A protected member function that outputs semantic segmentation information after dimension reduction based on image information. (It is invoked for internal use only. Do not use it.)
1 | void SemanticSegPostProcessBase::CoordinatesReduction(const ResizedImageInfo& resizedImageInfo, SemanticSegInfo& semanticSegInfos); |
Parameter |
Input/Output |
Description |
|---|---|---|
resizedImageInfo |
Input |
Image information. The widths and heights of the original and resized images cannot be greater than 8192. The resizing ratio range is [1/32, 16]. |
semanticSegInfos |
Output |
Information such as the semantic segmentation pixel value and class mapping table. |