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

Where is the pretrained model on KITTI ? #19

Closed
cgbcgb opened this issue Jul 8, 2021 · 4 comments
Closed

Where is the pretrained model on KITTI ? #19

cgbcgb opened this issue Jul 8, 2021 · 4 comments
Assignees

Comments

@cgbcgb
Copy link

cgbcgb commented Jul 8, 2021

Thanks for your great work, I have two questions:

  1. I Notice there is no pretrained model on KITTI in https://share.phys.ethz.ch/~gsg/Predator/weights.zip, don't you want to make it public for forgot it ?

2.and there is no file : configs/train/kitti.yaml, and you didn't mention that training network in kitti dataset, only mentioned evaluating Predator on KITTI test set in README.md, So you have not make the training code/config files on kitti dataset public ?

@ShengyuH
Copy link
Member

ShengyuH commented Jul 8, 2021

hi,

Thanks for your interest. To answer your question:

  1. I will make it public
  2. I will provide the config file

Please see: #15 (comment), and overlappredator/OverlapPredator.Mink#3. I am busy with other projects BUT will update them ASAP.

best,
Shengyu

@ShengyuH ShengyuH self-assigned this Jul 8, 2021
@cgbcgb
Copy link
Author

cgbcgb commented Jul 9, 2021

OK, thanks a lot.

@ShengyuH
Copy link
Member

ShengyuH commented Aug 1, 2021

hi,

  1. I have updated KITTI pretrained models
  2. For training, I use the curriculum training strategy. Specifically, I start with max_points in circle loss being 512, then increase it to 1024 and 1536, this helps learn sharp features in the end.

Best,
Shengyu

@ShengyuH ShengyuH closed this as completed Aug 1, 2021
@cgbcgb
Copy link
Author

cgbcgb commented Aug 16, 2021

hi,

  1. I have updated KITTI pretrained models
  2. For training, I use the curriculum training strategy. Specifically, I start with max_points in circle loss being 512, then increase it to 1024 and 1536, this helps learn sharp features in the end.

Best,
Shengyu

Thank you : )

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