Process

Function Usage

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

Prototype

1
virtual APP_ERROR SemanticSegPostProcessBase::Process(const std::vector<TensorBase>& tensors, std::vector<SemanticSegInfo>& semanticSegInfos, const std::vector<ResizedImageInfo>& resizedImageInfos = {}, const std::map<std::string, std::shared_ptr<void>> &configParamMap = {});

Parameters

Parameter

Input/Output

Description

tensors

Input

Input tensors for model postprocessing.

semanticSegInfos

Output

Output information such as the semantic segmentation pixel value and class mapping table

resizedImageInfos

Input

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

configParamMap

Input

(Optional) Other parameters.

Response Parameters

Data Structure

Description

APP_ERROR

For details about the returned error codes, see APP_ERROR Description.