segmentation_models.pytorch epsilon in jaccardscore and dicescore is not read as a torch tensor

epsilon in jaccardscore and dicescore is not read as a torch tensor

Open TomatoGreen2 opened this issue 11 months ago • 2 comments

suggestion - add line: eps=torch.tensor(1e-07, dtype=torch.float32) or eps=torch.tensor(1e-07, dtype=gt.dtype)

Mar 07 '24 02:03 TomatoGreen2

Maybe you should suggest this PR to https://github.com/isaaccorley/torchseg

Mar 12 '24 02:03 JulienMaille

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.

May 12 '24 01:05 github-actions[bot]

This issue was closed because it has been stalled for 7 days with no activity.

May 19 '24 01:05 github-actions[bot]