TypeError: umx() got an unexpected keyword argument 'target'

[jiseong1209]

Hello, If you run this code:

import torch
eps = np.finfo(np.float).eps

N = track.audio.shape[0] # remember number of samples for future use
X = stft(track.audio.T, nperseg=4096, noverlap=3072)[-1]
(I, F, T) = X.shape

P = {}
model = eps

for name, source in track.sources.items():
unmix = torch.hub.load('sigsep/open-unmix-pytorch', model='umx', target=name)
P[name] = unmix(torch.tensor(track.audio.T[None, ...]).float()).detach().numpy()[:, 0, ...].transpose(1, 2, 0)
model += P[name]

The following error occurs:

TypeError Traceback (most recent call last)
in
15 for name, source in track.sources.items():
16 # compute spectrogram of target source:
---> 17 unmix = torch.hub.load('sigsep/open-unmix-pytorch', model='umx', target=name)
18 P[name] = unmix(torch.tensor(track.audio.T[None, ...]).float()).detach().numpy()[:, 0, ...].transpose(1, 2, 0)
19 # P[name] = np.abs(stft(source.audio.T, nperseg=4096, noverlap=3072)[-1])

1 frames
/usr/local/lib/python3.8/dist-packages/torch/hub.py in load(repo_or_dir, model, source, trust_repo, force_reload, verbose, skip_validation, *args, **kwargs)
540 verbose=verbose, skip_validation=skip_validation)
541
--> 542 model = _load_local(repo_or_dir, model, *args, **kwargs)
543 return model
544

/usr/local/lib/python3.8/dist-packages/torch/hub.py in _load_local(hubconf_dir, model, *args, **kwargs)
570
571 entry = _load_entry_from_hubconf(hub_module, model)
--> 572 model = entry(*args, **kwargs)
573
574 sys.path.remove(hubconf_dir)

TypeError: umx() got an unexpected keyword argument 'target'

How can we solve this problem?