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.

Sign up for GitHub

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

Jump to bottom

l1_lamda value for SUN RGBD #7

Open
harshm121 opened this issue Sep 27, 2022 · 4 comments
Open

l1_lamda value for SUN RGBD #7

harshm121 opened this issue Sep 27, 2022 · 4 comments

Comments

@harshm121
Copy link

Hi,
I am trying to reproduce the results for SUN RGBD. The paper mentions 1e-3 whereas the ReadMe mentions 1e-6.
Thanks!
@yikaiw
Copy link
Owner

yikaiw commented Sep 28, 2022

Hi, do you mean SUN RGBD for semantic segmentation or SUN RGBD for 3D object detection?

@harshm121
Copy link
Author

Hi,
Sorry for not being clear. I mean SUN RGBD for the segmentation task.

@yikaiw
Copy link
Owner

yikaiw commented Oct 4, 2022

1e-6 empirically works better. In fact, choosing this hyper-parameter is not strict, as long as we keep the final exchanged ratios around 30%~50%.

@harshm121
Copy link
Author

Thanks. I did try reproducing the results with 1e-6 but was not able to get even close to the reported 51.4 mIoU on Segformer B2.
Can you share the config.py file for the SUN RGBD (and also any other specific details I should note when training on SUN RGBD)?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@yikaiw @harshm121