seq2seq-couplet

by wb14123

Play couplet with seq2seq model. 用深度学习对对联。

4.7K Stars 934 Forks Last release: Not found GNU Affero General Public License v3.0 33 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

This is a project use seq2seq model to play couplets (对对联)。 This project is written with Tensorflow. You can try the demo at https://ai.binwang.me/couplet.

Pre-requirements

  • Tensorflow
  • Python 3.6
  • Dataset

Dataset

You will need some data to run this program, the dataset can be downloaded from this project.

** Note: If you are using your own dataset, you need to add

and
 as the first two line into the vocabs file. **

Usage

Train

Open

couplet.py
and config the file locations and hyperparams. Then run
python couplet.py
to train the model. You can see the training loss and bleu score at Tensorbloard. You may need to re-config
learning_rate
when you find the loss stops descresing. Here is an example of the loss graph:

loss graph

If you stoped the training and want to continue to train it. You can set

restore_model
to
True
and use
m.train(, start=)
, which
start
is the steps you've already run.

I've trained the model on a Nivida GTX-1080 GPU for about 4 days.

Run the trained model

Open

server.py
and config the
vocab_file
and
model_dir
params. Then run
python server.py
will start a web service that can play couplet.

Examples

Here are some examples generated by this model:

| 上联 | 下联 | |-----------------------------|--------------------| | 殷勤怕负三春意 | 潇洒难书一字愁 | | 如此清秋何吝酒 | 这般明月不须钱 | | 天朗气清风和畅 | 云蒸霞蔚日光辉 | | 梦里不知身是客 | 醉时已觉酒为朋 | | 千秋月色君长看 | 一夜风声我自怜 |

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.