chengsen / PyTorch_TextGCN

The PyTorch 1.6 and Python 3.7 implementation for the paper Graph Convolutional Networks for Text Classification
https://arxiv.org/abs/1809.05679
107 stars 21 forks source link

feature矩阵为什么是全1呢? #8

Open kyle5358 opened 1 year ago

kyle5358 commented 1 year ago

作者你好!我对您trainer.py中的feature矩阵有点疑问。论文中feature矩阵应该是文档节点和单词节点的词袋表示,但是我看了您的代码,好像您用全1代替,请问是什么原因呢?