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

A potential bug of points_in_boxes_gpu #289

Closed
caiqi opened this issue Jan 28, 2021 · 2 comments
Closed

A potential bug of points_in_boxes_gpu #289

caiqi opened this issue Jan 28, 2021 · 2 comments
Assignees
@xiliu8006

Comments

@caiqi
Copy link

caiqi commented Jan 28, 2021

https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/ops/roiaware_pool3d/points_in_boxes.py#L6 will not check the dim of points. For example, points of shape [B, C, 4] will not raise an error but the returned results are wrong. It would be better to assert the dim of points to 3. The commonly used Kitti dataset has 4 dims and will get wrong outputs when directly used the raw points.
@Tai-Wang
Copy link
Member

Tai-Wang commented Feb 2, 2021

Thanks for your information. We will add assertion reminder with a PR ASAP.

This was referenced Mar 11, 2021
Closed
Closed
@xiliu8006
Copy link
Contributor

Thanks for your information. PR #357 fixed this issue.

tpoisonooo pushed a commit to tpoisonooo/mmdetection3d that referenced this issue Sep 5, 2022
@SingleZombie
[Fix]: Fix rewriter conflict when processing derived class (open-mmla…
78b37bb 
…b#289)

* Fix rewriter

* lint

* rename function and update docstring

* use is class

* Update docstring
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@xiliu8006 xiliu8006

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@caiqi @Tai-Wang @xiliu8006