-
Notifications
You must be signed in to change notification settings - Fork 1.8k
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
Fix issue #754 #1035
Fix issue #754 #1035
Conversation
See this comment (#1034 (comment)) about a question on possible change to the implementation. |
Hi @rolson24 👋🏻 ! Thanks a lot for your contribution. This is exactly what we needed. I'm super happy with this update. |
Hi @SkalskiP I made a silly mistake in this PR with using enumerate to get the index of each track, because I forgot to test the new version. I have submitted another PR that fixes the issue. So sorry about this, I will try to remember to re-test every time before I submit a PR. |
fix bug from PR roboflow#1035 change update_with_tensors to not return tracks with track_id < 0 reset the track_id counter when initializing a new ByteTrack object
fix bug from PR roboflow#1035 change update_with_tensors to not return tracks with track_id < 0 reset the track_id counter when initializing a new ByteTrack object update docstring
fix bug from PR roboflow#1035 change update_with_tensors to not return tracks with track_id < 0 reset the track_id counter when initializing a new ByteTrack object update docstring
fix tuple unpacking bug in PR roboflow#1035 Fix bug with detections with un-initialized tracker_ids
fix bug from PR roboflow#1035 change update_with_tensors to not return tracks with track_id < 0 reset the track_id counter when initializing a new ByteTrack object update docstring Fix other bug from PR roboflow#1035
fix tuple unpacking bug in PR #1035 Fix bug with detections with un-initialized tracker_ids
Description
New version of this PR (#1034) with one commit and requested changes.
This change addresses this issue: (#754)
update_with_detections
now returns the original detections that were tracked by ByteTrack with their original bboxes, masks, class_ids, data fields and with updated track_ids. Detections that were not tracked this frame are not included in the returned detections.Type of change
How has this change been tested, please provide a testcase or example of how you tested the change?
I have tested this change by running object tracking for both object detection and segmentation in this colab notebook
Any specific deployment considerations
Tracking docs should be updated to reflect that ByteTrack can now do segmentation tracking.
Docs