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.

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

data augmentation #142

Open
CHN-001 opened this issue Jun 21, 2024 · 0 comments
Open

data augmentation #142

CHN-001 opened this issue Jun 21, 2024 · 0 comments

Comments

@CHN-001
Copy link

CHN-001 commented Jun 21, 2024

Hello author, I would like to use online data augmentation in BCNet now. I see that the image size can be randomly processed in the cfg file,So I want to add some other enhancements, such as the ones shown below,

T.RandomBrightness(0.9, 1.1) and T.RandomFlip(prob=0.5)

and I'm not sure how to add them. Should I modify the datamapper.py file? Or should I add some code to my train.py file? I'm looking forward to your reply and i will be grateful if u can help me! Please forgive my poor English.

These are some related works that I found, and i hope these can help us.
https://stackoverflow.com/questions/71774744/how-to-use-detectron2s-augmentation-with-datasets-loaded-using-register-coco-in/71799464#71799464
https://github.com/facebookresearch/detectron2/issues/1578

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

No branches or pull requests

1 participant