Encountered an in-place operation error when using the PAMNet model

[lfcdepression]

I have encountered an error while using the PAMNet model for RNA structure prediction. Specifically, the error occurred when executing the following line of code:

torch.arange(1, self.freq.numel() + 1, out=self.freq).mul_(PI)

The program threw the following error:
RuntimeError: a leaf Variable that requires grad is being used in an in-place operation.

I have consulted the relevant documentation but still cannot resolve this issue. Could you please advise on how to modify the code to avoid this error?

[zetayue]

I think it should be related to this: https://github.com/pyg-team/pytorch_geometric/pull/4424. I haven't encountered this error before, but you can try the following code to replace the previous one: https://github.com/pyg-team/pytorch_geometric/blob/c15421387b8049f32cae6967a9f8e77a03ff56b5/torch_geometric/nn/models/dimenet.py#L63-L66

[lfcdepression]

Thanks for your reply! The code runs normally after replacing.I think it's because the version is different, I'm using a different version than the one in requirement.txt