Documentation

Process

Function Usage

Receives the model inference output tensors and outputs the object detection result. During subsequent execution, the Init() method needs to be executed first.

Prototype

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

Parameter Description

Parameter

Input/Output

Description

tensors

Input

Input tensors for model post-processing

textObjectInfos

Output

Outputs information such as the coordinates and confidence level of the text bounding box

resizedImageInfos

Input

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

configParamMap

Input

(Optional) Other parameters

Return Parameter Description

Data Structure

Description

APP_ERROR

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