Loading...
Searching...
No Matches
cv::gapi::onnx::ep::OpenVINO Struct Reference

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::string &dev_type)
 Class constructor.
 
GAPI_WRAP OpenVINOcfgCacheDir (const std::string &dir)
 Specifies OpenVINO Execution Provider cache dir.
 
GAPI_WRAP OpenVINOcfgEnableDynamicShapes ()
 Enables OpenVINO Execution Provider dynamic shapes.
 
GAPI_WRAP OpenVINOcfgEnableOpenCLThrottling ()
 Enables OpenVINO Execution Provider opencl throttling.
 
GAPI_WRAP OpenVINOcfgNumThreads (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
 

Detailed Description

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.

Constructor & Destructor Documentation

◆ OpenVINO()

GAPI_WRAP cv::gapi::onnx::ep::OpenVINO::OpenVINO ( const std::string &  dev_type)
inlineexplicit

Class constructor.

Constructs OpenVINO parameters based on device type information.

Parameters
dev_typeTarget device type to use. ("CPU_FP32", "GPU_FP16", etc)

Member Function Documentation

◆ cfgCacheDir()

GAPI_WRAP OpenVINO & cv::gapi::onnx::ep::OpenVINO::cfgCacheDir ( const std::string &  dir)
inline

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.

Parameters
dirPath to the directory what will be used as cache.
Returns
reference to this parameter structure.

◆ cfgEnableDynamicShapes()

GAPI_WRAP OpenVINO & cv::gapi::onnx::ep::OpenVINO::cfgEnableDynamicShapes ( )
inline

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.

Returns
reference to this parameter structure.

◆ cfgEnableOpenCLThrottling()

GAPI_WRAP OpenVINO & cv::gapi::onnx::ep::OpenVINO::cfgEnableOpenCLThrottling ( )
inline

Enables OpenVINO Execution Provider opencl throttling.

This function is used to enable OpenCL queue throttling for GPU devices (reduces CPU utilization when using GPU).

Returns
reference to this parameter structure.

◆ cfgNumThreads()

GAPI_WRAP OpenVINO & cv::gapi::onnx::ep::OpenVINO::cfgNumThreads ( size_t  nthreads)
inline

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.

Parameters
nthreadsNumber of threads.
Returns
reference to this parameter structure.

Member Data Documentation

◆ cache_dir

std::string cv::gapi::onnx::ep::OpenVINO::cache_dir

◆ device_type

std::string cv::gapi::onnx::ep::OpenVINO::device_type

◆ enable_dynamic_shapes

bool cv::gapi::onnx::ep::OpenVINO::enable_dynamic_shapes = false

◆ enable_opencl_throttling

bool cv::gapi::onnx::ep::OpenVINO::enable_opencl_throttling = false

◆ num_of_threads

size_t cv::gapi::onnx::ep::OpenVINO::num_of_threads = 0

The documentation for this struct was generated from the following file: