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.

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

Forget function #220

Open
jsuit opened this issue Apr 23, 2016 · 0 comments
Open

Forget function #220

jsuit opened this issue Apr 23, 2016 · 0 comments

Comments

@jsuit
Copy link

jsuit commented Apr 23, 2016

I have some questions about forget.

  1. What exactly does forget do?
  2. When should you call it?
    2.a When should you call it when you are using a LSTM?
  3. If you call forget, should you also call recycle?

Here's a test case:
I have a tensor T of size n (batchsize) x 50, each entry represents the indx to lookup a word. Let this represent a batch of size n with 50 timesteps. If I have a LSTM in my model, do (or should) I call forget after I give my model T. I noticed in the language model example, forget was never called if you were using a LSTM.

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

No branches or pull requests

1 participant