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

some questions about the average RTE based on KITTI #53

Closed
callmewanzi opened this issue Apr 24, 2024 · 1 comment
Closed

some questions about the average RTE based on KITTI #53

callmewanzi opened this issue Apr 24, 2024 · 1 comment

Comments

@callmewanzi
Copy link

callmewanzi commented Apr 24, 2024

Hi,thanks for your great work.But some problem came to me.
There is self.use_icp = True in the coding , is it just mean using ICP to refine register model ? which called "Ours+ICP"method in paper.
However,we use KITTI dataset's sequence08 to test the "Ours+ICP" model, and the average RTE is 0.15760340035163767(m) ? and if we set self.use_icp = False, the average RTE is 0.37215860772969533(m) based on sequence08 .
Thanks for your great job again!

@callmewanzi
Copy link
Author

Hi! I know why my answer was different from Tab3 now.Because in your file test_kitti.py ,there is succ_rate, rte, rre, avg_time, _ = stats[:i + 1].mean(0) so the logger will record all RTE and RRE including unsuccssed pairs.
Thanks!

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

1 participant