Ошибка в работе нейронной сети Python для распознавания музыки с Keras и Librosa

Question

Недавно я попытался завершить эксперимент, в котором алгоритм нейронной сети идентифицирует композитора произведения классической музыки. Я. однако, основываясь на этом эксперименте на предыдущем проекте, в котором нейронная сеть создается с использованием системы Keras и анализирует соответствующие музыкальные произведения. Мой источник этой статьи:

https://medium.com/@navdeepsingh_2336/identifying-the-genre-of-a-song-with-neural-networks-851db89c42f0

После проведения различных тестов, где программа работала как ожидалось, я недавно столкнулся с другой ошибкой. Когда я попытался запустить программу, представленную в статье:

import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.utils.np_utils import to_categorical

def display_mfcc(song):
    y, _ = librosa.load(song)
    mfcc = librosa.feature.mfcc(y)

    plt.figure(figsize=(10, 4))
    librosa.display.specshow(mfcc, x_axis='time', y_axis='mel')
    plt.colorbar()
    plt.title(song)
    plt.tight_layout()
    plt.show()


def extract_features_song(f):
    y, _ = librosa.load(f)

    mfcc = librosa.feature.mfcc(y)
    mfcc /= np.amax(np.absolute(mfcc))

    return np.ndarray.flatten(mfcc)[:25000]

def generate_features_and_labels():
    all_features = []
    all_labels = []
     genres = ['blues', 'classical', 'country', 'disco', 'hiphop', 
     'jazz', 'metal', 'pop', 'reggae', 'rock']

    for genre in genres:
        sound_files = glob.glob('genres/'+genre+'/*.au')
    print('Processing %d songs in %s genre...' %   
    (len(sound_files), genre))
        for f in sound_files:
            features = extract_features_song(f)
            all_features.append(features)
            all_labels.append(genre)

    label_uniq_ids, label_row_ids = np.unique(all_labels, 
    return_inverse=True)
    label_row_ids = label_row_ids.astype(np.int32, copy=False)
    onehot_labels = to_categorical(label_row_ids,
    len(label_uniq_ids)) 
    return np.stack(all_features), onehot_labels



features, labels = generate_features_and_labels()

print(np.shape(features))
print(np.shape(labels))

training_split = 0.8

alldata = np.column_stack((features, labels))

np.random.shuffle(alldata)
splitidx = int(len(alldata) * training_split)
train, test = alldata[:splitidx,:], alldata[splitidx:,:]

print(np.shape(train))
print(np.shape(test))

train_input = test[:,:-10]
train_labels = train[:,-10]

test_input = test[:,:-10]
test_labels = test[:,-10]

print(np.shape(train_input))
print(np.shape(train_labels))

model = Sequential([
    Dense(100, input_dim=np.shape(train_input)[1]),
    Activation('relu'),
    Dense(10),
    Activation('softmax'),
    ])


model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
print(model.summary())

model.fit(train_input, train_labels, epochs=10, batch_size=32,
          validation_split=0.2)

loss, acc = model.evaluate(test_input, test_labels, batch_size=32)

print('Done!')
print('Loss: %.4f, accuracy: %.4f' % (loss, acc))

Python, наряду с этими ожидаемыми результатами:

Processing 100 songs in blues genre...
Processing 100 songs in classical genre...
Processing 100 songs in country genre...
Processing 100 songs in disco genre...
Processing 100 songs in hiphop genre...
Processing 100 songs in jazz genre...
Processing 100 songs in metal genre...
Processing 100 songs in pop genre...
Processing 100 songs in reggae genre...
Processing 100 songs in rock genre...
(1000, 25000)
(1000, 10)
(800, 25010)
(200, 25010)
(200, 25000)
(800,)
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 100)               2500100   
_________________________________________________________________
activation_1 (Activation)    (None, 100)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 10)                1010      
_________________________________________________________________
activation_2 (Activation)    (None, 10)                0         
=================================================================
Total params: 2,501,110
Trainable params: 2,501,110
Non-trainable params: 0
_________________________________________________________________

Дал сообщение об ошибке:

Traceback (most recent call last):
  File "/Users/surengrigorian/Documents/Stage1.py", line 88, in 
  <module>
    validation_split=0.2)
  File     "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 952, in fit
    batch_size=batch_size)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 789, in _standardize_user_data
    exception_prefix='target')
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training_utils.py", line 138, in standardize_input_data
    str(data_shape))
ValueError: Error when checking target: expected activation_2 to have shape (10,) but got array with shape (1,)

Answer 1

Вы сделали ошибку при разделении данных на этом этапе:

train_input = test[:,:-10] <<======
train_labels = train[:,-10] <<=====

test_input = test[:,:-10]
test_labels = test[:,-10]

Попробуй это:

train_input = train[:,:-10] <<======
train_labels = train[:,-10:] <<=====

test_input = test[:,:-10]
test_labels = test[:,-10:]