored during inference.
BGRX	BGRX color format with X ignored during inference.
NV12	NV12 color format represented as compound Y+UV blob.

MeanVariant

enum InferenceEngine::MeanVariant

Defines available types of mean.

Enumerator
MEAN_IMAGE	mean value is specified for each input pixel
MEAN_VALUE	mean value is specified for each input channel
NONE	no mean value specified

TargetDevice

enum InferenceEngine::TargetDevice : uint8_t

strong

Describes known device types.

Deprecated:

Deprecated since the enum is not scalable for 3rd party plugins / devices. All devices are managed by InferenceEngine::Core

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>

std::shared_ptr<T> InferenceEngine::as ( const Blob::Ptr &  blob )

noexcept

Helper cast function to work with shared Blob objects.

Returns

shared_ptr to the type T. Returned shared_ptr shares ownership of the object with the input Blob::Ptr

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>

std::shared_ptr<const T> InferenceEngine::as ( const Blob::CPtr &  blob )

noexcept

Helper cast function to work with shared Blob objects.

Returns

shared_ptr to the type const T. Returned shared_ptr shares ownership of the object with the input Blob::Ptr

ConvertImageToInput()

void InferenceEngine::ConvertImageToInput ( unsigned char *  imgBufRGB8, size_t  lengthbytesSize, Blob &  input  )

inline

Splits the RGB channels to either I16 Blob or float blob. The image buffer is assumed to be packed with no support for strides.

Parameters

imgBufRGB8	Packed 24bit RGB image (3 bytes per pixel: R-G-B)
lengthbytesSize	Size in bytes of the RGB image. It is equal to amount of pixels times 3 (number of channels)
input	Blob to contain the split image (to 3 channels)

ConvertLayout()

template<typename T >

void InferenceEngine::ConvertLayout	(	Layout	sourceLayout,
		Layout	destLayout,
		const T *	sourceBuffer,
		T *	destBuffer,
		SizeVector	dims
	)

Deprecated:

Please use TensorDesc for conversion

copyFromRGB8()

template<typename data_t >

void InferenceEngine::copyFromRGB8	(	uint8_t *	RGB8,
		size_t	RGB8_size,
		InferenceEngine::TBlob< data_t > *	blob
	)

Copies a 8-bit RGB image to the blob. Throws an exception in case of dimensions or input size mismatch.

Template Parameters

data_t

Type of the target blob

Parameters

RGB8	8-bit RGB image
RGB8_size	Size of the image
blob	Target blob to write image to

copyToFloat()

template<typename T >

void InferenceEngine::copyToFloat	(	float *	dst,
		const InferenceEngine::Blob *	src
	)

Copies data from a certain precision to float.

Parameters

dst	Pointer to an output float buffer, must be allocated before the call
src	Source blob to take data from

CreateCNNNetReader()

ICNNNetReader* InferenceEngine::CreateCNNNetReader ( )

noexcept

Creates a CNNNetReader instance.

Returns

An object that implements the ICNNNetReader interface

CreateDefaultAllocator()

InferenceEngine::IAllocator* InferenceEngine::CreateDefaultAllocator ( )

noexcept

Creates the default implementation of the Inference Engine allocator per plugin.

Returns

The Inference Engine IAllocator* instance

CreateExtension()

StatusCode InferenceEngine::CreateExtension ( IExtension *&  ext, ResponseDesc *  resp  )

noexcept

Creates the default instance of the extension.

Parameters

ext	Extension interface
resp	Response description

Returns

Status code

CreatePluginEngine()

StatusCode InferenceEngine::CreatePluginEngine ( IInferencePlugin *&  plugin, ResponseDesc *  resp  )

noexcept

Creates the default instance of the interface (per plugin)

Parameters

plugin	Pointer to the plugin
resp	Pointer to the response message that holds a description of an error if any occurred

Returns

Status code of the operation. OK if succeeded

CreateShapeInferExtension()

StatusCode InferenceEngine::CreateShapeInferExtension ( IShapeInferExtension *&  ext, ResponseDesc *  resp  )

noexcept

Creates the default instance of the shape infer extension.

Parameters

ext	Shape Infer Extension interface
resp	Response description

Returns

Status code

findPlugin() [1/2]

FindPluginResponse InferenceEngine::findPlugin

(

const FindPluginRequest &

req

)

Finds an appropriate plugin for requested target device.

Deprecated:

Deprecated since InferenceEngine::TargetDevice is deprecated

Parameters

req	A requested target device

Returns

A response object

findPlugin() [2/2]

StatusCode InferenceEngine::findPlugin ( const FindPluginRequest &  req, FindPluginResponse &  result, ResponseDesc *  resp  )

noexcept

Finds an appropriate plugin for requested target device.

