請問我該如何解決 repeats has to be Long tensor 的問題？(How to solve a problem) about autopst

[auspicious3000]

Please make sure num_rep is a long tensor.

[chullin]

Thank you very much for your help, I have solved the problem

The following is my solution:
In torch.Tensor — PyTorch 1.9.1 documentation found that long tensor is 64-bit integer (signed)
Then print num_rep[i] in line 152 of model_autopst.py to know it dtype = torch.int32
And use num_rep = num_rep.to(torch.int64) to convert its type

152. num_rep = num_rep.to(torch.int64)
153.          for i in range(B):
154.              code_sync = cd_short[i].repeat_interleave(num_rep[i], dim=0)
155.              out_tensor[i, :len_long[i]-1, :] = code_sync