mac cuda cpu/gpu issue

[JonasIsLive]

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.

[amna-ai]

I am facing similar issue. I have changed the code to thid snapshot = torch.load(model_weight, map_location=torch.device('cpu')) but still getting the same error you got.

[amirulmsri]

the codes run perfectly with the example video you provided but failed with camera or video of my own (in .avi format), is there any explanation for this?

there is no error message, just for both camera and video there's huge delay and tend to crash.