Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
| Date | Stars |
|---|---|
| 2026-07-24 | 335 |
| 2026-07-25 | 335 |
| 2026-07-28 | 335 |
| 2026-07-30 | 335 |
| 2026-08-06 | 335 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
=================================================更新=========================================================== 训练好的模型已经上传到百度云网盘,如果大家有需要可以前去下载。模型训练速度的话,CPU,16G内存,一天即刻训练完成~~~ 链接:https://pan.baidu.com/s/1hrNxaSk 密码:d2sn =================================================分割线,下面是正文=============================================== 本文是一个简单的基于seq2seq模型的chatbot对话系统的tensorflow实现。 代码的讲解可以参考我的知乎专栏文章: [从头实现深度学习的对话系统--简单chatbot代码实现](https://zhuanlan.zhihu.com/p/32455898) 代码参考了DeepQA,在其基础上添加了beam search的功能和attention的机制, 最终的效果如下图所示:   测试效果,根据用户输入回复概率最大的前beam_size个句子:  #使用方法 1,下载代码到本地(data文件夹下已经包含了处理好的数据集,所以无需额外下载数据集) 2,训练模型,将chatbot.py文件第34行的decode参数修改为False,进行训练模型 (之后我会把我这里训练好的模型上传到网上方便大家使用) 3,训练完之后(大概要一天左右的时间,30个epoches),再将decode参数修改为True 就可以进行测试了。输入你想问的话看他回复什么吧== 这里还需要注意的就是要记得修改数据集和最后模型文件的绝对路径,不然可能会报错。 分别在44行,57行,82行三处。好了,接下来就可以愉快的玩耍了~~
Excerpt of 960 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c61eec57945d8a42, topic:chatbot, name:chatbot, readme:chatbot
matched fp:c61eec57945d8a42, topic:tensorflow