We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hello. While using mmdet2 I wrote custom tensorboard hook which uses this metrics
'val/bbox_mAP': 'Validate/Precision total', 'val/bbox_mAP_l': 'Validate/Precision large', 'val/bbox_mAP_m': 'Validate/Precision medium', 'val/bbox_mAP_s': 'Validate/Precision small',
How can I use same metrics during evaluation to save best model weights and to look at graphs in tensorboard?
The text was updated successfully, but these errors were encountered:
Thanks to this comment wrote my custom hook with additional metrics for validation for object detection.
Sorry, something went wrong.
RangiLyu
No branches or pull requests
Hello. While using mmdet2 I wrote custom tensorboard hook which uses this metrics
How can I use same metrics during evaluation to save best model weights and to look at graphs in tensorboard?
The text was updated successfully, but these errors were encountered: