Closed nicolasugrinovic closed 1 year ago
Sorry for the late reply. Before refinement, we only evaluate the visible joints. After refinement, all joints are considered if the person is matched.
No worries, thanks for the reply. How do you this matching between people after refinement?
We use 2D joints and head. More details in test_util_panoptic.py P.S. It serves for reference only and may not support running directly.
Hello, I see that 2d matching is done in the code. If the prediction closest to the ground truth exceeds 30 pixels, the error of this ground truth will not be calculated, right?
Right, together with the head joint.
Ok,Thanks!
Dear authors, I was wondering:
Thanks!