search

aonotas / deep-crf

An implementation of Conditional Random Fields (CRFs) with Deep Learning Method
http://deep-crf.com
MIT License
167 stars 48 forks source link

--dev #63

Open HalaSalameh opened 5 years ago

HalaSalameh commented 5 years ago

what is the use of --dev? what does early stopping mean?

himkt commented 5 years ago

As you mentioned, the help comment says dev_file is used to do early stopping. However, current implementation does not seem to stop training loop by watching metrics on dev data.

dev_file is used to decide whether deep-crf creates a snapshot or not for each epoch, I think. https://github.com/aonotas/deep-crf/blob/ff24ecc9e9238afef28d14a2f3c8b75307c9ceaf/deepcrf/main.py#L484-L494

HalaSalameh commented 5 years ago

As you mentioned, the help comment says dev_file is used to do early stopping. However, current implementation does not seem to stop training loop by watching metrics on dev data.

dev_file is used to decide whether deep-crf creates a snapshot or not for each epoch, I think. https://github.com/aonotas/deep-crf/blob/ff24ecc9e9238afef28d14a2f3c8b75307c9ceaf/deepcrf/main.py#L484-L494

the code throws an error if there is no dev_file argument and i dont know what file i should give it so i just give it the same file as the input dataset