Hao Shao

Hi! > After running the (2) Data generation option. Is the data generation completed? Took less than a minute to generate, is that all? You need to delete the results/sample_result.json....

Hi! You may check this file: https://github.com/opendilab/InterFuser/blob/main/data_collection/base_script.sh#L17 If it is correct, you can check the term `TEAM_AGENT` in the sub-bash file o data_collection/batch_run/run_route_routes_town01_long.sh. Here we only use the auto-poilt agent...

Hi! Could you provide more information about your setting and why did you need to run "python scenario_runner.py"? I'm not familiar with this entry script. The two problems look like...

Hi! I'm very sorry that I cannot solve your problem. The issue is not from the Interfuser itself and I have never used scenario_runner.py to evaluate the agent before. However,...

Hi! You need to move the saved checkpoint to the path `leaderboard/team_code/interfuser.pth.tar`

I think you should modify the Carla simulator to support this feature:) The code may just need a little modification.

Hi! You can try to modify this function: https://github.com/opendilab/LMDrive/blob/43fc2e9a914623fd6eec954a94aeca2d3966e3db/leaderboard/leaderboard/leaderboard_evaluator.py#L169 , which is used to spawn the ego vehicle.

应该是没有用的，请发更多的log来帮助更好地解决的这个问题

效果略差一些，你可以试试

您好，请问能够描述更多细节吗，你是指的在离线数据集上进行测试吗？