Skip to content
This repository has been archived by the owner on Mar 23, 2021. It is now read-only.

Is the GRU implementation in consistent with the paper? #5

Open
my-yy opened this issue Dec 24, 2018 · 0 comments
Open

Is the GRU implementation in consistent with the paper? #5

my-yy opened this issue Dec 24, 2018 · 0 comments

Comments

@my-yy
Copy link

my-yy commented Dec 24, 2018

I read the peephole GRU implementation in models.py :

newgate = F.tanh(i_n + resetgate * h_n + p_n) (line54)
hy = newgate + inputgate * (hidden - newgate) . (line 55 )

Are they in consistent with the (3) and (4) equations in the paper?
I think the line 54 missed the “entrywise product of r_t and h_t-1” and the line 55 also not looks like the equation (4).

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

No branches or pull requests

1 participant