VAD
VAD copied to clipboard
hustvl
[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
由于数据集的不同，我的数据集的真值头指向为。  而nuscenes  请问一下我需要在create data的时候以及vad_head的forward的时候修改什么。可以麻烦指导一下嘛，谢谢了。
Hi authors, really appreciate for your work and sharing. I'm trying to run your base model with pre-trained parameters, and now I can run the evaluation with test.py file. I...
I would like to ask if you can provide the training curve. Why is the loss_plan_dir obtained after my training a curve of the upper body?
Hi, In your paper you basically say that the planning head is giving a driving command as input, if I'm not mistaken. These commands include "turn right", "turn left", and...
Hi, I noticed that there is no definition for v116ADTR (which is referred to in VADv2_config_voca4096.py), although there is one for v116ADTR_Head. Are you planning on releasing the full code...
when i run : python tools/data_converter/vad_nuscenes_converter.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag vad_nuscenes --version v1.0-mini --canbus ./data run scueess when run: CUDA_VISIBLE_DEVICES=0 python tools/test.py projects/configs/VAD/VAD_tiny_e2e.py /home/wxl/VAD/ckpts/VAD_tiny.pth --launcher none --eval bbox...
Thank you so much for your amazing work! I was trying to run the new released VADv2, but the mmdet3d_plugin.PIPP dependencies in the VADv2_head.py file are missing. Could you please...
Thank you for sharing your great work. I notice that VDA-v2 is just released but only config and model code. Do you have plan to fully release VDA-v2 such as...
Thank you very much for the valuable work of your team, I have completed the validation on the validation set using the pre-trained model.But when I use the following command,...
I modified the code #68 `img_norm_cfg = dict( mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)` and Completed the test`CUDA_VISIBLE_DEVICES=0 python tools/test.py projects/configs/VAD/VAD_tiny_e2e.py ckpts/VAD_tiny.pth --launcher none --eval bbox --tmpdir tmp` But...
