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 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

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_type

Target 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

dir	Path 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

nthreads

Number 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:

• opencv2/gapi/infer/onnx.hpp