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
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.
The text was updated successfully, but these errors were encountered:
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.
The text was updated successfully, but these errors were encountered: