OpenCV
4.6.0
Open Source Computer Vision
|
#include <opencv2/gapi/infer/onnx.hpp>
Public Member Functions | |
Params (const std::string &model) | |
Class constructor. More... | |
GBackend | backend () const |
Params< Net > & | cfgInputLayers (const typename PortCfg< Net >::In &layer_names) |
Specifies sequence of network input layers names for inference. More... | |
Params< Net > & | cfgMeanStd (const typename PortCfg< Net >::NormCoefs &m, const typename PortCfg< Net >::NormCoefs &s) |
Specifies mean value and standard deviation for preprocessing. More... | |
Params< Net > & | cfgNormalize (const typename PortCfg< Net >::Normalize &normalizations) |
Specifies normalize parameter for preprocessing. More... | |
Params< Net > & | cfgOutputLayers (const typename PortCfg< Net >::Out &layer_names) |
Specifies sequence of output layers names for inference. More... | |
Params< Net > & | cfgPostProc (const std::vector< cv::GMatDesc > &out_metas, const PostProc &remap_function) |
Configures graph output and provides the post processing function from user. More... | |
Params< Net > & | cfgPostProc (std::vector< cv::GMatDesc > &&out_metas, PostProc &&remap_function) |
Params< Net > & | cfgPostProc (const std::vector< cv::GMatDesc > &out_metas, const PostProc &remap_function, const std::vector< std::string > &names_to_remap) |
Params< Net > & | cfgPostProc (std::vector< cv::GMatDesc > &&out_metas, PostProc &&remap_function, std::vector< std::string > &&names_to_remap) |
Params< Net > & | constInput (const std::string &layer_name, const cv::Mat &data, TraitAs hint=TraitAs::TENSOR) |
Sets a constant input. More... | |
cv::util::any | params () const |
std::string | tag () const |
Protected Attributes | |
detail::ParamDesc | desc |
Contains description of inference parameters and kit of functions that fill this parameters.
|
inline |
Class constructor.
Constructs Params based on model information and sets default values for other inference description parameters.
model | Path to model (.onnx file). |
|
inline |
|
inline |
Specifies sequence of network input layers names for inference.
The function is used to associate data of graph inputs with input layers of network topology. Number of names has to match the number of network inputs. If a network has only one input layer, there is no need to call it as the layer is associated with input automatically but this doesn't prevent you from doing it yourself. Count of names has to match to number of network inputs.
layer_names | std::array<std::string, N> where N is the number of inputs as defined in the G_API_NET. Contains names of input layers. |
|
inline |
Specifies mean value and standard deviation for preprocessing.
The function is used to set mean value and standard deviation for preprocessing of input data.
m | std::array<cv::Scalar, N> where N is the number of inputs as defined in the G_API_NET. Contains mean values. |
s | std::array<cv::Scalar, N> where N is the number of inputs as defined in the G_API_NET. Contains standard deviation values. |
|
inline |
Specifies normalize parameter for preprocessing.
The function is used to set normalize parameter for preprocessing of input data.
normalizations | std::array<cv::Scalar, N> where N is the number of inputs as defined in the G_API_NET. Сontains bool values that enabled or disabled normalize of input data. |
|
inline |
Specifies sequence of output layers names for inference.
The function is used to associate data of graph outputs with output layers of network topology. If a network has only one output layer, there is no need to call it as the layer is associated with output automatically but this doesn't prevent you from doing it yourself. Count of names has to match to number of network outputs or you can set your own output but for this case you have to additionally use cfgPostProc function.
layer_names | std::array<std::string, N> where N is the number of outputs as defined in the G_API_NET. Contains names of output layers. |
|
inline |
Configures graph output and provides the post processing function from user.
The function is used when you work with networks with dynamic outputs. Since we can't know dimensions of inference result needs provide them for construction of graph output. This dimensions can differ from inference result. So you have to provide PostProc function that gets information from inference result and fill output which is constructed by dimensions from out_metas.
out_metas | Out meta information about your output (type, dimension). |
remap_function | Post processing function, which has two parameters. First is onnx result, second is graph output. Both parameters is std::map that contain pair of layer's name and cv::Mat. |
|
inline |
This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Function with a rvalue parameters.
out_metas | rvalue out meta information about your output (type, dimension). |
remap_function | rvalue post processing function, which has two parameters. First is onnx result, second is graph output. Both parameters is std::map that contain pair of layer's name and cv::Mat. |
|
inline |
This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. The function has additional parameter names_to_remap. This parameter provides information about output layers which will be used for inference and post processing function.
out_metas | Out meta information. |
remap_function | Post processing function. |
names_to_remap | Names of output layers. network's inference will be done on these layers. Inference's result will be processed in post processing function using these names. |
|
inline |
This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Function with a rvalue parameters and additional parameter names_to_remap.
out_metas | rvalue out meta information. |
remap_function | rvalue post processing function. |
names_to_remap | rvalue names of output layers. network's inference will be done on these layers. Inference's result will be processed in post processing function using these names. |
|
inline |
Sets a constant input.
The function is used to set constant input. This input has to be a prepared tensor since preprocessing is disabled for this case. You should provide name of network layer which will receive provided data.
layer_name | Name of network layer. |
data | cv::Mat that contains data which will be associated with network layer. |
hint | Type of input (TENSOR). |
|
inline |
|
inline |
|
protected |