The training loss is always nan. about pytorch-unet HOT 3 OPEN

I found if revert it to the tag v4.0, it's ok, maybe some one can find which commit after that version involved the problem.

from pytorch-unet.

I managed to solve this problem by turning off mixed precision flag.
That is, instead of using python train.py --amp,
use python train.py to train the code.
Although it takes more time and memory during training, the code can be trained successfully.

Similar issue: pytorch/pytorch#40497

from pytorch-unet.

I am experiencing the same issue, I have used all the default settings and the Carvana Dataset, but my loss is always nan and dice score is not changing during training. Did you find any solution ?

from pytorch-unet.