This repository has been archived by the owner on Jul 1, 2023. It is now read-only.
RNN gradients are wrong #518
Comments
Nice catch! |
Should I take care of this @eaplatanios |
@Shashi456 thanks! Feel free to fix the |
I think this has been solved by the two PRs merged. Feel free to reopen if there is still a problem. |
Like you said there are already two issues tracking this. I wanted to do a bit of clean-up, but if anyone feels strongly about this issue remaining open, they can click the button :) |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
This line should be
饾泚cell += new饾泚cell
instead. There is also an issue with the initial state initialization to a zeros tensor with batch size 1 that does not broadcast. I don't have time to open a PR right now because I'm traveling but will try to open one once I get a chance.The text was updated successfully, but these errors were encountered: