Open mizoru opened 8 months ago
@isaaccorley you added the original Potsdam data loader, can you take a look into this?
I took a look at this and I think the dataset may have been updated or something because I have a prior version of Potsdam that doesn't seem to have this issue.
I'll make a PR once I figure out the best way to handle this in the dataset class.
We haven't yet found a license for it so we can't just rehost on HF 😢
The download times for their server are awful for me. It hosts Vaihingen as well
Can you try reaching out to them and find out about this bug and the license? If we know the license we can likely rehost on HF.
Description
The file
top_potsdam_4_12_label.tif
in5_Labels_all.zip
isn't actually the mask, but seemts to be the mask overlayed on the RGB image. This leads to the 8th sample in the dataset having an all-zero mask.5_Labels_for_participants.zip
does contain the proper mask. Substituting with the image from that archive seems to solve the issue. Making it so thatrgb_to_mask
gives a warning about pixels not in the colormap would be good as well.Steps to reproduce
Version
0.5.0