Use this code on a mac

[elinxie]

Hello,

I was wondering what the correct command would be if I wanted to run your script on a mac?

I tried the default:
python yolo_slowfast.py --input 0
and got

Adding AutoShape... 
Traceback (most recent call last):
  File "yolo_slowfast.py", line 201, in <module>
    main(config)
  File "yolo_slowfast.py", line 120, in main
    model = torch.hub.load('ultralytics/yolov5', 'yolov5l6').to(device)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 673, in to
    return self._apply(convert)
  File "/Users/elinxie/.cache/torch/hub/ultralytics_yolov5_master/models/common.py", line 648, in _apply
    self = super()._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 387, in _apply
    module._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 387, in _apply
    module._apply(fn)
  File "/Users/elinxie/.cache/torch/hub/ultralytics_yolov5_master/models/yolo.py", line 155, in _apply
    self = super()._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 387, in _apply
    module._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 387, in _apply
    module._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 387, in _apply
    module._apply(fn)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 409, in _apply
    param_applied = fn(param)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/nn/modules/module.py", line 671, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
  File "/Users/elinxie/anaconda3/envs/yolo_slowfast/lib/python3.7/site-packages/torch/cuda/__init__.py", line 164, in _lazy_init
    raise AssertionError("Torch not compiled with CUDA enabled")

I tried python yolo_slowfast.py --input 0 --device cpu and got

processing...
[W NNPACK.cpp:80] Could not initialize NNPACK! Reason: Unsupported hardware.
processing 0th second clips

What device should I use?