OpenCV 4.10.0-dev
Open Source Computer Vision
|
This structure provides functions that fill inference options for ONNX OpenVINO Execution Provider. Please follow https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#summary-of-options. More...
#include <opencv2/gapi/infer/onnx.hpp>
Public Member Functions | |
GAPI_WRAP | OpenVINO (const std::map< std::string, std::string > ¶ms) |
Class constructor. | |
GAPI_WRAP | OpenVINO (const std::string &dev_type) |
Class constructor. | |
GAPI_WRAP OpenVINO & | cfgCacheDir (const std::string &dir) |
Specifies OpenVINO Execution Provider cache dir. | |
GAPI_WRAP OpenVINO & | cfgEnableDynamicShapes () |
Enables OpenVINO Execution Provider dynamic shapes. | |
GAPI_WRAP OpenVINO & | cfgEnableOpenCLThrottling () |
Enables OpenVINO Execution Provider opencl throttling. | |
GAPI_WRAP OpenVINO & | cfgNumThreads (size_t nthreads) |
Specifies OpenVINO Execution Provider number of threads. | |
Public Attributes | |
std::string | cache_dir |
std::string | device_type |
bool | enable_dynamic_shapes = false |
bool | enable_opencl_throttling = false |
size_t | num_of_threads = 0 |
std::map< std::string, std::string > | params_map |
This structure provides functions that fill inference options for ONNX OpenVINO Execution Provider. Please follow https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#summary-of-options.
|
inlineexplicit |
Class constructor.
Constructs OpenVINO parameters based on device type information.
dev_type | Target device type to use. ("CPU", "GPU", "GPU.0" etc) |
|
inlineexplicit |
Class constructor.
Constructs OpenVINO parameters based on map of options passed.
params | A map of parameter names and their corresponding string values. |
Specifies OpenVINO Execution Provider cache dir.
This function is used to explicitly specify the path to save and load the blobs enabling model caching feature.
dir | Path to the directory what will be used as cache. |
Enables OpenVINO Execution Provider dynamic shapes.
This function is used to enable OpenCL queue throttling for GPU devices (reduces CPU utilization when using GPU). This function is used to enable work with dynamic shaped models whose shape will be set dynamically based on the infer input image/data shape at run time in CPU.
Enables OpenVINO Execution Provider opencl throttling.
This function is used to enable OpenCL queue throttling for GPU devices (reduces CPU utilization when using GPU).
Specifies OpenVINO Execution Provider number of threads.
This function is used to override the accelerator default value of number of threads with this value at runtime.
nthreads | Number of threads. |
std::string cv::gapi::onnx::ep::OpenVINO::cache_dir |
std::string cv::gapi::onnx::ep::OpenVINO::device_type |
bool cv::gapi::onnx::ep::OpenVINO::enable_dynamic_shapes = false |
bool cv::gapi::onnx::ep::OpenVINO::enable_opencl_throttling = false |
size_t cv::gapi::onnx::ep::OpenVINO::num_of_threads = 0 |
std::map<std::string, std::string> cv::gapi::onnx::ep::OpenVINO::params_map |