-
Notifications
You must be signed in to change notification settings - Fork 0
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
Augmentation SpeedUp fix #154
Conversation
…into fix/augmentation_speedup
This reverts commit 0d6d962.
Test Results 1 files 1 suites 4m 28s ⏱️ Results for commit 178a395. ♻️ This comment has been updated with latest results. |
☂️ Python Coverage
Overall Coverage
New FilesNo new covered files... Modified Files
|
), | ||
) | ||
|
||
return batch_transform, spatial_transform, resize_transform |
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.
The return type annotation and docs of _parse_cfg
are outdated
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.
LGTM
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.
Left some comments otherwise LGTM
This PR includes:
Resize()
after all other augmentations to ensure the correct input shapeResize()
callsSome benchmarks on the COCO train dataset (1 epoch, 4 workers, bs 16):
Mosaic + set of other augmentations (do change shape):
Only mosaic augmentation (doesn't change shape):
Update:
COCO train dataset (normalize, defocus, sharpen, rotate, perspective, affine, randomscale (all with p=1)):
Original PR with a bug (reverted)