RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0

resume 을 구현하기 위해 저장한 optimizer 를 불러왔는데 이런 오류가 있었다.. ... RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 optimizer 에도 .cuda() 를 해줘야하나...고민하던 차에 공식 문서를 보고 알았다. torch.optim — PyTorch master documentation Constructing it To construct an Optimizer you have to give it an iterable containing the parameters (all should be Variable s) to optimize. Then, you can specify optimizer-specific options such as the learning rate, weight decay, etc. Note If you ...

원문링크 : RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0