search

opendilab / LMDrive

[CVPR 2024] LMDrive: Closed-Loop End-to-End Driving with Large Language Models
Apache License 2.0
526 stars 48 forks source link

Segmentation fault when using server ubuntu, remote desktop #58

Closed pastapeter closed 3 weeks ago

pastapeter commented 3 weeks ago

Hi, I'm facing issue when starting, i got segmentation Fault when Setting up the Agent.

========= Preparing RouteScenario_3 (repetition 0) =========
> Setting up the agent
Fatal Python error: Segmentation fault

Thread 0x00007ffbd8f67700 (most recent call first):
  File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/threading.py", line 306 in wait
  File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/threading.py", line 558 in wait
  File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/threading.py", line 1252 in run
  File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/threading.py", line 932 in _bootstrap_inner
  File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/threading.py", line 890 in _bootstrap

Current thread 0x00007ffbf9be2280 (most recent call first):
  File "/home/dohyun/LMDrive/leaderboard/team_code/lmdriver_agent.py", line 80 in __init__
  File "/home/dohyun/LMDrive/leaderboard/team_code/lmdriver_agent.py", line 175 in setup
  File "/home/dohyun/LMDrive/leaderboard/leaderboard/autoagents/autonomous_agent.py", line 45 in __init__
  File "leaderboard/leaderboard/leaderboard_evaluator.py", line 276 in _load_and_run_scenario
  File "leaderboard/leaderboard/leaderboard_evaluator.py", line 422 in run
  File "leaderboard/leaderboard/leaderboard_evaluator.py", line 487 in main
  File "leaderboard/leaderboard/leaderboard_evaluator.py", line 496 in <module>
./leaderboard/scripts/run_evaluation.sh: line 45: 295043 Segmentation fault      (core dumped) python3 -u ${LEADERBOARD_ROOT}/leaderboard/leaderboard_evaluator.py --scenarios=${SCENARIOS} --routes=${ROUTES} --repetitions=${REPETITIONS} --track=${CHALLENGE_TRACK_CODENAME} --checkpoint=${CHECKPOINT_ENDPOINT} --agent=${TEAM_AGENT} --agent-config=${TEAM_CONFIG} --debug=${DEBUG_CHALLENGE} --record=${RECORD_PATH} --resume=${RESUME} --port=${PORT} --trafficManagerPort=${TM_PORT}

How can i solve it? Carla library is 0.9.15

pastapeter commented 3 weeks ago

I just deleted the self._display in lmdrive_agent.py this issue has been solved