VAD
VAD copied to clipboard
hustvl
[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Hi, dear authors, when i evaluate VAD following official steps and run forward infer, sometimes BEVFormerEncoder's output is tensor with NAN which occurs randomly. Soon i found that the output...
Hello, After I did this [response,](https://github.com/hustvl/VAD/issues/29#issuecomment-1778550912) I ran the visualization command. However, the visualization did not work correctly. ``` (vad) user1@Dev-VAD1:~/VAD$ python tools/analysis_tools/visualization.py --result-path ./test/VAD_tiny_stage_2/Sat_Oct_28_02_13_15_2023/pts_bbox/results_nusc.pkl --save-path ./save/visualization/results4 ====== Loading NuScenes...
I find the comannd is generated by ego future position，but I can't find where is the high-command used in model。I find cmd is encoded as an embedding and concated with...
Hi, thanks for your great work and open-source code! I've met some problems when I try to reproduce the results with pre-trained weights, and I would love some advice and...
Hello, I have executed the following commands for training purposes. `python -m torch.distributed.run --nproc_per_node=1 --master_port=2333 tools/train.py rojects/configs/VAD/VAD_tiny_stage_1.py --launcher pytorch --deterministic --work-dir ./outputs` Given that I have access to only one...
Hello, I hope this finds you well. I've been facing some challenges in successfully verifying the VAD, and I kindly seek your advice. I've followed the installation steps outlined in...
I had downloaded the pretrained weights. I tried to run the visualization code: ```bash python tools/analysis_tools/visualization.py --result-path test/VAD_base_stage_2/Fri_Aug__4_10_18_26_2023/pts_bbox/results_nusc.pkl --save-path work/vis_results ``` It gave some warning like this one: ```bash /mnt/10t/yantao/adev/p00/VAD/projects/mmdet3d_plugin/core/bbox/structures/nuscenes_box.py:262:...
Hi, I have trained two models (stage 1 and stage 2) according to your instruction. However, when I run this command `CUDA_VISIBLE_DEVICES=0 python tools/test.py /home/guxunjia/Desktop/VAD/projects/configs/VAD/VAD_base_stage_2.py /home/guxunjia/Desktop/VAD/work_dirs/VAD_base_stage_2/epoch_12.pth --launcher none --eval bbox...
Hello, I am having trouble understanding the visualisation code. Could anyone please explain what exactly is going on here in simple terms? https://github.com/hustvl/VAD/blob/main/tools/analysis_tools/visualization.py#L800C1-L834C1 ```python plan_traj = np.concatenate(( plan_traj[:, [0]], plan_traj[:,...
