Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/freakwill/ezgcn
🕸️easy graph convolution net (GCN) based on keras. So easy!
https://github.com/freakwill/ezgcn
gcn keras
Last synced: 5 days ago
JSON representation
🕸️easy graph convolution net (GCN) based on keras. So easy!
- Host: GitHub
- URL: https://github.com/freakwill/ezgcn
- Owner: Freakwill
- Created: 2020-05-10T08:21:45.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2023-03-24T23:24:21.000Z (almost 2 years ago)
- Last Synced: 2024-11-28T00:18:40.361Z (2 months ago)
- Topics: gcn, keras
- Language: Python
- Homepage:
- Size: 28.3 KB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
在[GCN](https://github.com/zhouchunpong/GCN_Keras)基础上修改。更加接近**scikit-learn**用法。
更加简单好用,几乎无需文档,看一个例子即可`train.py`。
## 基本流程
- 建立模型, (快捷方法from_data)
- 训练, fit(X_train, y_train, [X_test])
- 测试/预测, predict()## 注意事项
对分类问题,输出变量会被onehot编码,因此最终结果应该进行onehot解码。