-
Notifications
You must be signed in to change notification settings - Fork 170
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
The RandAugment Implementation Is Wrong #39
Comments
Hi @psellcam , thanks for pointing out the issue. Let me know if I understand this correctly. Thanks again. |
Yes exactly!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
google-research/fixmatch#65
As confirmed by the collaborator of the official implementation the randaugment function should be applied all the time not 50 percent of the time.
The only 50% chance from the original paper refers to the flips etc of weak augmentation only and definitely not the strong augmentation methods
This could explain why this repository does better than the original paper but it isn't what the original paper did.
For those who want the true performance of the original fixmatch paper you need to delete
From the https://github.com/kekmodel/FixMatch-pytorch/blob/master/dataset/randaugment.py file
The text was updated successfully, but these errors were encountered: