Notes on versioning
0.2.1 (2018-08-31)
- First compatibility steps with Pytorch 0.4.1 (non breaking)
- Fix TranslationServer (when various request try to load the same model at the same time)
- Fix StopIteration error (python 3.7)
- Ensemble at inference (thanks @Waino)
0.2 (2018-08-28)
- Compatibility fixes with Pytorch 0.4 / Torchtext 0.3
- Multi-GPU based on Torch Distributed
- Average Attention Network (AAN) for the Transformer (thanks @francoishernandez )
- New fast beam search (see -fast in translate.py) (thanks @guillaumekln)
- Sparse attention / sparsemax (thanks to @bpopeters)
- Refactoring of many parts of the code base:
- change from -epoch to -train_steps -valid_steps (see opts.py)
- reorg of the logic train => train_multi / train_single => trainer
- Many fixes / improvements in the translationserver (thanks @pltrdy @francoishernandez)
- fix BPTT