codekansas / keras-language-modeling

:book: Some language modeling tools for Keras
https://codekansas.github.io/language
MIT License
658 stars 170 forks source link

What changes are needed to run the CNN model? #17

Open wailoktam opened 8 years ago

wailoktam commented 8 years ago

Hi, I try changing the attention model to cnn without success. I get complaints about shape of input layers. Can you give me some ideas what to fix in order to run the cnn model included?

eshijia commented 8 years ago

For CNN model, you should first change the question_len = answer_len. In my experiments, CNN modoel is better enough. The attention (LSTM) model just improve the results a little.

snowlord commented 7 years ago

@eshijia i used CNN model,but it epochs 2 twice ,the loss value became nan. it seems getting in local minmize. image