Given a State obtain the ground-truth bounding-boxes as torchvision.tv_tensors.BoundingBoxes object of size [N x 4].
State
torchvision.tv_tensors.BoundingBoxes
[N x 4]
Notes
The box_iou function expects that the bounding boxes are in the ‘XYXY’ format.
IntersectionOverUnion.get_data()
dgs.models.similarity.pose_similarity.IntersectionOverUnion.forward
dgs.models.similarity.pose_similarity.IntersectionOverUnion.get_target