focal_segmentation icon indicating copy to clipboard operation
focal_segmentation copied to clipboard

semantic segmentation with focal loss

Results 2 focal_segmentation issues
Sort by recently updated
recently updated
newest added

Hello, I found you use `pt = torch.exp(logpt)` to calculate probability, but which sample's probability is represented by `pt`. I think `pt` represents the probability of a sample, not the...

Please add training results