You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When trying to train a tracker on your dataset, we noticed that some frames contain duplicate track ids, however, the bounding box is not the same, for example : (video 33)
Should we split this track id into two separate ids, or remove the second identity ?
The text was updated successfully, but these errors were encountered:
After checking, we found that for duplicate track IDs, the later occurrence should be modified. Specifically, it should be updated to a value larger than the largest ID in the gt.txt file.
Hello,
When trying to train a tracker on your dataset, we noticed that some frames contain duplicate track ids, however, the bounding box is not the same, for example : (video 33)
Should we split this track id into two separate ids, or remove the second identity ?
The text was updated successfully, but these errors were encountered: