-
Notifications
You must be signed in to change notification settings - Fork 26.3k
Use NNPACK for strided convolutions. #29595
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
Conversation
houseroad
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
New function should be backward compatible. Could you fix the CI and trigger the backward_compatible_test?
facebook-github-bot
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@AshkanAliabadi has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
Good suggestion. We should run the test to confirm. For this specific PR it only adds an internal op (starting with "_", not exposed to python) so it shouldn't break any external contract if we have done it correctly :) |
facebook-github-bot
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@AshkanAliabadi has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
|
Synced offline with Lu and ran the test locally. That aside, there seems to be something wrong with the CI. |
|
The whole CI is broken at this moment as well. |
facebook-github-bot
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@AshkanAliabadi has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
Summary: Use NNPACK for strided convolutions. ResNet50 on Pixel 3: - Before: 552.956 ms - After: 402.947 ms Pull Request resolved: pytorch/pytorch#29595 Reviewed By: houseroad Differential Revision: D18457472 Pulled By: AshkanAliabadi fbshipit-source-id: 51f22ce120c39f197cd564bcc71bbad2951edf85
|
@AshkanAliabadi merged this pull request in 9ee6fa0. |
Summary: Use NNPACK for strided convolutions. ResNet50 on Pixel 3: - Before: 552.956 ms - After: 402.947 ms Pull Request resolved: pytorch#29595 Reviewed By: houseroad Differential Revision: D18457472 Pulled By: AshkanAliabadi fbshipit-source-id: 51f22ce120c39f197cd564bcc71bbad2951edf85
Use NNPACK for strided convolutions.
ResNet50 on Pixel 3: