i'm a freshman in pytorch, when i follow the guides to train the AI model from scratch, and run the human_play.py, errors display:RuntimeError: Error(s) in loading state_dict for Net:
size mismatch for act_fc1.weight: copying a param with shape torch.Size([36, 144]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for act_fc1.bias: copying a param with shape torch.Size([36]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for val_fc1.weight: copying a param with shape torch.Size([64, 72]) from checkpoint, the shape in current model is torch.Size([64, 128]).
But i don't modify anywhere except those mentioned in the README.md. Could you please point out where the point is? THX.
i'm a freshman in pytorch, when i follow the guides to train the AI model from scratch, and run the human_play.py, errors display:RuntimeError: Error(s) in loading state_dict for Net: size mismatch for act_fc1.weight: copying a param with shape torch.Size([36, 144]) from checkpoint, the shape in current model is torch.Size([64, 256]). size mismatch for act_fc1.bias: copying a param with shape torch.Size([36]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for val_fc1.weight: copying a param with shape torch.Size([64, 72]) from checkpoint, the shape in current model is torch.Size([64, 128]).
But i don't modify anywhere except those mentioned in the README.md. Could you please point out where the point is? THX.