Xiaosong Jia
Xiaosong Jia
@wangmingcqu Thanks for your interestes. Note that the INTERACTION code is uncleaned and quite different from current codebase. You may write the dataloader by yourself. I I attach the prerpocess...
Hi neel04, thank you for your interests. The dataset is available at google drive and soon at BaiduYun.
Hi vaydingul, thanks for your feedback and interesting findings. We have not try weighted sampling for TCP. As for the epoch length and LR decay, we do not tune them...
Hi yixiao1, Since the code have been released, you could find out that we use both the 2D feature map and flattened one of ResNet34. No additional layers are used.
@byaman14 Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced....
@Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results open sourced....
> > @Wolfybox Hi, we are the authors of Bench2Drive and we would like to introduce that we have implemented VAD (non-official) in CARLA with code, checkpoints, and closed-loop results...
Hi, thanks for your interests. This codebase has encountered a major refactor and it is mixed with some implementations in our next work (accepted by ICCV 2023 and this time...