Checkpoint之后报错

[smylab]

检查了很久不知道哪一步数没放到GPU设备上，没改动过代码，求助

Traceback (most recent call last):
File "main.py", line 116, in
main(config)
File "main.py", line 107, in main
solver.train()
File "/pubdata/lyz/SMY/TaylorSENet-main/solver.py", line 107, in train
train_avg_loss = self._run_one_epoch(epoch, val_opt=False)
File "/pubdata/lyz/SMY/TaylorSENet-main/solver.py", line 381, in _run_one_epoch
loss_dict = self._train_batch(batch_info)
File "/pubdata/lyz/SMY/TaylorSENet-main/solver.py", line 368, in train_batch
self.update_params(batch_loss)
File "/pubdata/lyz/SMY/TaylorSENet-main/solver.py", line 424, in update_params
self.optimizer.step()
File "/home/linyz/anaconda3/envs/py38/lib/python3.8/site-packages/torch/optim/optimizer.py", line 88, in wrapper
return func(*args, **kwargs)
File "/home/linyz/anaconda3/envs/py38/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
return func(*args, **kwargs)
File "/home/linyz/anaconda3/envs/py38/lib/python3.8/site-packages/torch/optim/adam.py", line 107, in step
F.adam(params_with_grad,
File "/home/linyz/anaconda3/envs/py38/lib/python3.8/site-packages/torch/optim/functional.py", line 86, in adam
exp_avg.mul(beta1).add(grad, alpha=1 - beta1)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!