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
Loss_region unable to converge #11
Comments
How is your test performance? |
The performanceis similar to your result |
As shown in Paper, without using Loss_region can still work well, but I wonder why it is hard to estimate this part. I think estimate crop_xyz is a harder task and it can work. |
Loss region can be regarded as a regularizer or auxiliary task for learning the symmetries and the coarse region information. To estimate a 6D pose, we only need the correspondences, so the network might pay more attention to optimize towards the xyz part rather than the regions. Besides, when doing the class-agnostic training, the learning of regions might be much harder. |
thanks for your explanation |
Other Loss has significant decline, but Loss_region‘s drop is very weak. My training use config : configs/gdrn/lm/a6_cPnP_lm13.py
Region area choose 4, 16, 64 can not make any improve.
The text was updated successfully, but these errors were encountered: