Run evaluate error (AssertionError)

[linever]

When I running evaluate.sh, i meet assertion error. The errors are follows. Please help me, very thank you!

—— —— —— > An error occurred during Hydra's exception formatting: AssertionError() Traceback (most recent call last): File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/_internal/utils.py", line 252, in run_and_report assert mdl is not None AssertionError

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "evaluate.py", line 246, in main() File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/main.py", line 48, in decorated_main _run_hydra( File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/_internal/utils.py", line 377, in _run_hydra run_and_report( File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/_internal/utils.py", line 294, in run_and_report raise ex File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/_internal/utils.py", line 211, in run_and_report return func() File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/_internal/utils.py", line 378, in lambda: hydra.run( File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/internal/hydra.py", line 111, in run = ret.return_value File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/core/utils.py", line 233, in return_value raise self._return_value File "/home/lwd/programs/anaconda3/envs/mile/lib/python3.8/site-packages/hydra/core/utils.py", line 160, in run_job ret.return_value = task_function(task_cfg) File "evaluate.py", line 171, in main list_render, ep_stat_dict, ep_event_dict, timestamp = run_single( File "evaluate.py", line 35, in run_single obs = env.reset() File "/home/lwd/codes/mile/carla_gym/carla_multi_agent_env.py", line 78, in reset ev_spawn_locations = self._ev_handler.reset(self._task['ego_vehicles']) File "/home/lwd/codes/mile/carla_gym/core/task_actor/ego_vehicle/ego_vehicle_handler.py", line 39, in reset blueprint = np.random.choice(self._world.get_blueprint_library().filter(bp_filter)) File "mtrand.pyx", line 915, in numpy.random.mtrand.RandomState.choice ValueError: 'a' cannot be empty unless no samples are taken

[anthonyhu]

Hello,

Could you share the exact bash command you have ran to get this error?

[linever]

Thank you very much! The bash command is -> bash run/evaluate.sh ~/carla_0913/CarlaUE4.sh /home/lwd/codes/mile/checkpoints/mile.ckpt 2000 My server can not connect to web, so i choose wandb 3 while running.

[anthonyhu]

Are you using CARLA 0.9.13? This code has only been tested on CARLA 0.9.11. Could you retry by downloading CARLA 0.9.11 ?

[linever]

The advice may help me. I will try it. Thank you again!