This is a pytorch seq2seq tutorial for Formosa Speech Grand Challenge, which is modified from pratical-pytorch seq2seq-translation-batched.
Here is the tutorial in Chinese.
- python 3.5+
- pytorch 0.4.0
- tqdm
git clone https://github.com/ywk991112/pytorch-chatbot
In the corpus file, the input-output sequence pairs should be in the adjacent lines. For example,
I'll see you next time.
Sure. Bye.
How are you?
Better than ever.
The corpus files should be placed under a path like,
pytorch-chatbot/data/<corpus file name>
Otherwise, the corpus file will be tracked by git.
Run this command to start training, change the argument values in your own need.
python main.py -tr <CORPUS_FILE_PATH> -la 1 -hi 512 -lr 0.0001 -it 50000 -b 64 -p 500 -s 1000
Continue training with saved model.
python main.py -tr <CORPUS_FILE_PATH> -l <MODEL_FILE_PATH> -lr 0.0001 -it 50000 -b 64 -p 500 -s 1000
For more options,
python main.py -h
Models will be saved in pytorch-chatbot/save/model while training, and this can be changed in config.py.
Evaluate the saved model with input sequences in the corpus.
python main.py -te <MODEL_FILE_PATH> -c <CORPUS_FILE_PATH>
Test the model with input sequence manually.
python main.py -te <MODEL_FILE_PATH> -c <CORPUS_FILE_PATH> -i
Beam search with size k.
python main.py -te <MODEL_FILE_PATH> -c <CORPUS_FILE_PATH> -be k [-i]