UniAD icon indicating copy to clipboard operation
UniAD copied to clipboard

[CVPR'23 Best Paper Award] Planning-oriented Autonomous Driving

Results 75 UniAD issues
Sort by recently updated
recently updated
newest added

Given a video, does UniAD support to generate a demo video with tracked objects? What is the entry script to run UniAd models on a single video or image without...

Hi, As mentioned [here](https://github.com/OpenDriveLab/UniAD/issues/29#issuecomment-1717594344) you are not using the same definition of the L2 metric as other works (e.g., [VAD](https://github.com/hustvl/VAD) or [ST-P3](https://github.com/OpenDriveLab/ST-P3)). However, you present UniADs numbers using your new...

enhancement

As described in #166, there is a discrepancy between how planning metrics (L2 and collision rate) are computed in this repo vs previous works, such as [VAD](https://github.com/hustvl/VAD) and [ST-P3](https://github.com/OpenDriveLab/ST-P3). However,...

Hi there, I am trying to run UniAD on AGX Orin platform. uname -a `Linux nvidia-desktop 5.10.120-tegra #4 SMP PREEMPT aarch64 aarch64 aarch64 GNU/Linux` nvcc -v ``` nvcc: NVIDIA (R)...

I tried using torch.onnx.export But it doesn't work Even if torch.onnx.export is executed successfully, onnx will not be saved. And sometimes it succeeds and sometimes it doesn't very strange

使用V1.0-mini数据集运行uniad_dist_eval.sh报错如下: File "./tools/test.py", line 261, in main() File "./tools/test.py", line 231, in main outputs = custom_multi_gpu_test(model, data_loader, args.tmpdir, File "/home/zzz/Downloads/UniAD-1.0.1/projects/mmdet3d_plugin/uniad/apis/test.py", line 88, in custom_multi_gpu_test for i, data in enumerate(data_loader): File...

Hi ! Thanks for your great work. After reading your paper, I was interested in the performance of UniAD. And I used nvidia Nsight System to profile the model and...

Facts: 1) According to the paper, the performance of UniAD in comparison to prior state-of-the-arts was tested on the nuScenes validation set. 2) According to the training log in release...

Hello team: Will C++ inference code be provided in the future? Or are there any similar plans or reference cases?