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

number of nodes + 1 in train.py and model.py and number of layer - 1 in train.py? #14

Open
ShouravBR opened this issue Jul 21, 2022 · 0 comments

Comments

@ShouravBR
Copy link

ShouravBR commented Jul 21, 2022

Nice work!

I have questions regarding the number of nodes (n) in train.py#L68 and model.py#L123. From the paper, you mentioned the decoder layer has (n+m) nodes (I am assuming m=1 here as Y vector is of length 1). But why did you add a node in the training script?

And why reduce the number of layers by 1 from args in train.py#39?

Thank you for answering.

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