text_gcn.pytorch

text_gcn.pytorch copied to clipboard

I didn't understand the point of generating node vectors in `./preprocess/build_graph.py` when using an Identity matrix as node features in `./train.py`. Please correct me if I am wrong.

cocoiit

https://github.com/iworldtong/text_gcn.pytorch/blob/bc8d0c62f3167462d073ae7ef877ea24536c5f71/preprocess/build_graph.py#L369 Can u explain what labels did you used for vocab nodes? in ur code i see its all zero values.

riyaj8888

Why not use softmax for gcnlayer2?

lhy2749

support 在模型中的含义是什么？

2

damionfan

TypeError: cuda() missing 1 required positional argument: 'self'

5

when i run python train.py mr, error reporting Traceback (most recent call last): File "train.py", line 82, in model_func = model_func.cuda() TypeError: cuda() missing 1 required positional argument: 'self' Do...

dcheason