Is it possible to run the single frame keypoint evaluation without the head bounding box?? My estimator only estimates keypoints. If i set the head bounding box size to 0 it gives 0 percent accuracy
Hi what about this case? in MS COCO, we do not need to provide scale as it is automatically computed from given keypoints. How come PoseTrack seems to need this?
Good day,
Is it possible to run the single frame keypoint evaluation without the head bounding box?? My estimator only estimates keypoints. If i set the head bounding box size to 0 it gives 0 percent accuracy