Class InferenceEngine::ICore¶
-
class ICore : public ov::ICore¶
Public Functions
-
virtual CNNNetwork ReadNetwork(const std::string &model, const Blob::CPtr &weights, bool frontendMode = false) const = 0¶
Reads IR xml and bin (with the same name) files.
- Parameters
model – string with IR
weights – shared pointer to constant blob with weights
frontendMode – read network without post-processing or other transformations
- Returns
CNNNetwork
-
virtual CNNNetwork ReadNetwork(const std::string &modelPath, const std::string &binPath) const = 0¶
Reads IR xml and bin files.
- Parameters
modelPath – path to IR file
binPath – path to bin file, if path is empty, will try to read bin file with the same name as xml and if bin file with the same name was not found, will load IR without weights.
- Returns
CNNNetwork
-
virtual SoExecutableNetworkInternal LoadNetwork(const CNNNetwork &network, const std::string &deviceName, const std::map<std::string, std::string> &config = {}) = 0¶
Creates an executable network from a network object.
Users can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources)
- Parameters
network – CNNNetwork object acquired from Core::ReadNetwork
deviceName – Name of device to load network to
config – Optional map of pairs: (config parameter name, config parameter value) relevant only for this load operation
- Returns
An executable network reference
-
virtual SoExecutableNetworkInternal LoadNetwork(const CNNNetwork &network, const RemoteContext::Ptr &remoteCtx, const std::map<std::string, std::string> &config = {}) = 0¶
Creates an executable network from a network object.
Users can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources)
- Parameters
network – CNNNetwork object acquired from Core::ReadNetwork
remoteCtx – “Remote” (non-CPU) accelerator device-specific execution context to use
config – Optional map of pairs: (config parameter name, config parameter value) relevant only for this load operation
- Returns
An executable network reference
-
virtual SoExecutableNetworkInternal LoadNetwork(const std::string &modelStr, const InferenceEngine::Blob::CPtr &weights, const std::string &deviceName, const std::map<std::string, std::string> &config, const std::function<void(const InferenceEngine::CNNNetwork&)> &val = nullptr) = 0¶
Creates an executable network from a model memory.
Users can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources)
- Parameters
modelStr – String data of model
weights – Model’s weights
deviceName – Name of device to load network to
config – Optional map of pairs: (config parameter name, config parameter value) relevant only for this load operation
val – Optional callback to perform validation of loaded CNNNetwork, if ReadNetwork is triggered
- Returns
An executable network reference
-
virtual SoExecutableNetworkInternal LoadNetwork(const std::string &modelPath, const std::string &deviceName, const std::map<std::string, std::string> &config, const std::function<void(const CNNNetwork&)> &val = nullptr) = 0¶
Creates an executable network from a model file.
Users can create as many networks as they need and use them simultaneously (up to the limitation of the hardware resources)
- Parameters
modelPath – Path to model
deviceName – Name of device to load network to
config – Optional map of pairs: (config parameter name, config parameter value) relevant only for this load operation
val – Optional callback to perform validation of loaded CNNNetwork, if ReadNetwork is triggered
- Returns
An executable network reference
-
virtual SoExecutableNetworkInternal ImportNetwork(std::istream &networkModel, const std::string &deviceName = {}, const std::map<std::string, std::string> &config = {}) = 0¶
Creates an executable network from a previously exported network.
- Parameters
networkModel – network model stream
deviceName – Name of device load executable network on
config – Optional map of pairs: (config parameter name, config parameter value) relevant only for this load operation*
- Returns
An executable network reference
-
virtual QueryNetworkResult QueryNetwork(const CNNNetwork &network, const std::string &deviceName, const std::map<std::string, std::string> &config) const = 0¶
Query device if it supports specified network with specified configuration.
- Parameters
deviceName – A name of a device to query
network – Network object to query
config – Optional map of pairs: (config parameter name, config parameter value)
- Returns
An object containing a map of pairs a layer name -> a device name supporting this layer.
-
virtual ov::Any GetMetric(const std::string &deviceName, const std::string &name, const ov::AnyMap &options = {}) const = 0¶
Gets general runtime metric for dedicated hardware.
The method is needed to request common device properties which are executable network agnostic. It can be device name, temperature, other devices-specific values.
- Parameters
deviceName – - A name of a device to get a metric value.
name – - metric name to request.
- Returns
Metric value corresponding to metric key.
-
virtual ov::Any GetConfig(const std::string &deviceName, const std::string &name) const = 0¶
Gets configuration dedicated to device behaviour.
The method is targeted to extract information which can be set via SetConfig method.
- Parameters
deviceName – - A name of a device to get a configuration value.
name – - config key.
- Returns
Value of config corresponding to config key.
-
virtual std::vector<std::string> GetAvailableDevices() const = 0¶
Returns devices available for neural networks inference.
- Returns
A vector of devices. The devices are returned as { CPU, GPU.0, GPU.1, GNA } If there more than one device of specific type, they are enumerated with .# suffix.
-
virtual bool DeviceSupportsModelCaching(const std::string &deviceName) const = 0¶
Checks whether device supports model caching feature.
- Parameters
deviceName – - A name of a device to get a metric value.
- Returns
True if device has IMPORT_EXPORT_SUPPORT and CACHING_PROPERTIES metric in SUPPORTED_METRICS and this metric returns ‘true’, False otherwise.
-
virtual InferenceEngine::RemoteContext::Ptr CreateContext(const std::string &deviceName, const ov::AnyMap&) = 0¶
Create a new shared context object on specified accelerator device using specified plugin-specific low level device API parameters (device handle, pointer, etc.)
- Parameters
deviceName – Name of a device to create new shared context on.
params – Map of device-specific shared context parameters.
- Returns
A shared pointer to a created remote context.
-
virtual std::map<std::string, std::string> GetSupportedConfig(const std::string &deviceName, const std::map<std::string, std::string> &config) = 0¶
Get only configs that are supported by device.
- Parameters
deviceName – Name of a device
config – Map of configs that can contains configs that are not supported by device
- Returns
map of configs that are supported by device
-
virtual RemoteContext::Ptr GetDefaultContext(const std::string &deviceName) = 0¶
Get a pointer to default shared context object for the specified device.
- Parameters
deviceName – - A name of a device to get create shared context from.
- Returns
A shared pointer to a default remote context.
-
virtual CNNNetwork ReadNetwork(const std::string &model, const Blob::CPtr &weights, bool frontendMode = false) const = 0¶