A header that defines advanced related properties for VPU plugins. These properties should be used in SetConfig() and LoadNetwork() methods of plugins.
More...
|
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_HW_STAGES_OPTIMIZATION) |
| | Turn on HW stages usage (applicable for MyriadX devices only). This option should be used with values: CONFIG_VALUE(YES) or CONFIG_VALUE(NO) (default)
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_LOG_LEVEL) |
| | The key to specify desirable log level for devices. This option should be used with values: CONFIG_VALUE(LOG_NONE) (default), CONFIG_VALUE(LOG_WARNING), CONFIG_VALUE(LOG_INFO), CONFIG_VALUE(LOG_DEBUG)
|
| |
| | InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_INPUT_NORM) |
| | The key to define normalization coefficient for the network input. This option should used with be a real number. Example "255.f". More...
|
| |
| | InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_INPUT_BIAS) |
| | The flag to specify Bias value that is added to each element of the network input. This option should used with be a real number. Example "0.1f". More...
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_PRINT_RECEIVE_TENSOR_TIME) |
| | The flag for adding to the profiling information the time of obtaining a tensor. This option should be used with values: CONFIG_VALUE(YES) or CONFIG_VALUE(NO) (default)
|
| |
| | InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_NETWORK_CONFIG) |
| | This option allows to pass extra configuration for executable network. By default, it is empty string, which means - no configuration. String format: <key>=,<key>=,... Supported parameters and options: More...
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_COMPUTE_LAYOUT) |
| | This option allows to to specify input output layouts for network layers. By default, this value set to VPU_CONFIG_VALUE(AUTO) value. Supported values: VPU_CONFIG_VALUE(AUTO) executable network configured to use optimal layer layout depending on available HW VPU_CONFIG_VALUE(NCHW) executable network forced to use NCHW input/output layouts VPU_CONFIG_VALUE(NHWC) executable network forced to use NHWC input/output layouts.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_AUTO) |
| | Supported keys definition for VPU_CONFIG_KEY(COMPUTE_LAYOUT) option.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_NCHW) |
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_NHWC) |
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_CUSTOM_LAYERS) |
| | This option allows to pass custom layers binding xml. If layer is present in such an xml, it would be used during inference even if the layer is natively supported.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_IGNORE_IR_STATISTIC) |
| | Ignore statistic in IR by plugin. Plugin could use statistic present in IR in order to try to improve calculations precision. If you don't want statistic to be used enable this option. This option should be used with values: CONFIG_VALUE(YES) or CONFIG_VALUE(NO) (default)
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_MYRIAD_PROTOCOL) |
| | This option allows to specify protocol.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_MYRIAD_PCIE) |
| | Supported keys definition for VPU_MYRIAD_CONFIG_KEY(PROTOCOL) option.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_MYRIAD_USB) |
| |
| | InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_FORCE_RESET) |
| |
| | InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_PLATFORM) |
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_2450) |
| | Supported keys definition for DECLARE_VPU_CONFIG_KEY(PLATFORM) option.
|
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_VALUE (VPU_2480) |
| |
|
| InferenceEngine::VPUConfigParams::DECLARE_CONFIG_KEY (VPU_HDDL_USE_SGAD) |
| | [Only for HDDLPlugin] Type: "YES/NO", default is "NO". SGAD is short for "Single Graph All Device". With this scheduler, once application allocates 1 network, all devices (managed by SGAD scheduler) will be loaded with this graph. The number of network that can be loaded to one device can exceed one. Once application deallocates 1 network from device, all devices will unload the network from them.
|
| |
A header that defines advanced related properties for VPU plugins. These properties should be used in SetConfig() and LoadNetwork() methods of plugins.