ifzhang / FairMOT

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
MIT License
3.96k stars 930 forks source link

EOFError: Ran out of input help me! #209

Open qifyin opened 3 years ago

qifyin commented 3 years ago

When I run the demo.py, I faced a problem: EOFError: Ran out of input . Please tell me what can i do. Traceback is as follows:

sudo python demo.py mot --load_model /home/qfy/FairMOT-master/models/all_dla34.pth --conf_thres 0.4

Fix size testing. training chunk_sizes: [6, 6] The output will be saved to /home/qfy/FairMOT-master/src/lib/../../exp/mot/default heads {'hm': 1, 'wh': 2, 'id': 512, 'reg': 2} 2020-08-04 14:26:25 [INFO]: Starting tracking... Lenth of the video: 1500 frames Creating model... Traceback (most recent call last): File "demo.py", line 40, in demo(opt) File "demo.py", line 30, in demo eval_seq(opt, dataloader, 'mot', result_filename, save_dir=frame_dir, show_image=False, frame_rate=frame_rate) File "/home/qfy/FairMOT-master/src/track.py", line 51, in eval_seq tracker = JDETracker(opt, frame_rate=frame_rate) File "/home/qfy/FairMOT-master/src/lib/tracker/multitracker.py", line 178, in init self.model = load_model(self.model, opt.load_model) File "/home/qfy/FairMOT-master/src/lib/models/model.py", line 31, in load_model checkpoint = torch.load(model_path, map_location=lambda storage, loc: storage) File "/home/qfy/.conda/envs/py37/lib/python3.7/site-packages/torch/serialization.py", line 386, in load return _load(f, map_location, pickle_module, pickle_load_args) File "/home/qfy/.conda/envs/py37/lib/python3.7/site-packages/torch/serialization.py", line 563, in _load magic_number = pickle_module.load(f, pickle_load_args) EOFError: Ran out of input

ifzhang commented 3 years ago

I think the all_dla34.pth model is not correctly downloaded. You can try download it again.