GodMan
GodMan
In the code [here](https://github.com/hustvl/MapTR/blob/e03f097abef19e1ba3fed5f471a8d80fbfa0a064/projects/mmdet3d_plugin/datasets/nuscenes_offlinemap_dataset.py#L77) , it announced using LIDAR coordinates, but LIDAR coordinates x is front, see bellow figure, so if we specific (bev_h, bev_w) = (200, 100), the point_cloud_range...
Following next fig, the green data show there are same coords and cates but different id, why? How to predict this result using network? 