Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Multiple layers support #34

Closed
vikram-gupta opened this issue Jun 9, 2016 · 6 comments
Closed

Multiple layers support #34

vikram-gupta opened this issue Jun 9, 2016 · 6 comments

Comments

@vikram-gupta
Copy link

Do we have a plan to support multiple layers of LSTM ? The paper seems to have used multiple layers in encoder and decoder.
@macournoyer
Copy link
Owner

I'd like to. But ATM I run into memory errors when trying this. Not sure if it's the data or the model causing problems yet...

@vikram-gupta
Copy link
Author

Hi @macournoyer

Is there a branch where you committed the code changes for multiple layer support? If yes, i can try to work on it and get back if if the out of memory issue gets resolved.

Thanks,
Vikram

@macournoyer
Copy link
Owner

No branch @vikram-gupta. I just added a line here: https://github.com/macournoyer/neuralconvo/blob/master/seq2seq.lua#L14

@chenb67
Copy link
Contributor

chenb67 commented Jun 16, 2016

@vikram-gupta
I have multi-layer working on https://github.com/chenb67/neuralconvo/tree/b32fb1725b9977c1933bd4ec7669cc958cca3c18
I'd be happy to have some help testing it..
number of layers is controlled by the flag --numLayers

@vikram-gupta
Copy link
Author

@chenb67 Surely !

@macournoyer
Copy link
Owner

Currently testing this out in #38

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@macournoyer @chenb67 @vikram-gupta