This repository has been archived by the owner on Oct 11, 2023. It is now read-only.
Running ROI detection at training #31
Comments
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Is there a reason why we run ROI detection for training and keep those with large overlap, instead of just using the ground truth bounding boxes with transitional + scaling (random) augmentation?
The text was updated successfully, but these errors were encountered: