should dropout be set to zero when inference?

liu-nlper / NER-LSTM-CRF

An easy-to-use named entity recognition (NER) toolkit, implemented the Bi-LSTM+CRF model in tensorflow.

347 stars 117 forks source link

should dropout be set to zero when inference? #9

Closed Alex-X-W closed 6 years ago

Alex-X-W commented 7 years ago

Hi liu-nlper,

Nice work and an easy to follow README!

But I noticed in your testing phase, you still construct the model such that its dropout equals what's in the config. Was is a design out of some special consideration? Cuz usually when inference we use the complete model without dropout.

Thanks! Xuan

liu-nlper commented 6 years ago

Hi Xuan, I have set dropout to zero in the 305th and 339th in the 'model.py'.