zhaohaoyu376

 The model doesn't converge.

I have tried multiple environments, including py37+torch1.31+cu11.6 and py38+torch2.01+cu11.8. However, the final results are all not satisfactory.

> > I have tried multiple environments, including py37+torch1.31+cu11.6 and py38+torch2.01+cu11.8. However, the final results are all not satisfactory. > > It looks very strange. Can you show me the...

> In my test, set `no_dr=True` and `no_ds=True` (disable the deformation of rotation and scaling) will decrease the happening of the problem. However, it seems that performance might be significantly...

Why do I always run again because the loss is nan? I can't even finish running it once.