Skip to content
This repository has been archived by the owner on Apr 11, 2021. It is now read-only.

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

Open
wailoktam opened this issue Jul 5, 2016 · 2 comments
Open

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

wailoktam opened this issue Jul 5, 2016 · 2 comments

Comments

@wailoktam
Copy link

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
Copy link
Contributor

eshijia commented Jul 5, 2016

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
Copy link

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

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants