[Bug] using create_data.py convert kitti_tiny_data to mmdetection support data, but when using browse_dataset.py vis data, find 3dbox has bias in 2D image, there is no problem on lidar

Prerequisite

[X] I have searched Issues and Discussions but cannot get the expected help.
[X] I have read the FAQ documentation but cannot get the expected help.
[x] The bug has not been fixed in the latest version (dev-1.x) or latest version (dev-1.0).

Task

I'm using the official example scripts/configs for the officially supported tasks/models/datasets.

Branch

main branch https://github.com/open-mmlab/mmdetection3d

Environment

None

Reproduces the problem - code sample

python create_data.py python tools/misc/browse_dataset.py configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py --task multi-modality_det --output-dir vis_data --show-interval 1

Reproduces the problem - command or script

python create_data.py python tools/misc/browse_dataset.py configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py --task multi-modality_det --output-dir vis_data --show-interval 1

Reproduces the problem - error message

Additional information

correct result

I using test.py get the metric very low. using mvxnet official weight, dataset is kitti tiny(https://onedrive.live.com/download?resid=CB1C03091115D5EA%21119&authkey=!AO57a1ru2Tz2jHQ) command: python tools/test.py mmdetection3d/configs/mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py mmdetection3d/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class-8963258a.pth

---------- AP11 Results ------------

Pedestrian AP11@0.50, 0.50, 0.50: bbox AP11:9.0909, 9.0909, 9.0909 bev AP11:9.0909, 9.0909, 9.0909 3d AP11:9.0909, 9.0909, 9.0909 aos AP11:0.06, 0.06, 0.06 Pedestrian AP11@0.50, 0.25, 0.25: bbox AP11:9.0909, 9.0909, 9.0909 bev AP11:9.0909, 9.0909, 9.0909 3d AP11:9.0909, 9.0909, 9.0909 aos AP11:0.06, 0.06, 0.06 Cyclist AP11@0.50, 0.50, 0.50: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 aos AP11:0.00, 0.00, 0.00 Cyclist AP11@0.50, 0.25, 0.25: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 aos AP11:0.00, 0.00, 0.00 Car AP11@0.70, 0.70, 0.70: bbox AP11:9.0909, 9.0909, 9.0909 bev AP11:9.0909, 9.0909, 9.0909 3d AP11:9.0909, 9.0909, 9.0909 aos AP11:9.09, 9.09, 9.09 Car AP11@0.70, 0.50, 0.50: bbox AP11:9.0909, 9.0909, 9.0909 bev AP11:9.0909, 14.1414, 14.1414 3d AP11:9.0909, 14.1414, 14.1414 aos AP11:9.09, 9.09, 9.09

Overall AP11@easy, moderate, hard: bbox AP11:6.0606, 6.0606, 6.0606 bev AP11:6.0606, 6.0606, 6.0606 3d AP11:6.0606, 6.0606, 6.0606 aos AP11:3.05, 3.05, 3.05

----------- AP40 Results ------------

Pedestrian AP40@0.50, 0.50, 0.50: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 aos AP40:0.00, 0.00, 0.00 Pedestrian AP40@0.50, 0.25, 0.25: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 aos AP40:0.00, 0.00, 0.00 Cyclist AP40@0.50, 0.50, 0.50: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 aos AP40:0.00, 0.00, 0.00 Cyclist AP40@0.50, 0.25, 0.25: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 aos AP40:0.00, 0.00, 0.00 Car AP40@0.70, 0.70, 0.70: bbox AP40:4.0000, 6.4286, 6.4286 bev AP40:1.6667, 6.5000, 6.5000 3d AP40:1.6667, 4.3750, 4.3750 aos AP40:4.00, 6.42, 6.42 Car AP40@0.70, 0.50, 0.50: bbox AP40:4.0000, 6.4286, 6.4286 bev AP40:2.9167, 7.8889, 7.8889 3d AP40:2.9167, 7.8889, 7.8889 aos AP40:4.00, 6.42, 6.42

Overall AP40@easy, moderate, hard: bbox AP40:1.3333, 2.1429, 2.1429 bev AP40:0.5556, 2.1667, 2.1667 3d AP40:0.5556, 1.4583, 1.4583 aos AP40:1.33, 2.14, 2.14

open-mmlab / mmdetection3d