Mattia Segù

Hi Kieran, thank you so much for your interest and for your updates to the codebase! I will keep an eye on the pull request and merge it as soon...

Hi @lsssssssssss , I've just updated the README with instructions on how to compile the Chamfer module. Can you please try that and let me know if it solves your...

Hi @qiminchen and @csjxchen, sorry for not replying before! This definitely is a typo :) If you are working on it, you could simply make a PR to fix it...

Hi @godspeed1989 I am glad to know that you appreciate our work! The loss to train our network is literally `torch.nn.functional.mse(outputs,targets)`, plus L2 regularization on model weights. To evaluate the...

Hi @AndreMouton As I replied to @SaumilShah66, it is a known problem that training with the heteroscedastic loss may be difficult because of numerical instability problems. As you noticed, we...

Hi @SaumilShah66 Thanks for the interest in our work! Concerning the NaNs for loss when training ADF, it is a known problem that training with the heteroscedastic loss may be...

Hi @MoHassoubah, you are right, it should be the std! I fixed this already in the version of the repo on my github: https://github.com/mattiasegu/uncertainty_estimation_deep_learning

Hi @Eric-mingjie, great to hear that you enjoy our work! We plan to release the trained models, however it will take some time to polish the code for training. I'll...

Yes, 8 GPUs NVIDIA RTX 4090. I use the --use-checkpoint flag and the default learning rate provided in the config file. I'm now trying with deformable DETR to see if...

Thank you very much for your detailed replies and for your efforts! I will keep the issue updated as soon as I: - re-run the DAB-DETR training - run the...