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 @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.
As such, can you release segmentation checkpoints to facilitate reproducibility? Thank you so much.
Hi, do you plan to release the pre-trained seg/track checkpoints on sailvos3d and hoi4d datasets? Thanks!
The text was updated successfully, but these errors were encountered: