VAD
VAD copied to clipboard
[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Hi @outsidercsy , We wanted to understand the contribution of different modules in VAD. For the same, in the config `VAD_base_e2e.py`, we updated the `loss-weight = 0.0` for all losses...
Hi @outsidercsy , Thanks for great work. I had a question on Planning metrics. What is the difference between `Obj_collision` and `Obj_box_collision` ? Can you help us with the intuition...
Hello, when I was testing the dataset, although I successfully obtained some test results,  I also encountered these errors in the follow-up, it seems that the code...
May I ask if this article is not a purely visual input? Why is there an error about missing LIDAR files when evaluating a given model? 
```CUDA_VISIBLE_DEVICES=0 python tools/test.py projects/configs/VAD/VAD_base.py /path/to/ckpt.pth --launcher none --eval bbox --tmpdir tmp``` ``` Traceback (most recent call last): File "tools/test.py", line 22, in from mmdet3d.apis import single_gpu_test File "/home/cthalia/.local/lib/python3.8/site-packages/mmdet3d/__init__.py", line 21,...
when I run the test.py,I encountered an error: File "/media/lab1214/home/lab1214/huangtingyu/VAD/tools/test.py", line 301, in main() File "/media/lab1214/home/lab1214/huangtingyu/VAD/tools/test.py", line 281, in main print(dataset.evaluate(outputs['bbox_results'], **eval_kwargs)) File "/media/lab1214/home/lab1214/huangtingyu/VAD/projects/mmdet3d_plugin/datasets/nuscenes_vad_dataset.py", line 1786, in evaluate result_dict['ADE_'+cls] =...
Hi, Thanks for your great work and effort for releasing the code. When i tried to reproduce the results as the paper said, i had the following trouble and hard...
Hi,thanks for sharing this great work! I'm wondering why Nuscenes open loop eval is not conducted in VAD v2 as other papers do?
 I have changed the img_norm_cfg in VAD_base_stage_2.py, and download the VAD_base.pth offered in your page. Then, I use the test command: CUDA_VISIBLE_DEVICES=0 python tools/test.py projects/configs/VAD/VAD_base_stage_2.py ./ckpts/VAD_base.pth --launcher none --eval...
Hi there, Thank you so much for your outstanding work, I was tring to build your code and understanding your work, I got two questions want to ask, I really...