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.

[nEdAy]

python3 --version
Python 3.9.0

python u2net_portrait_test.py

Number of images:  8
...load U2NET---173.6 MB
Traceback (most recent call last):
  File "/Users/Kevin.SuTJ/Desktop/U^2 Net/u2net_portrait_test.py", line 117, in <module>
    main()
  File "/Users/Kevin.SuTJ/Desktop/U^2 Net/u2net_portrait_test.py", line 87, in main
    net.load_state_dict(torch.load(model_dir))
  File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 595, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 774, in _legacy_load
    result = unpickler.load()
  File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 730, in persistent_load
    deserialized_objects[root_key] = restore_location(obj, location)
  File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 175, in default_restore_location
    result = fn(storage, location)
  File "/usr/local/lib/python3.9/site-packages/torch/serialization.py", line 151, in _cuda_deserialize
    device = validate_cuda_device(location)
  File "/usr/local/lib/python3.9/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.

In the u2net_portrait_test.py i added , map_location=torch.device("cpu")

net.load_state_dict(torch.load(model_dir))

to

net.load_state_dict(torch.load(model_dir, map_location=torch.device("cpu")))

And then I'm doing fine.

[a-stankevich]

This is fixed in #3 and #133. But it looks like this repo has been abandoned by the owner :(

[nEdAy]

@a-stankevich thanks.