-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
poor box width regression on text detection #518
Comments
Some questions:
Also, double check that mixup augmentation is not ruining your training. Try seeing if augmentation is what you expect. Below is a script I use to visualize the augmentation: |
@ankandrew hello
|
Hi @travisCxy! Sorry for late response. I think your analysis on point (3) seems accurate. Seems existing Lines 292 to 296 in 5b1ea9a
You can use my branch to select the bounding box loss function or cherry pick my commit to easily test other loss functions than default one ankandrew@9527269. |
hello, thank you for your code. I am training a yolov9-model for document image layout detection。I got a good map on my validate set。But the question is text detection some time got a bad width regression。can u help me?
![0cdd69db56714fbc89b8845eb3f6e11f_sm_yolov9](https://private-user-images.githubusercontent.com/39194742/343647213-2bbc157b-f7c5-4199-955d-7428aa9c2efb.jpg?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjMxMTA4MzYsIm5iZiI6MTcyMzExMDUzNiwicGF0aCI6Ii8zOTE5NDc0Mi8zNDM2NDcyMTMtMmJiYzE1N2ItZjdjNS00MTk5LTk1NWQtNzQyOGFhOWMyZWZiLmpwZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA4MDglMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwODA4VDA5NDg1NlomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPWUwNzdmNjI4ZmU3Yjg3YTJlY2RkOGRjZmJlMmNjZmE1Y2Q2YTNiN2NiMmM0ZmZiNTA4OWIyZTAzOGFiNTJlMDUmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.T-Ua6-PlN0k8YMk1yfJR3BlO3Wk0rVqiyhUGg64epSo)
The text was updated successfully, but these errors were encountered: