Inference Engine Plugin API namespace. More...
Namespaces | |
| details | |
| A namespace with non-public Inference Engine Plugin API. | |
| PluginConfigInternalParams | |
| A namespace with internal plugin configuration keys. | |
| PrecisionUtils | |
| Namespace for precision utilities. | |
Data Structures | |
| class | InferRequest |
| class | BatchedBlob |
| class | Blob |
| class | BlockingDesc |
| class | CNNNetwork |
| class | CompoundBlob |
| class | Core |
| class | Data |
| struct | DataConfig |
| struct | Exception |
| class | ExecutableNetwork |
| class | Extension |
| class | I420Blob |
| interface | IAllocator |
| interface | ICNNNetwork |
| class | IExecutableNetwork |
| class | IExtension |
| class | IInferRequest |
| interface | ILayerExecImpl |
| interface | ILayerImpl |
| struct | InferenceEngineProfileInfo |
| class | InputInfo |
| interface | IVariableState |
| struct | LayerConfig |
| class | LockedMemory |
| class | LockedMemory< const T > |
| class | LockedMemory< void > |
| class | MemoryBlob |
| class | NV12Blob |
| class | Parameter |
| class | Precision |
| struct | PrecisionTrait |
| struct | PreProcessChannel |
| class | PreProcessInfo |
| struct | QueryNetworkResult |
| class | RemoteBlob |
| class | RemoteContext |
| struct | ResponseDesc |
| struct | ROI |
| class | TBlob |
| class | TensorDesc |
| union | UserValue |
| class | VariableState |
| struct | Version |
| class | ExecutableNetworkThreadSafeDefault |
| This class provides optimal thread safe default implementation. The class is recommended to be used as a base class for Executable Network impleentation during plugin development. More... | |
| class | AsyncInferRequestThreadSafeDefault |
| Base class with default implementation of asynchronous multi staged inference request. To customize pipeline stages derived class should change the content of AsyncInferRequestThreadSafeDefault::_pipeline member container. It consists of pairs of tasks and executors which will run the task. The class is recommended to be used by plugins as a base class for asynchronous inference request implementation. More... | |
| interface | IExecutableNetworkInternal |
| An internal API of executable network to be implemented by plugin,. More... | |
| interface | IInferRequestInternal |
| An internal API of synchronous inference request to be implemented by plugin, which is used in InferRequestBase forwarding mechanism. More... | |
| interface | IInferencePlugin |
| An API of plugin to be implemented by a plugin. More... | |
| interface | IVariableStateInternal |
| Minimal interface for variable state implementation. More... | |
| struct | DescriptionBuffer |
| A description buffer wrapping StatusCode and ResponseDesc. More... | |
| interface | ICore |
| Minimal ICore interface to allow plugin to get information from Core Inference Engine class. More... | |
| class | CPUStreamsExecutor |
| CPU Streams executor implementation. The executor splits the CPU into groups of threads, that can be pinned to cores or NUMA nodes. It uses custom threads to pull tasks from single queue. More... | |
| class | ExecutorManager |
| This is global point for getting task executor objects by string id. It's necessary in multiple asynchronous requests for having unique executors to avoid oversubscription. E.g. There 2 task executors for CPU device: one - in FPGA, another - in MKLDNN. Parallel execution both of them leads to not optimal CPU usage. More efficient to run the corresponding tasks one by one via single executor. More... | |
| class | ImmediateExecutor |
| Task executor implementation that just run tasks in current thread during calling of run() method. More... | |
| interface | IStreamsExecutor |
Interface for Streams Task Executor. This executor groups worker threads into so-called streams. More... | |
| interface | ITaskExecutor |
Interface for Task Executor. Inference Engine uses InferenceEngine::ITaskExecutor interface to run all asynchronous internal tasks. Different implementations of task executors can be used for different purposes: More... | |
Typedefs | |
| typedef VariableState | MemoryState |
| typedef void * | gpu_handle_param |
