rehg-lab / eye-contact-cnn Goto Github PK

Im trying to run this on an old macbook pro and keep running into this issue with cuda..
I have a GT 650M graphics card and according to CUDA's support page, it looks like it should run without issues.. but i've also heard before that most mac book pro's don't have a card that supports cuda and that pytorch therefore is installed by default without (for mac).. can you help me understand what to do ? is it my mac, should i upgrade to fix this? (link to cuda page: https://en.wikipedia.org/wiki/CUDA#GPUs_supported)

error code:

eye-contact-cnn % python3 demo.py --video /Users/jonasbjerg/noedit/input/test1.MP4
loading saved model weights
Traceback (most recent call last):
File "demo.py", line 184, in
run(args.video, args.face, args.model_weight, args.jitter, args.save_vis, args.display_off, args.save_text)
File "demo.py", line 101, in run
model = model_static(model_weight)
File "/Users/jonasbjerg/noedit/eye-contact-cnn/model.py", line 11, in model_static
snapshot = torch.load(pretrained)
File "/opt/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 "/opt/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 772, in _legacy_load
result = unpickler.load()
File "/opt/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 728, in persistent_load
deserialized_objects[root_key] = restore_location(obj, location)
File "/opt/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 175, in default_restore_location
result = fn(storage, location)
File "/opt/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 151, in _cuda_deserialize
device = validate_cuda_device(location)
File "/opt/anaconda3/lib/python3.8/site-packages/torch/serialization.py", line 135, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.