Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/bojone/dgcnn_for_reading_comprehension
keras implement of dgcnn for reading comprehension
https://github.com/bojone/dgcnn_for_reading_comprehension
Last synced: about 1 month ago
JSON representation
keras implement of dgcnn for reading comprehension
- Host: GitHub
- URL: https://github.com/bojone/dgcnn_for_reading_comprehension
- Owner: bojone
- Created: 2019-08-20T03:08:54.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2019-10-14T02:56:35.000Z (about 5 years ago)
- Last Synced: 2024-08-03T09:07:06.317Z (5 months ago)
- Language: Python
- Size: 646 KB
- Stars: 166
- Watchers: 4
- Forks: 52
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- StarryDivineSky - bojone/dgcnn_for_reading_comprehension
README
## keras implement of dgcnn for reading comprehension
基于膨胀门卷积的阅读理解式问答模型(Keras实现)### 详细介绍
- https://kexue.fm/archives/6906
- https://kexue.fm/archives/5409### 简要说明
- 每个目录下都有相应的README.md说明作用,整体结构简明清晰,应该不难理解。
- 测试环境为Python 2.7 + Tensorflow 1.8 + Keras 2.2.4。运行环境问题勿扰,谢谢!
- 直接进入到dgcnn目录,执行`python dgcnn.py`即可开始训练。
- 测试GPU为单卡GTX1060 6G(不用担心OOM了吧~),大概6小时内能训练到最优
- 有啥问题再提问吧。请尽量提有价值的问题~### 下载
- 词向量: 链接:https://pan.baidu.com/s/1YYE2T3f-lPyLBrJuUowAsA 密码:5p0h
- 数据集: 链接:https://pan.baidu.com/s/11C21BAupOpiYWoOx23J7Mg 密码:dh9w### 交流
QQ交流群:67729435,微信群请加机器人微信号spaces_ac_cn