You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When should you call it?
2.a When should you call it when you are using a LSTM?
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.
The text was updated successfully, but these errors were encountered:
I have some questions about forget.
2.a When should you call it when you are using a LSTM?
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.
The text was updated successfully, but these errors were encountered: