RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

[iooops]

跑训练的时候报错

[iooops]

candidate_starts = candidate_starts.view(-1)[flattened_candidate_mask]    # [num_candidates]

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

[cuikai-ai]

遇到了同样的问题，请问你解决了吗，是怎么解决的？

[iooops]

没有

[lixiaoxiaobin]

也遇到了这个gpu和cpu乱用的问题，求解

[heguyu]

出问题的代码添加to("cuda:0")