mattyt03 / baithoven Goto Github PK

I ve got error during try to run rnn.py file as

`[ValueError Traceback (most recent call last)
in
1 if name == 'main':
----> 2 train_network()

in train_network()
5 # get amount of pitch names
6 n_vocab = len(set(notes))
----> 7 network_input, network_output = prepare_sequences(notes, n_vocab)
8 model = create_network(network_input, n_vocab)
9 train(model, network_input, network_output)

in prepare_sequences(notes, n_vocab)
22 # normalize input
23 network_input = network_input / float(n_vocab)
---> 24 network_output = np_utils.to_categorical(network_output)
25 return (network_input, network_output)

~/python-envs/tfenv/lib/python3.8/site-packages/tensorflow/python/keras/utils/np_utils.py in to_categorical(y, num_classes, dtype)
73 y = y.ravel()
74 if not num_classes:
---> 75 num_classes = np.max(y) + 1
76 n = y.shape[0]
77 categorical = np.zeros((n, num_classes), dtype=dtype)

<array_function internals> in amax(*args, **kwargs)

~/python-envs/tfenv/lib/python3.8/site-packages/numpy/core/fromnumeric.py in amax(a, axis, out, keepdims, initial, where)
2665 5
2666 """
-> 2667 return _wrapreduction(a, np.maximum, 'max', axis, None, out,
2668 keepdims=keepdims, initial=initial, where=where)
2669

~/python-envs/tfenv/lib/python3.8/site-packages/numpy/core/fromnumeric.py in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs)
88 return reduction(axis=axis, out=out, **passkwargs)
89
---> 90 return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
91
92

ValueError: zero-size array to reduction operation maximum which has no identity
]`

How do I pass over this error