You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi there, greetings to you! Thank you for acknowledging our outstanding work. I'm currently facing an issue where I'd like to extract the location names for each high_descs, but I haven't been able to find any relevant information.
To make matters worse, I can't even determine the location names for each task. I've noticed that the scene field contains 'floor_plan' and 'scene_num', but I haven't been able to find the corresponding scene names for their attribute values (for example, 'floor_plan': "FloorPlan7", 'scene_num': 7).
In the defined folder names, I can indeed find some container names, but I'm more interested in obtaining the container or location information corresponding to each high_descs. This would allow me to see the positional changes as the tasks progress (from a semantic perspective rather than an image-based one).
This has been somewhat perplexing, and I would greatly appreciate any professional advice you could offer.
The text was updated successfully, but these errors were encountered:
Hi there, greetings to you! Thank you for acknowledging our outstanding work. I'm currently facing an issue where I'd like to extract the location names for each
high_descs
, but I haven't been able to find any relevant information.To make matters worse, I can't even determine the location names for each task. I've noticed that the
scene
field contains 'floor_plan' and 'scene_num', but I haven't been able to find the corresponding scene names for their attribute values (for example, 'floor_plan': "FloorPlan7", 'scene_num': 7).In the defined folder names, I can indeed find some container names, but I'm more interested in obtaining the container or location information corresponding to each
high_descs
. This would allow me to see the positional changes as the tasks progress (from a semantic perspective rather than an image-based one).This has been somewhat perplexing, and I would greatly appreciate any professional advice you could offer.
The text was updated successfully, but these errors were encountered: