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

No such file or directory: 'sensor_pretrain.pth.tar.r50' #59

Closed pastapeter closed 3 weeks ago

pastapeter commented 3 weeks ago

I thought the pretrained weight would be on internet and download it by api. but error message says about no file sensor_pretrained.pth.tar.r50, is there any solution?

`` ========= Preparing RouteScenario_3 (repetition 0) =========

Setting up the agent build model...

Could not set up the required agent:

[Errno 2] No such file or directory: 'sensor_pretrain.pth.tar.r50'

Traceback (most recent call last): File "leaderboard/leaderboard/leaderboard_evaluator.py", line 270, in _load_and_run_scenario self.agent_instance = getattr(self.module_agent, agent_class_name)(args.agent_config) File "/home/dohyun/LMDrive/leaderboard/leaderboard/autoagents/autonomous_agent.py", line 45, in init self.setup(path_to_conf_file) File "/home/dohyun/LMDrive/leaderboard/team_code/lmdriver_agent.py", line 205, in setup model = model_cls(preception_model=self.config.preception_model, File "/home/dohyun/LMDrive/LAVIS/lavis/models/drive_models/drive.py", line 86, in init pretrain_weights = torch.load(preception_model_ckpt, map_location=torch.device('cpu'))['state_dict'] File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/site-packages/torch/serialization.py", line 791, in load with _open_file_like(f, 'rb') as opened_file: File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/site-packages/torch/serialization.py", line 271, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/dohyun/miniconda3/envs/lmdrive/lib/python3.8/site-packages/torch/serialization.py", line 252, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: 'sensor_pretrain.pth.tar.r50'