PropertyKey Enumeration
A header for advanced hardware specific properties for OpenVINO runtime devices.
To use in set_property, compile_model, import_model, get_property methods.
Namespace: OpenVinoSharpAssembly: OpenVINO_CSharp_API (in OpenVINO_CSharp_API.dll) Version: 2024.3.0.2+a9617c0f8f80882646d0eba11b88ae6cb17b3fb8
SUPPORTED_PROPERTIES |
0 |
|
AVAILABLE_DEVICES |
1 |
|
OPTIMAL_NUMBER_OF_INFER_REQUESTS |
2 |
Read-only property(uint32_t string) to get an unsigned integer value of optimaln
number of compiled model infer requests.
|
RANGE_FOR_ASYNC_INFER_REQUESTS |
3 |
|
RANGE_FOR_STREAMS |
4 |
Read-only property(string(unsigned int, unsigned int)) to provide information about a range for
streams on platforms where streams are supported
|
FULL_DEVICE_NAME |
5 |
|
OPTIMIZATION_CAPABILITIES |
6 |
|
NETWORK_NAME |
7 |
|
OPTIMAL_BATCH_SIZE |
8 |
Read-only property(uint32_t string) to query information optimal batch size for the given device
and the network
|
MAX_BATCH_SIZE |
9 |
Read-only property to get maximum batch size which does not cause performance degradation due
to memory swap impact.
|
CACHE_DIR |
10 |
Read-write property(string) to set/get the directory which will be used to store any data cached
by plugins.
|
CACHE_MODE |
11 |
|
NUM_STREAMS |
12 |
Read-write property(uint32_t string) to set/get the number of executor logical partitions.
|
AFFINITY |
13 |
Read-write property to set/get the name for setting CPU affinity per thread option.
|
INFERENCE_NUM_THREADS |
14 |
Read-write property9int32_t string) to set/get the maximum number of threads that can be used
for inference tasks.
|
PERFORMANCE_HINT |
15 |
Read-write property, it is high-level OpenVINO Performance Hints
|
ENABLE_CPU_PINNING |
16 |
Read-write property, it is high-level OpenVINO hint for using CPU pinning to bind CPU threads to processors
during inference
|
SCHEDULING_CORE_TYPE |
17 |
Read-write property, it is high-level OpenVINO Hints for the type of CPU core used during inference
|
ENABLE_HYPER_THREADING |
18 |
Read-write property, it is high-level OpenVINO hint for using hyper threading processors during CPU inference
|
INFERENCE_PRECISION_HINT |
19 |
|
PERFORMANCE_HINT_NUM_REQUESTS |
20 |
(Optional) Read-write property(uint32_t string) that backs the Performance Hints by giving
additional information on how many inference requests the application will be
keeping in flight usually this value comes from the actual use-case (e.g.
number of video-cameras, or other sources of inputs)
|
MODEL_PRIORITY |
21 |
Read-write property, high-level OpenVINO model priority hint.
|
LOG_LEVEL |
22 |
|
PERF_COUNT |
23 |
Read-write property(string) for setting performance counters option.
|
MULTI_DEVICE_PRIORITIES |
24 |
Read-write property(std::pair(std::string, Any)), device Priorities config option,
with comma-separated devices listed in the desired priority
|
EXECUTION_MODE_HINT |
25 |
Read-write property(string) for high-level OpenVINO Execution hint
unlike low-level properties that are individual (per-device), the hints are something that every device accepts
and turns into device-specific settings
Execution mode hint controls preferred optimization targets (performance or accuracy) for given model
|
FORCE_TBB_TERMINATE |
26 |
Read-write property to set whether force terminate tbb when ov core destruction
|
ENABLE_MMAP |
27 |
Read-write property to configure `mmap()` use for model read
|
AUTO_BATCH_TIMEOUT |
28 |
Read-write property
|