| typedef std::map< std::string, Blob::Ptr > | BlobMap |
| typedef std::vector< size_t > | SizeVector |
| typedef std::shared_ptr< Data > | DataPtr |
| typedef std::shared_ptr< const Data > | CDataPtr |
| typedef std::weak_ptr< Data > | DataWeakPtr |
| typedef std::map< std::string, CDataPtr > | ConstOutputsDataMap |
| typedef std::map< std::string, DataPtr > | OutputsDataMap |
| typedef std::shared_ptr< IExtension > | IExtensionPtr |
| typedef IVariableState | IMemoryState |
| typedef std::map< std::string, InputInfo::Ptr > | InputsDataMap |
| typedef std::map< std::string, InputInfo::CPtr > | ConstInputsDataMap |
| typedef std::map< std::string, Parameter > | ParamMap |
| using | SoExecutableNetworkInternal = details::SOPointer< IExecutableNetworkInternal > |
| SOPointer to IExecutableNetworkInternal. | |
| using | SoIInferRequestInternal = details::SOPointer< IInferRequestInternal > |
| SOPointer to IInferRequestInternal. | |
| using | IMemoryStateInternal = IVariableStateInternal |
| For compatibility reasons. | |
| using | SoIVariableStateInternal = details::SOPointer< IVariableStateInternal > |
| SOPointer to IVariableStateInternal. | |
| using | MemoryStateInternal = IVariableStateInternal |
| For compatibility reasons. | |
| using | ie_fp16 = short |
| A type difinition for FP16 data type. Defined as a singed short. | |
| using | Task = std::function< void()> |
| Inference Engine Task Executor can use any copyable callable without parameters and output as a task. It would be wrapped into std::function object. | |
| template<typename T > | |
| using | ThreadLocal = tbb::enumerable_thread_specific< T > |
| A wrapper class to keep object to be thread local. More... | |
Enumerations | |
| enum | LockOp |
| enum | Layout |
| enum | ColorFormat |
| enum | StatusCode |
| enum | MeanVariant |
| enum | ResizeAlgorithm |
Functions | |
| std::shared_ptr< InferenceEngine::IAllocator > | CreateDefaultAllocator () noexcept |
| std::shared_ptr< T > | as (const Blob::Ptr &blob) noexcept |
| std::shared_ptr< const T > | as (const Blob::CPtr &blob) noexcept |
| InferenceEngine::TBlob< Type >::Ptr | make_shared_blob (const TensorDesc &tensorDesc) |
| InferenceEngine::TBlob< Type >::Ptr | make_shared_blob (const TensorDesc &tensorDesc, Type *ptr, size_t size=0) |
| InferenceEngine::TBlob< Type >::Ptr | make_shared_blob (const TensorDesc &tensorDesc, const std::shared_ptr< InferenceEngine::IAllocator > &alloc) |
| InferenceEngine::TBlob< TypeTo >::Ptr | make_shared_blob (const TBlob< TypeTo > &arg) |
| std::shared_ptr< T > | make_shared_blob (Args &&... args) |
| Blob::Ptr | make_shared_blob (const Blob::Ptr &inputBlob, const ROI &roi) |
| std::ostream & | operator<< (std::ostream &out, const Layout &p) |
| std::ostream & | operator<< (std::ostream &out, const ColorFormat &fmt) |
| std::shared_ptr< T > | make_so_pointer (const std::string &name) |
| void | CreateExtensionShared (IExtensionPtr &ext) |
| StatusCode | CreateExtension (IExtension *&ext, ResponseDesc *resp) noexcept |
| TensorDesc | make_roi_desc (const TensorDesc &origDesc, const ROI &roi, bool useOrigMemDesc) |
| RemoteBlob::Ptr | make_shared_blob (const TensorDesc &desc, RemoteContext::Ptr ctx) |
| void | LowLatency (InferenceEngine::CNNNetwork &network) |
| void | lowLatency2 (InferenceEngine::CNNNetwork &network, bool use_const_initializer=true) |
| std::string | fileNameToString (const file_name_t &str) |
| file_name_t | stringToFileName (const std::string &str) |
| const Version * | GetInferenceEngineVersion () noexcept |
| void | blob_copy (Blob::Ptr src, Blob::Ptr dst) |
| Copies data with taking into account layout and precision params. More... | |
| PreProcessInfo | copyPreProcess (const PreProcessInfo &from) |
| Copies preprocess info. More... | |
| template<typename T > | |
| std::map< std::string, std::shared_ptr< const T > > | constMapCast (const std::map< std::string, std::shared_ptr< T >> &map) |
Copies the values of std::string indexed map and apply const cast. More... | |
| template<typename T > | |
| std::map< std::string, std::shared_ptr< T > > | constMapCast (const std::map< std::string, std::shared_ptr< const T >> &map) |
