MrBlankness/LightM-UNet

about grad_scaler is set None

Xchhher opened this issue · 0 comments

hi, thx for the great work!
I have a question about the code.
In the class "nnUNetTrainerLightMUNet", I noticed that you set "self.grad_scaler = None"
In the case of using CUDA, Is there some special reason?