fix(bev_pool_cuda.cu): fixed bev_pool cuda .cu wrong cur_geom_feats address

[ZouJiu1]

Contribution

I fix a problem with wrong cur_geom_feats address in file of bev_pool_cuda.cu.

Problem

the reason is the wrong implement of file bev_pool_cuda.cu or mmdetection3d and another repo

Reproduce

To reproduce the wrong different result, you can follow the instruction of file README.md https://github.com/ZouJiu1/bevPool/blob/master/README.md

step 1

reproduce the problem

download the file bev_pool_cuda.cu

mv bev_pool/src/bev_pool_cuda.cu bev_pool/src/bev_pool_cuda_tmp.cu

git clone https://github.com/ZouJiu1/bevPool.git

cd bevPool

pip install -e .

cd bev_pool

python3 bev_pool.py

by checking or debuging or printing the variables like error, errorMean, www, tmp, tmp2 in file bev_pool.py, you can reproduce the problem

step 2

fix the problem

mv bev_pool/src/bev_pool_cuda_tmp.cu bev_pool/src/bev_pool_cuda.cu

cd bevPool

pip install -e .

cd bev_pool

python3 bev_pool.py

by checking variables in file bev_pool.py, you will find the problem is fixed.

Environment:

Ubuntu22.04
Python 3.10.12
torch 2.2.2+cu118
torchvision 0.17.2+cu118
mmcv 2.1.0
mmengine 0.10.7
mmdet 3.3.0
mmdet3d 1.4.0
cuda 11.8
cudnn 8.9.7
gcc g++ 11.4.0

others:

hustvl/MapTR#212
#12491
open-mmlab/mmdetection3d#3143
weiyangdaren/Fisheye3DOD#4
hustvl/VMA#21

Motivation

fix some problem.

Modification

fixed wrong cur_geom_feats address in file of bev_pool_cuda.cu

Description

As the title.
The PR forgot to add that to the list.

Related links

Parent Issue:

• Link

How was this PR tested?

Psim

Notes for reviewers

None.

Interface changes

None.

Effects on system behavior

None.

[github-actions]

Thank you for contributing to the Autoware project!

🚧 If your pull request is in progress, switch it to draft mode.

Please ensure:

• You've checked our contribution guidelines.
• Your PR follows our pull request guidelines.
• All required CI checks pass before marking the PR ready for review.

[KSeangTan]

Hi @ZouJiu1

Thanks for the fix, would you mind providing more details about the fix? For example, do you have any examples that can validate the output feature map in your bev_pool is valid?

Sth similar to this PR to check the projection of bev features:
#12206