search

NVlabs / Deep_Object_Pose

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
Other
1.03k stars 287 forks source link

Update the codes related to the position from pybullet #208

Closed Branden-Kang closed 2 years ago

Branden-Kang commented 2 years ago

This PR fixes the following things in single_video_pybullet:

I fix the error below:

When we command "python single_video_pybullet.py --path_single_obj models/Ketchup/google_16k/textured.obj --nb_frames 10 --nb_objects 4 --nb_distractors 4 --scale_single_obj 0.04" (Only nb_distractors parameter is added in this command), there is an error and the code doesn't work.

The error part is below:  525         visii.entity.get(entry['visii_id']).get_transform().get_parent().set_position(  526         visii.entity.get(entry['visii_id']).get_transform().get_parent().get_position(), 528         previous = True 529     ) 530     visii.entity.get(entry['visii_id']).get_transform().get_parent().set_rotation( 531         visii.entity.get(entry['visii_id']).get_transform().get_parent().get_rotation(), 532         previous = True 533     )

534     update_pose(entry,parent=True)

TontonTremblay commented 2 years ago

Thank you so much, I tested it on my end and I was able to use it no problems.