keras-language-modeling icon indicating copy to clipboard operation
keras-language-modeling copied to clipboard

What changes are needed to run the CNN model?

Open wailoktam opened this issue 8 years ago • 2 comments

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?

wailoktam avatar Jul 05 '16 13:07 wailoktam

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.

eshijia avatar Jul 05 '16 14:07 eshijia

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

snowlord avatar Oct 13 '16 08:10 snowlord