Fang-git0

I wonder to know that why you use distill in the paper. I did not figure it out. And it did not explain in the paper.

关于evaler

1

直接运行时，遇到问题 ValueError: ('The `preds` and `target` should have the same shape,', ' got `preds` with shape=torch.Size([11, 16]) and `target` with shape=torch.Size([11, 15]).') 出错位置 f1 = metrics.f1_score(pred_padded.T.to('cpu'), target.T.to('cpu'))