Run Inference with pre-trained model failed
axbaldanza opened this issue · comments
When I try to run inference on my images with run_inference.py
and a pre-trained model load in the google drive mentionned for it : https://drive.google.com/drive/folders/0B5EC7HMbyk3CbjFPb0RuODI3NmM I have this error :
Traceback (most recent call last):
File "run_inference.py", line 118, in <module>
main()
File "/home/abaldanza/anaconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "run_inference.py", line 80, in main
network_data = torch.load(args.pretrained)
File "/home/abaldanza/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 593, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/abaldanza/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 762, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '\x04'.
As if the pre-trained model can't be used i think ...
If anyone knows why or how to fix it (if there is anything to do with de model) i should be in