We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
According the GeoSeg repo,the clutter category was not taken into account:GeoSeg Repo
clutter
The GeoSeg contain lots of code of the paper about semantic segmentation in remote sensing
like following,mIoU 0.8604=(0.8791+0.9279+0.7775+0.7938+0.9239)/5
But in mmsegmentation,when calculating mIoU, the category of 'clutter' was taken into account for mIoU ISPRS potsdam
like following,mIoU 78.06=(87.31+93.7+76.31+79.66+92.17+39.2)/6
The class clutter tend to acquire low IoU, so is this an error or a different standard?
The text was updated successfully, but these errors were encountered:
No branches or pull requests
According the GeoSeg repo,the
clutter
category was not taken into account:GeoSeg RepoThe GeoSeg contain lots of code of the paper about semantic segmentation in remote sensing
like following,mIoU 0.8604=(0.8791+0.9279+0.7775+0.7938+0.9239)/5
But in mmsegmentation,when calculating mIoU, the category of 'clutter' was taken into account for mIoU ISPRS potsdam
like following,mIoU 78.06=(87.31+93.7+76.31+79.66+92.17+39.2)/6
The class
clutter
tend to acquire low IoU, so is this an error or a different standard?The text was updated successfully, but these errors were encountered: