Self-Correction-Human-Parsing
Self-Correction-Human-Parsing copied to clipboard
RuntimeError: All input tensors must be on the same device. Received cuda:0 and cuda:3
File "./train.py", line 189, soft_preds = torch.cat(soft_parsing, dim = 0).
Does anyone meet this error?
Do you solve this problem? I'm also have this problem
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?
Do you solve this problem? I'm also have this problem