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.

Sign up for GitHub

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

Jump to bottom

Evaluate peephole importance #21

Open
carlthome opened this issue Dec 6, 2017 · 0 comments
Open

Evaluate peephole importance #21

carlthome opened this issue Dec 6, 2017 · 0 comments
Labels
help wanted question

Comments

@carlthome
Copy link
Owner

The basic intuition for peepholes is that they benefit problems that require precise timing but I wonder how they work for the convolutional RNNs. The simpler version without peepholes could be calculated with fewer operations so what are the exact trade-offs?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
help wanted question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@carlthome