dgs.models.similarity.pose_similarity.IntersectionOverUnion.get_data

IntersectionOverUnion.get_data(ds: State) torchvision.tv_tensors.BoundingBoxes[source]

Given a State obtain the ground-truth bounding-boxes as torchvision.tv_tensors.BoundingBoxes object of size [N x 4].

Notes

The box_iou function expects that the bounding boxes are in the ‘XYXY’ format.