Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
fabwa opened this issue · comments
Getting this for any image or setting i try on GFPGAN
you need the facexlib change that was made in the environment.yaml yesterday, update
I pulled today and have facexlib==0.2.5.
Same issue tho.
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same