Hao Shao

Hi! Thank you for your attention to our project! I have attached our previous latency analysis. The experiments were conducted on a 3090 platform. With 2 A800 GPUs and a...

Hi! Sorry for the late reply, I have been very busy recently. Thanks for your kind help and I will update the related links.

Hi, 0.9.10.1 is the version of the Carla simulator, and 0.9.15 is the Carla Python API version. They are not the same. Best regards.

Hi! We haven't tested LMDrive on the other benchmarks. Our framework only tasks as input the instruction based on natural language. It's harder compared with other frameworks that can directly...

Hi! I have attached the log file for your reference. [long_vicuna2_with_notice_t1.json](https://github.com/opendilab/LMDrive/files/14138457/long_v2_w_notice_t1.json) Could you run it with more times? the variance of the performance scores is large. Also, you can check...

Hi! Sorry for the late reply, I have been very busy recently. To find proper waypoints in the Carla map, you can refer to https://github.com/opendilab/LMDrive/issues/19

Hi! Sorry for the late reply. Maybe you can check the disk speed? It will significantly affect the training efficiency. I recommend moving the training data to the SSD.

你好， measurements文件中的x/y和gps_x/gps_y 都是直接来自于carla模拟器，这两对坐标值之间可以通过简单变换得到。 关于生成bev map图时，x,y方向的坐标系可以参考 ：https://github.com/opendilab/LMDrive/blob/c335417de391cb964b437cbbe29455cf59414125/vision_encoder/timm/data/heatmap_utils.py#L74

Hi! Sorry for the late reply, I have been very busy recently. It looks that the Carla simulator didn't start normally and the agent cannot connect the server. Maybe you...

Hi! Sorry for the late reply. I've been very busy recently. @lion-zhang Could you try use_notice = False? @zacz08 What's your reproduced results? If they are slightly lower than those...