ContrastiveLosses4VRD icon indicating copy to clipboard operation
ContrastiveLosses4VRD copied to clipboard

Format of relation annotations?

Open shabnamsadegh opened this issue 5 years ago • 0 comments

I wonder how you defined the bbox for the subjects and objects in rel_annotations_train.json?

Do you have any documentation or code on how you built rel_annotations_train.json?

Anyway, I tracked the code to this line(json_dataset_rel.py):

sbj_gt_box = box_utils_rel.y1y2x1x2_to_x1y1x2y2(rel['subject']['bbox'])

are you using y1y2x1x2 format for the annotations?

shabnamsadegh avatar May 27 '20 08:05 shabnamsadegh