bug：总是提示KeyError: 'sh'

[hustcxx]

@brxx122 您好： 下载了您提供的cnn的数据集，采用运行命令 python train.py --cuda --gpu 0 --data_dir ./data/middledata_2/ --cache_dir ./cache/cnn --embedding_path ./embedding_dir/glove.42B.300d.txt --model HSG --save_root ./data/model_path --log_root ./log --lr_descent --grad_clip -m 3，其他的都没有改过，但是提示sh的keyerror错误，找了很久没有发现错误是什么原因导致的，是否可以帮忙解答下。报错详细信息如下： result = self.forward(*input, **kwargs) File "/data/cxx/program/extractivemethod/heterogeneousgraph/module/GATLayer.py", line 119, in forward h = g.ndata.pop('sh') File "/home/cxx/anaconda3/envs/cxxnlp/lib/python3.6/_collections_abc.py", line 795, in pop value = self[key] File "/home/cxx/anaconda3/envs/cxxnlp/lib/python3.6/site-packages/dgl/view.py", line 66, in getitem return self._graph._get_n_repr(self._ntid, self._nodes)[key] File "/home/cxx/anaconda3/envs/cxxnlp/lib/python3.6/site-packages/dgl/frame.py", line 393, in getitem return self._columns[name].data KeyError: 'sh'

[mhillebrand]

I too have this problem, but only if I run on CPU with --model HSG (rather than HDSG).

[cece00]

@mhillebrand @hustcxx Hi, I had this "sh" problem too when debugging. It's supposed to be a data problem. At line 113, reduce_func can't be called because there are no eligible edges, and that's why the key "sh" is not assigned. I solved it by checking the edges.