Deprecated:

Deprecated since InferenceEngine::TargetDevice is deprecated

Parameters

req	A requested target device
result	The results of the request
resp	The response message description

Returns

A status code

getDeviceName()

const char* InferenceEngine::getDeviceName ( TargetDevice  device )

inline

Returns the device name.

Deprecated:

Deprecated since InferenceEngine::TargetDevice is deprecated

Parameters

device

Instance of InferenceEngine::TargetDevice

Returns

A c-string with the name

GetInferenceEngineVersion()

const Version* InferenceEngine::GetInferenceEngineVersion ( )

noexcept

Gets the current Inference Engine version.

Returns

The current Inference Engine version

getNetworkComplexity()

std::unordered_map<std::string, LayerComplexity> InferenceEngine::getNetworkComplexity

(

const InferenceEngine::ICNNNetwork &

network

)

Computes per layer theoretical computational and memory complexity.

Parameters

network

input graph

Returns

map from layer name to layer complexity

make_shared_blob() [1/17]

template<class Type >

TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l, const SizeVector &  dims  )

inline

Creates a blob with given precision and dimensions.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

Type	Type of the shared pointer to be created

Parameters

p	Given precision
dims	Given dimensions

Returns

A shared pointer to the created blob

make_shared_blob() [2/17]

template<class Type >

TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( Precision  p, const SizeVector &  dims  )

inline

Creates a blob with the NCHW layout, given precision, and given dimensions.

Deprecated:

Use the make_shared_blob signature which accepts TensorDesc

Template Parameters

Type	Type of the shared pointer to be created

Parameters

p	Given precision
dims	Given dimensions

Returns

A shared pointer to the created blob

make_shared_blob() [3/17]

template<typename Type , class TArg >

InferenceEngine::TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l, const TArg &  arg  )

inline

Creates a blob with the given precision.

Deprecated:

Use the make_shared_blob signature which accepts TensorDesc

Template Parameters

Type	Type of the shared pointer to be created

Parameters

p	Given precision
arg	Shared pointer to IAllocator to use in the blob

Returns

A shared pointer to the blob created

make_shared_blob() [4/17]

template<typename Type , class TArg >

InferenceEngine::TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( Precision  p, const TArg &  arg  )

inline

Creates a blob with the NCHW layout and given tensor precision.

Deprecated:

Use the make_shared_blob signature which accepts TensorDesc

Template Parameters

Type	Type of the shared pointer to be created

Parameters

p	Given precision
arg	Shared pointer to IAllocator to use in the blob

Returns

A shared pointer to the blob created

make_shared_blob() [5/17]

template<typename Type >

InferenceEngine::TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( const TensorDesc &  tensorDesc )

inline

Creates a blob with the given tensor descriptor.

Template Parameters

Type	Type of the shared pointer to be created

Parameters

tensorDesc

Tensor descriptor for Blob creation

Returns

A shared pointer to the newly created blob of the given type

make_shared_blob() [6/17]

template<typename Type >

InferenceEngine::TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( const TensorDesc &  tensorDesc, Type *  ptr, size_t  size = 0  )

inline

Creates a blob with the given tensor descriptor from the pointer to the pre-allocated memory.

Template Parameters

Type	Type of the shared pointer to be created

Parameters

tensorDesc	TensorDesc for Blob creation
ptr	Pointer to the pre-allocated memory
size	Length of the pre-allocated array

Returns

A shared pointer to the newly created blob of the given type

make_shared_blob() [7/17]

template<typename Type >

InferenceEngine::TBlob<Type>::Ptr InferenceEngine::make_shared_blob ( const TensorDesc &  tensorDesc, const std::shared_ptr< InferenceEngine::IAllocator > &  alloc  )

inline

Creates a blob with the given tensor descriptor and allocator.

Template Parameters

Type	Type of the shared pointer to be created

Parameters

tensorDesc	Tensor descriptor for Blob creation
alloc	Shared pointer to IAllocator to use in the blob

Returns

A shared pointer to the newly created blob of the given type

make_shared_blob() [8/17]

template<typename TypeTo >

InferenceEngine::TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( TBlob< TypeTo > &&  arg )

inline

Gets a shared pointer for the new TBlob instance. The created instance is based on move semantics from the given TBlob instance.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

arg	rvalue for the blob to move from

Returns

A shared pointer to the newly created blob of the given type

make_shared_blob() [9/17]

template<typename TypeTo >

InferenceEngine::TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( const TBlob< TypeTo > &  arg )

inline

Creates a copy of given TBlob instance.

