-
Notifications
You must be signed in to change notification settings - Fork 0
/
classificacao_musicas.py
237 lines (183 loc) · 7.05 KB
/
classificacao_musicas.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
# -*- coding: utf-8 -*-
"""classificacao_musicas.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1cbNIPL3Y-4paD2zCo7rR2myygFYn-Q0k
"""
from google.colab import drive
drive.mount('/content/drive')
import warnings
warnings.filterwarnings("ignore", category = FutureWarning)
import os
import keras
import h5py
import librosa
import itertools
import numpy as np
import matplotlib.pyplot as plt
from collections import OrderedDict
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dropout
from keras.layers import Flatten
import cv2
from google.colab.patches import cv2_imshow
from keras.layers import BatchNormalization
def splitsongs(X, y, window = 0.1, overlap = 0.5):
# Empty lists to hold our results
temp_X = []
temp_y = []
# Get the input song array size
xshape = X.shape[0]
chunk = int(xshape*window)
offset = int(chunk*(1.-overlap))
# Split the song and create new ones on windows
spsong = [X[i:i+chunk] for i in range(0, xshape - chunk + offset, offset)]
for s in spsong:
temp_X.append(s)
temp_y.append(y)
return np.array(temp_X), np.array(temp_y)
def to_melspectrogram(songs, n_fft = 1024, hop_length = 512):
# Função para transformar arquivos de audio em mel spectogramas
melspec = lambda x: librosa.feature.melspectrogram(x, n_fft = n_fft,
hop_length = hop_length)[:,:,np.newaxis]
tsongs = map(melspec, songs)
return np.array(list(tsongs))
def read_data(src_dir, genres, song_samples, spec_format, debug = True):
# Empty array of dicts with the processed features from all files
arr_specs = []
arr_genres = []
# Read files from the folders
for x,_ in genres.items():
folder = src_dir + x
print (folder)
for root, subdirs, files in os.walk(folder):
for file in files:
# Read the audio file
file_name = folder + "/" + file
signal, sr = librosa.load(file_name)
signal = signal[:song_samples]
# Debug process
if debug:
print("Reading file: {}".format(file_name))
# Convert to dataset of spectograms/melspectograms
signals, y = splitsongs(signal, genres[x])
# Convert to "spec" representation
specs = spec_format(signals)
# Save files
arr_genres.extend(y)
arr_specs.extend(specs)
return np.array(arr_specs), np.array(arr_genres)
# Parameters
gtzan_dir = '/content/drive/My Drive/GTZAN/genres/'
song_samples = 660000
genres = {'metal': 0, 'disco': 1, 'classical': 2, 'hiphop': 3, 'jazz': 4,
'country': 5, 'pop': 6, 'blues': 7, 'reggae': 8, 'rock': 9}
# Read the data
X, y = read_data(gtzan_dir, genres, song_samples, to_melspectrogram, debug=False)
print(X.shape)
np.save('x_gtzan_npy.npy', X)
np.save('y_gtzan_npy.npy', y)
y = to_categorical(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42, stratify = y)
print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
values, count = np.unique(np.argmax(y_train, axis=1), return_counts=True)
plt.bar(values, count)
values, count = np.unique(np.argmax(y_test, axis=1), return_counts=True)
plt.bar(values, count)
plt.show()
input_shape = X_train[0].shape
num_genres = 10
model = Sequential()
#implementação da concolução 2D
model.add(Conv2D(16, kernel_size=(3, 3), strides=(1, 1),
activation='relu', input_shape=input_shape))
#implementação de MAxPooling para reduzir o tamanho da imagem
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
#implementação de DropOut
model.add(Dropout(0.2))
model.add(Conv2D(32, (3, 3), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3, 3), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(128, (3, 3), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3, 3), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4), strides=(4, 4)))
model.add(Dropout(0.2))
#Flatten para transformar a imagem em array
model.add(Flatten())
model.add(Dense(num_genres, activation='softmax'))
model.summary()
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adam(),
metrics=['accuracy'])
history = model.fit(X_train, y_train,
batch_size=32,
epochs=50,
verbose=1,
validation_data=(X_test, y_test))
score = model.evaluate(X_test, y_test, verbose=0)
print("val_loss = {:.3f} and val_acc = {:.3f}".format(score[0], score[1]))
plt.figure(figsize=(15,7))
plt.subplot(1,2,1)
plt.plot(hist.history['acc'], label='train')
plt.plot(hist.history['val_acc'], label='validation')
plt.title('Accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.subplot(1,2,2)
plt.plot(hist.history['loss'], label='train')
plt.plot(hist.history['val_loss'], label='validation')
plt.title('Loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.tight_layout()
plt.show()
def plot_confusion_matrix(cm, classes,
normalize=False,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
print("Normalized confusion matrix")
else:
print('Confusion matrix, without normalization')
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
fmt = '.2f' if normalize else 'd'
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, format(cm[i, j], fmt),
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
preds = np.argmax(model.predict(X_test), axis = 1)
y_orig = np.argmax(y_test, axis = 1)
cm = confusion_matrix(preds, y_orig)
print("Confusion Matrix:")
print(cm)
keys = OrderedDict(sorted(genres.items(), key=lambda t: t[1])).keys()
#plt.figure(figsize=(8,8))
plot_confusion_matrix(cm, keys, normalize=False)