bug 求助？

[imnujf]

Traceback (most recent call last): File "main_mil.py", line 203, in fire.Fire() File "/usr/lib/python2.7/site-packages/fire/core.py", line 127, in Fire component_trace = _Fire(component, args, context, name) File "/usr/lib/python2.7/site-packages/fire/core.py", line 366, in _Fire component, remaining_args) File "/usr/lib/python2.7/site-packages/fire/core.py", line 542, in _CallCallable result = fn(*varargs, **kwargs) File "main_mil.py", line 67, in train data = select_instance(model, data, label) File "main_mil.py", line 117, in select_instance out = model(data) File "/usr/lib64/python2.7/site-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/home/zhaojiapeng/pytorch-relation-extraction-master/models/PCNN_ONE.py", line 126, in forward x = [self.mask_piece_pooling(i, insMasks) for i in x] File "/home/zhaojiapeng/pytorch-relation-extraction-master/models/PCNN_ONE.py", line 85, in mask_piece_pooling masks = mask_embedding(mask).unsqueeze(-2) * 100 File "/usr/lib64/python2.7/site-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/usr/lib64/python2.7/site-packages/torch/nn/modules/sparse.py", line 103, in forward self.scale_grad_by_freq, self.sparse File "/usr/lib64/python2.7/site-packages/torch/nn/_functions/thnn/sparse.py", line 59, in forward output = torch.index_select(weight, 0, indices.view(-1)) TypeError: torch.index_select received an invalid combination of arguments - got (torch.FloatTensor, int, torch.cuda.LongTensor), but expected (torch.FloatTensor source, int dim, torch.LongTensor index)

[tao2years]

同样的问题，请问您解决了吗

[ShomyLiu]

@imnujf @598807302 不好意思，最近在赶东西， 各位遇到的问题，可以先自行debug看看，或者检查下环境、数据。 过几天，会跟进这些bug

[imnujf]

@598807302 na'li 那里的问题，你在那加一个.cuda()就行了。

[tao2years]

@imnujf 好的谢谢