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

Pre-trained checkpoints #3

Open
MinamiKotoka opened this issue Jun 3, 2024 · 1 comment
Open

Pre-trained checkpoints #3

MinamiKotoka opened this issue Jun 3, 2024 · 1 comment

Comments

@MinamiKotoka
Copy link

Hi, do you plan to release the pre-trained seg/track checkpoints on sailvos3d and hoi4d datasets? Thanks!

@nguyentthong
Copy link

Hi @Jingkang50 @Jun-CEN @LilyDaytoy @choiszt, I have the same question as well. I have trained the rgbd segmentation model on the sailvos3d dataset. Particularly, these are the configs I use:

  • For training: configs/mask2former/mask2former_dual_rgbd.py
  • For testing: psg_4d_unitrack.py
  • Epochs: 12
  • Learning rate: 1e-4

Unfortunately, the results have not been so reasonable. In particular, these are some points with the segmentation model:

  • The model only works effectively with the person and car object.
  • It usually mis-detects other objects such as table, chair, and potted plant.
Screenshot 2024-06-16 at 11 23 08 Screenshot 2024-06-16 at 11 21 58

As such, can you release segmentation checkpoints to facilitate reproducibility? Thank you so much.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants