Test inference of model on cpu and python3

[MetaDev]

I would like to test the trained model in python 3 and on cpu. Right now I'm having issues with loading the model.

Traceback (most recent call last): File "demo.py", line 31, in main() File "demo.py", line 13, in main model = torch.load(opt.loadModel).cuda() File "/home/hdbondt/miniconda3/lib/python3.6/site-packages/torch/serialization.py", line 231, in load return _load(f, map_location, pickle_module) File "/home/hdbondt/miniconda3/lib/python3.6/site-packages/torch/serialization.py", line 379, in _load result = unpickler.load() UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 875: ordinal not in range(128)

Is there by any chance a trained version compatible with python3?

[xingyizhou]

Sorry I don't have it.

[tom1994]

@MetaDev I have the "Stage1" model file which has been trained in Python3 model_60.pth

[xingyizhou]

Thanks @tom1994 !