Self-Correction-Human-Parsing icon indicating copy to clipboard operation
Self-Correction-Human-Parsing copied to clipboard

Published 20 hours ago • verified publisher icon GoGoDuck912

RuntimeError: All input tensors must be on the same device. Received cuda:0 and cuda:3

Open tjwyj opened this issue 3 years ago • 3 comments

File "./train.py", line 189, soft_preds = torch.cat(soft_parsing, dim = 0).

Does anyone meet this error?

tjwyj avatar Jun 11 '21 09:06 tjwyj

Do you solve this problem? I'm also have this problem

lioo717 avatar Jul 22 '21 06:07 lioo717

File "train.py", line 189, in main soft_parsing = [] RuntimeError: All input tensors must be on the same device. Received cuda:0 and cuda:1 When I use only one device, I also have the problem.Do you solve this problem?

longyue00 avatar Aug 07 '21 02:08 longyue00

Do you solve this problem? I'm also have this problem

zj12346666 avatar Nov 25 '22 05:11 zj12346666