search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

KeyError: 'state_dict' when running inference.py #10

Closed ZhiqiJiang closed 5 years ago

ZhiqiJiang commented 5 years ago

Traceback (most recent call last): File "inference.py", line 77, in main() File "inference.py", line 32, in main model.load_state_dict(checkpoint['state_dict']) KeyError: 'state_dict'

wave-transmitter commented 5 years ago

I met the same issue, can this be solved somehow? As far as I understand from issue #8 , one should train the model again and then load provided model's weights. Not very handy to be honest.

Kind of new in pytorch, so please let me know if I get this wrong.