forward from:
https://blog.csdn.net/qq_24305433/article/details/80844548
The use of the training model is a new version of pytorch, and is loaded using an older version of pytorch
Solution:
1, since it is pytorch older version, that the easiest solution is of course a simple upgrade about pytorch ok.
2, the big foreign gods gave another solution is to add the following code at the beginning of the program, which can make older versions pytorch compatible with the new version pytorch, reference links https://discuss.pytorch.org/t/question-about -rebuild-tensor-v2 / 14560
import torch._utils try: torch._utils._rebuild_tensor_v2 except AttributeError: def _rebuild_tensor_v2(storage, storage_offset, size, stride, requires_grad, backward_hooks): tensor = torch._utils._rebuild_tensor(storage, storage_offset, size, stride) tensor.requires_grad = requires_grad tensor._backward_hooks = backward_hooks return tensor torch._utils._rebuild_tensor_v2 = _rebuild_tensor_v2