Process

Function Usage

Receives the model inference output tensors and outputs the object detection result. During subsequent execution, execute Init first.

Prototype 1

virtual APP_ERROR Process(const std::vector<TensorBase>& tensors, 
                          std::vector<std::vector<ObjectInfo>>& objectInfos,
                          const std::vector<ResizedImageInfo>& resizedImageInfos = {},
                          const std::map<std::string, std::shared_ptr<void>> &configParamMap = {});

Parameter Description 1

Parameter

Input/Output

Description

tensors

Input

Input tensors for model postprocessing

objectInfos

Output

Output information such as the coordinates, type, and confidence level of the detected object

resizedImageInfos

Input

Image information (including the original and resized widths and heights)

configParamMap

Input

(Optional) Other parameters

Return Parameter Description 1

Data Structure

Description

APP_ERROR

Error code returned during program execution. For details, see the MxBase/ErrorCode/ErrorCode.h file.

Prototype 2

virtual SDK_DEPRECATED_FOR() APP_ERROR Process(const std::vector<TensorBase>& tensors, 
                          std::vector<std::vector<ObjectInfo>>& objectInfos, 
                          const std::vector<ImagePreProcessInfo>& imagePreProcessInfos);// No long used.

Parameter Description 2

Parameter

Input/Output

Description

tensors

Input

Input tensors for model postprocessing

objectInfos

Output

Output information such as the coordinates, type, and confidence level of the detected object

imagePreProcessInfos

Input

Image pre-processing information

Return Parameter Description 2

Data Structure

Description

APP_ERROR

Error code returned during program execution. For details, see the MxBase/ErrorCode/ErrorCode.h file.