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

arg	given pointer to blob

Returns

A shared pointer to the newly created blob of the given type

make_shared_blob() [10/17]

template<typename TypeTo >

InferenceEngine::TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l = NCHW  )

inline

Creates a blob with the given precision.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

p	Given precision

Returns

A shared pointer to the blob created

make_shared_blob() [11/17]

template<typename TypeTo >

TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l, SizeVector  dims, const std::vector< TypeTo > &  arg  )

inline

Creates a blob with the given precision, layout and dimensions from the vector of values.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

p	Given precision
l	Given Layout
dims	Given dimensions
arg	Vector of values

Returns

A shared pointer to the blob created

make_shared_blob() [12/17]

template<typename TypeTo >

TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l, const std::vector< TypeTo > &  arg  )

inline

Creates a blob with the given precision from the vector of values.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

p	Given precision
l	Layout
arg	Vector of values

Returns

A shared pointer to the blob created

make_shared_blob() [13/17]

template<typename TypeTo >

TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, const std::vector< TypeTo > &  arg  )

inline

Creates a blob with the NCHW layout and the given precision from the vector of values.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Template Parameters

TypeTo

Type of the shared pointer to be created

Parameters

p	Given precision
arg	Vector of values

Returns

A shared pointer to the blob created

make_shared_blob() [14/17]

template<typename TypeTo >

TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, Layout  l, const SizeVector &  dims, TypeTo *  ptr, size_t  size = 0  )

inline

Creates a blob with the given precision from the pointer to the pre-allocated memory.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Parameters

p	Given precision
l	Layout
dims	Given dimensions
ptr	Pointer to the pre-allocated memory
size	Length of the pre-allocated array

Returns

A shared pointer to the blob created

make_shared_blob() [15/17]

template<typename TypeTo >

TBlob<TypeTo>::Ptr InferenceEngine::make_shared_blob ( Precision  p, const SizeVector &  dims, TypeTo *  ptr, size_t  size = 0  )

inline

Creates a blob with the NCHW layout and the given precision from the pointer to the pre-allocated memory.

Deprecated:

Use InferenceEngine::make_shared_blob(const TensorDesc&)

Parameters

p	Given precision
dims	Given dimensions
ptr	Pointer to the pre-allocated memory
size	Length of the pre-allocated array

Returns

A shared pointer to the blob created

make_shared_blob() [16/17]

template<typename T , typename ... Args, typename std::enable_if< std::is_base_of< Blob, T >::value, int >::type = 0>

std::shared_ptr<T> InferenceEngine::make_shared_blob

(

Args &&...

args

)

Creates a Blob object of the specified type.

Parameters

args	Constructor arguments for the Blob object

Returns

A shared pointer to the newly created Blob object

make_shared_blob() [17/17]

Blob::Ptr InferenceEngine::make_shared_blob	(	const Blob::Ptr &	inputBlob,
		const ROI &	roi
	)

Creates a blob describing given ROI object based on the given blob with pre-allocated memory.

Parameters

inputBlob	original blob with pre-allocated memory.
roi	A ROI object inside of the original blob.

Returns

A shared pointer to the newly created blob.

make_so_pointer() [1/3]

template<class T >

std::shared_ptr<T> InferenceEngine::make_so_pointer ( const file_name_t &  name )

inlinedelete

Creates a special shared_pointer wrapper for the given type from a specific shared module.

Parameters

name	Name of the shared library file
name	Name of the shared library file

Returns

shared_pointer A wrapper for the given type from a specific shared module

make_so_pointer() [2/3]

template<>

std::shared_ptr<IShapeInferExtension> InferenceEngine::make_so_pointer ( const file_name_t &  name )

inlinedelete

Creates a special shared_pointer wrapper for the given type from a specific shared module.

Parameters

name	Name of the shared library file

Returns

shared_pointer A wrapper for the given type from a specific shared module

make_so_pointer() [3/3]

template<>

std::shared_ptr<IExtension> InferenceEngine::make_so_pointer ( const file_name_t &  name )

inlinedelete

Creates a special shared_pointer wrapper for the given type from a specific shared module.

Parameters

name	Name of the shared library file

Returns

shared_pointer A wrapper for the given type from a specific shared module

TopResults() [1/2]

template<class T >

void InferenceEngine::TopResults ( unsigned int  n, TBlob< T > &  input, std::vector< unsigned > &  output  )

inline

Gets the top n results from a tblob.

Parameters

n	Top n count
input	1D tblob that contains probabilities
output	Vector of indexes for the top n places

TopResults() [2/2]

void InferenceEngine::TopResults ( unsigned int  n, Blob &  input, std::vector< unsigned > &  output  )

inline

Gets the top n results from a blob.

Parameters

n	Top n count
input	1D blob that contains probabilities
output	Vector of indexes for the top n places

Variable Documentation

I_C

const size_t InferenceEngine::I_C = 2

static

Deprecated:

Deprecated since provides dims in reverse order

I_H

const size_t InferenceEngine::I_H = 1

static

Deprecated:

Deprecated since provides dims in reverse order

I_N

const size_t InferenceEngine::I_N = 3

static

Deprecated:

Deprecated since provides dims in reverse order

I_W

const size_t InferenceEngine::I_W = 0

static

Deprecated:

Deprecated since provides dims in reverse order