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
We didn't make that as we originally target for the pedestrian-only tracking datasets, i.e. MOT datasets. But that might be trivial to support with minor modification:
Following the DETR or Deformable DETR logic, we should more category for the classification.
For the matching part, apart from the current matching cost, we should make sure the category is kept for the objects to be associated.
But all these require you to train the model on corresponding datasets. We may make such support in the future.
Thank you for your great work. Does this algorithm and repo support multi-class as well?
The text was updated successfully, but these errors were encountered: