3-D-Scene-Graph
3-D-Scene-Graph copied to clipboard
Bug reports and remedies
Thanks for your great job. And here I want to report some bugs and I have remedied them.
- In the https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/object_prior_extraction.py#L45 and https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/relation_prior_extraction.py#L103,
the key 'name' may not appear in the rel['subject'] or rel['object']. I think it may be the problem of the updated raw relationships.json. So you can replace them with the following codes:
if 'name' in rel['object']:
obj = rel['object']['name']
else:
obj = rel['object']['names'][0]
if 'name' in rel['subject']:
sub = rel['subject']['name']
else:
sub = rel['subject']['names'][0]
- In the https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/model/keyframe/keyframe_extracion.py#L274, the intrinsic_depth is a list containing the strings rather than float numbers. You can add the following codes:
tmp_intrinsic_depth = []
for row in intrinsic_depth:
row = [float(r) for r in row]
tmp_intrinsic_depth.append(row)
intrinsic_depth = tmp_intrinsic_depth
- In the https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/scene_graph_tuning.py#L160
You should firstly create the class instance first.
toolforvis = tools_for_visualizing()
img_obj_detected = toolforvis.vis_object_detection(image_scene.copy(), test_set, obj_cls[:, 0], obj_boxes, obj_scores[:, 0])