Copies the values of std::string indexed map and apply const cast. More... | |
| InputsDataMap | copyInfo (const InputsDataMap &networkInputs) |
| Copies InputInfo. More... | |
| OutputsDataMap | copyInfo (const OutputsDataMap &networkOutputs) |
| Copies OutputsData. More... | |
| std::string | getIELibraryPath () |
| Returns a path to Inference Engine library. More... | |
| inline ::FileUtils::FilePath | getInferenceEngineLibraryPath () |
| bool | checkOpenMpEnvVars (bool includeOMPNumThreads=true) |
| Checks whether OpenMP environment variables are defined. More... | |
| std::vector< int > | getAvailableNUMANodes () |
| Returns available CPU NUMA nodes (on Linux, and Windows [only with TBB], single node is assumed on all other OSes) More... | |
| std::vector< int > | getAvailableCoresTypes () |
| Returns available CPU cores types (on Linux, and Windows) and ONLY with TBB, single core type is assumed otherwise. More... | |
| int | getNumberOfCPUCores (bool bigCoresOnly=false) |
| Returns number of CPU physical cores on Linux/Windows (which is considered to be more performance friendly for servers) (on other OSes it simply relies on the original parallel API of choice, which usually uses the logical cores). call function with 'false' to get #phys cores of all types call function with 'true' to get #phys 'Big' cores number of 'Little' = 'all' - 'Big'. More... | |
| bool | with_cpu_x86_sse42 () |
| Checks whether CPU supports SSE 4.2 capability. More... | |
| bool | with_cpu_x86_avx () |
| Checks whether CPU supports AVX capability. More... | |
| bool | with_cpu_x86_avx2 () |
| Checks whether CPU supports AVX2 capability. More... | |
| bool | with_cpu_x86_avx512f () |
| Checks whether CPU supports AVX 512 capability. More... | |
| bool | with_cpu_x86_avx512_core () |
| Checks whether CPU supports AVX 512 capability. More... | |
| bool | with_cpu_x86_bfloat16 () |
| Checks whether CPU supports BFloat16 capability. More... | |
Variables | |
| LOCK_FOR_READ | |
| LOCK_FOR_WRITE | |
| ANY | |
| NCHW | |
| NHWC | |
| NCDHW | |
| NDHWC | |
| OIHW | |
| GOIHW | |
| OIDHW | |
| GOIDHW | |
| SCALAR | |
| C | |
| CHW | |
| HWC | |
| HW | |
| NC | |
| CN | |
| BLOCKED | |
| RAW | |
| RGB | |
| BGR | |
| RGBX | |
| BGRX | |
| NV12 | |
| I420 | |
| MEAN_IMAGE | |
| MEAN_VALUE | |
| NONE | |
| static constexpr auto | KEY_AUTO_DEVICE_LIST |
| static constexpr auto | HDDL_GRAPH_TAG |
| static constexpr auto | HDDL_STREAM_ID |
| static constexpr auto | HDDL_DEVICE_TAG |
| static constexpr auto | HDDL_BIND_DEVICE |
| static constexpr auto | HDDL_RUNTIME_PRIORITY |
| static constexpr auto | HDDL_USE_SGAD |
| static constexpr auto | HDDL_GROUP_DEVICE |
| static constexpr auto | MYRIAD_ENABLE_FORCE_RESET |
| static constexpr auto | MYRIAD_DDR_TYPE |
| static constexpr auto | MYRIAD_DDR_AUTO |
| static constexpr auto | MYRIAD_PROTOCOL |
| static constexpr auto | MYRIAD_PCIE |
| static constexpr auto | MYRIAD_THROUGHPUT_STREAMS |
| static constexpr auto | MYRIAD_ENABLE_HW_ACCELERATION |
| static constexpr auto | MYRIAD_ENABLE_RECEIVING_TENSOR_TIME |
| static constexpr auto | MYRIAD_CUSTOM_LAYERS |
Inference Engine Plugin API namespace.
| std::map<std::string, std::shared_ptr<T> > InferenceEngine::constMapCast | ( | const std::map< std::string, std::shared_ptr< const T >> & | map | ) |
Copies the values of std::string indexed map and apply const cast.
| [in] | map | map to copy |
| std::map<std::string, std::shared_ptr<const T> > InferenceEngine::constMapCast | ( | const std::map< std::string, std::shared_ptr< T >> & | map | ) |
Copies the values of std::string indexed map and apply const cast.
| [in] | map | map to copy |
| InputsDataMap InferenceEngine::copyInfo | ( | const InputsDataMap & | networkInputs | ) |
Copies InputInfo.
| [in] | networkInputs | The network inputs to copy from |
| OutputsDataMap InferenceEngine::copyInfo | ( | const OutputsDataMap & | networkOutputs | ) |
Copies OutputsData.
| [in] | networkInputs | network outputs to copy from |
| PreProcessInfo InferenceEngine::copyPreProcess | ( | const PreProcessInfo & | from | ) |
Copies preprocess info.
| [in] | from | PreProcessInfo to copy from |
