GeoZcx/A-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images

Problem about the output and the loss function

Closed this issue · 1 comments

Excuse me, i have a problem about the loss. the problem is that the output pixel of the branch is smaller than the label (such is the branch output is 2828,but the label is 256256),so how to deal with the label to fit the branch output pixel? i want to use downsampling...
looking foward to your reply!

Yes. The ground truth maps are downsampled to smaller sizes to fit the branch output.