RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

Memory Format
1

Screenshot from 2020-09-03 12-10-19
I have checked my input and model are on GPU. However, it seemed not working. Can anyone help me with the bug I’m encountering?

2

Could you post your code so that we could have a look, please?