Tianxiaomo / pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4
Apache License 2.0
4.46k stars 1.49k forks source link

UnpicklingError: invalid load key, '\x00'. #256

Open Juuustin opened 3 years ago

Juuustin commented 3 years ago

There is another error when I run on my own data: Traceback (most recent call last): File "train.py", line 616, in model = Yolov4(cfg.pretrained, n_classes=cfg.classes) File "D:\study\Dinosaour\pytorch-YOLOv4\models.py", line 426, in init pretrained_dict = torch.load(yolov4conv137weight) File "C:\Users\onthe\Anaconda3\lib\site-packages\torch\serialization.py", line 368, in load return _load(f, map_location, pickle_module) File "C:\Users\onthe\Anaconda3\lib\site-packages\torch\serialization.py", line 532, in _load magic_number = pickle_module.load(f) _pickle.UnpicklingError: invalid load key, '\x00'. Any suggestions?

ghost commented 3 years ago

I changed the filters, as mentioned in https://github.com/Tianxiaomo/pytorch-YOLOv4/issues/138#issuecomment-721116468.

DeviAyyagari commented 2 years ago

Have you been able to resolve this issue? I am seeing the same issue "_pickle.UnpicklingError: invalid load key, '\x00'." and would appreciate your help. Thank you!