Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about the Instance Segmentation data format #334

Open
lorjul opened this issue Sep 23, 2024 · 0 comments
Open

Question about the Instance Segmentation data format #334

lorjul opened this issue Sep 23, 2024 · 0 comments
Labels
question Further information is requested

Comments

@lorjul
Copy link

lorjul commented Sep 23, 2024

Steps to Reproduce

Run any generation job:

screen python -m infinigen.datagen.manage_jobs --output_folder outputs/my_dataset --num_scenes 1 --pipeline_configs local_256GB.gin monocular.gin blender_gt.gin indoor_background_configs.gin --configs singleroom.gin --pipeline_overrides get_cmd.driver_script='infinigen_examples.generate_indoors' manage_datagen_jobs.num_concurrent=16 --overrides compose_indoors.restrict_single_supported_roomtype=True 

What version of the code were you using?

d55e297

Additional context

What are the numbers in the generated Instance Segmentation .npy files? I checked the docs about Instance Segmentation, but I still don't fully understand it. The InstanceSegmentation.npy contains values that look like ids. But why do we then need 3 channels? And what do the ids refer to? In the docs it says the instance id is defined in Objects_XXXX_XX_XX.json, but I don't see any reference to those ids in the JSON file.

@lorjul lorjul added the question Further information is requested label Sep 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

1 participant