When I opened this repository in 2017, there was no official code yet. I tried to implement the paper as I understood, but to no surprise it had several bugs. I realized them mostly thanks to people who issued here, so I'm very grateful to all of them. Though there is the official implementation as well as several other unofficial github repos, I decided to update my own one. This update focuses on:
I still stick to IWSLT 2016 de-en. I guess if you'd like to test on a big data such as WMT, you would rely on the official implementation. After all, it's pleasant to check quickly if your model works. The initial code for TF1.2 is moved to the tf1.2_lecacy folder for the record.
It should be extracted to
iwslt2016/de-en folder automatically.
If you want to change the vocabulary size (default:32000), do this.
python prepro.py --vocab_size 8000
It should create two folders
hparams.py to see which parameters are possible. For example,
python train.py --logdir myLog --batch_size 256 --dropout_rate 0.5
wget https://dl.dropbox.com/s/4lom1czy5xfzr4q/log.zip; unzip log.zip; rm log.zip
python test.py --ckpt log/1/iwslt2016_E19L2.64-29146 (OR yourCkptFile OR yourCkptFileDirectory)
|tst2013 (dev)||tst2014 (test)|