This structure contains description of inference parameters which is specific to ONNX models. More...

#include <opencv2/gapi/infer/onnx.hpp>

Collaboration diagram for cv::gapi::onnx::detail::ParamDesc:

Public Types
using	ConstInput = std::pair< cv::Mat, TraitAs >

Public Attributes
std::unordered_map< std::string, ConstInput >	const_inputs
	Map with pair of name of network layer and ConstInput which will be associated with this.

PostProc	custom_post_proc
	Post processing function.

bool	disable_mem_pattern

std::vector< cv::gapi::onnx::ep::EP >	execution_providers

std::unordered_map< std::string, std::pair< cv::Scalar, cv::Scalar > >	generic_mstd

std::unordered_map< std::string, bool >	generic_norm

std::vector< std::string >	input_names
	Names of input network layers.

bool	is_generic

std::vector< cv::Scalar >	mean
	Mean values for preprocessing.

std::string	model_path
	Path to model.

std::vector< std::string >	names_to_remap
	Names of output layers that will be processed in PostProc function.

std::vector< bool >	normalize
	Vector of bool values that enabled or disabled normalize of input data.

std::size_t	num_in
	How many inputs are defined in the operation.

std::size_t	num_out
	How many outputs are defined in the operation.

std::vector< cv::GMatDesc >	out_metas
	Out meta information about your output (type, dimension).

std::vector< std::string >	output_names
	Names of output network layers.

std::vector< cv::Scalar >	stdev
	Standard deviation values for preprocessing.

Detailed Description

This structure contains description of inference parameters which is specific to ONNX models.

Member Typedef Documentation

◆ ConstInput

using cv::gapi::onnx::detail::ParamDesc::ConstInput = std::pair<cv::Mat, TraitAs>

Member Data Documentation

◆ const_inputs

std::unordered_map<std::string, ConstInput> cv::gapi::onnx::detail::ParamDesc::const_inputs

Map with pair of name of network layer and ConstInput which will be associated with this.

◆ custom_post_proc

PostProc cv::gapi::onnx::detail::ParamDesc::custom_post_proc

Post processing function.

◆ disable_mem_pattern

bool cv::gapi::onnx::detail::ParamDesc::disable_mem_pattern

◆ execution_providers

std::vector<cv::gapi::onnx::ep::EP> cv::gapi::onnx::detail::ParamDesc::execution_providers

◆ generic_mstd

std::unordered_map<std::string, std::pair<cv::Scalar, cv::Scalar> > cv::gapi::onnx::detail::ParamDesc::generic_mstd

◆ generic_norm

std::unordered_map<std::string, bool> cv::gapi::onnx::detail::ParamDesc::generic_norm

◆ input_names

std::vector<std::string> cv::gapi::onnx::detail::ParamDesc::input_names

Names of input network layers.

◆ is_generic

bool cv::gapi::onnx::detail::ParamDesc::is_generic

◆ mean

std::vector<cv::Scalar> cv::gapi::onnx::detail::ParamDesc::mean

Mean values for preprocessing.

◆ model_path

std::string cv::gapi::onnx::detail::ParamDesc::model_path

Path to model.

◆ names_to_remap

std::vector<std::string> cv::gapi::onnx::detail::ParamDesc::names_to_remap

Names of output layers that will be processed in PostProc function.

◆ normalize

std::vector<bool> cv::gapi::onnx::detail::ParamDesc::normalize

Vector of bool values that enabled or disabled normalize of input data.

◆ num_in

std::size_t cv::gapi::onnx::detail::ParamDesc::num_in

How many inputs are defined in the operation.

◆ num_out

std::size_t cv::gapi::onnx::detail::ParamDesc::num_out

How many outputs are defined in the operation.

◆ out_metas

std::vector<cv::GMatDesc> cv::gapi::onnx::detail::ParamDesc::out_metas

Out meta information about your output (type, dimension).

◆ output_names

std::vector<std::string> cv::gapi::onnx::detail::ParamDesc::output_names

Names of output network layers.

◆ stdev

std::vector<cv::Scalar> cv::gapi::onnx::detail::ParamDesc::stdev

Standard deviation values for preprocessing.

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

opencv2/gapi/infer/onnx.hpp

Public Types

Public Attributes