Closed gsygsy96 closed 5 years ago
To solve it, using nn.ModuleList() to warp self.lins in model/network_basics.py.
Please, can you tell me a little bit more about your solution? 😃 Sadly I'm stuck there while trying to train on multiple gpus for camvid segmentation.
I guess there is a bug when you put your model to mutil-gpus.
Reference: https://github.com/pytorch/pytorch/issues/8637#issuecomment-398268602