项目作者： itsmystyle

项目描述：
Interpretation for english autoencoder (seq2seq model).

高级语言： Jupyter Notebook

项目主页：

项目地址: git://github.com/itsmystyle/autoencoder-interpretation.git

创建时间： 2019-07-25T07:10:20Z
项目社区：https://github.com/itsmystyle/autoencoder-interpretation
开源协议：
下载

How to train

Put english corpus (train.txt, dev.txt, test.txt and long_test.txt[optional]) into the data/
Edit data/config.json
Change directory to src/ and run the following command to preprocess and generate training data.
```
 python make_dataset.py ../data/
```
Run the following command to prepapre model folder. Feel free to open the models/seq2seq/config.json to tune some hyperparameters.
```
 mkdir ../models/<your_model_folder>
 cp ../models/seq2seq/config.json ../models/<your_model_folder>
```

Run the following command to start training.

 python train.py ../models/<your_model_folder>/