Tengo unos pocos miles de archivos de audio y quiero clasificarlos usando Keras y Theano. Hasta ahora, generé un espectrograma de 28x28 (más grande probablemente sea mejor, pero solo estoy tratando de que el algoritmo funcione en este punto) de cada archivo de audio y lea la imagen en una matriz. Así que al final obtengo esta matriz de imágenes grandes para alimentar a la red para la clasificación de imágenes.

En un tutorial encontré este código de clasificación mnist:

import numpy as np

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epochs = 2

(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255

print(X_train.shape[0], "train samples")
print(X_test.shape[0], "test samples")

y_train = np_utils.to_categorical(y_train, nb_classes)
y_test =  np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))

model.compile(optimizer = "adam", loss = "categorical_crossentropy")

model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epochs, show_accuracy = True, verbose = 2, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 0)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])

Este código se ejecuta y obtengo el resultado como se esperaba:

(60000L, 'train samples')
(10000L, 'test samples')
Train on 60000 samples, validate on 10000 samples
Epoch 1/2
2s - loss: 0.2988 - acc: 0.9131 - val_loss: 0.1314 - val_acc: 0.9607
Epoch 2/2
2s - loss: 0.1144 - acc: 0.9651 - val_loss: 0.0995 - val_acc: 0.9673
('Test score: ', 0.099454972004890438)
('Test accuracy: ', 0.96730000000000005)

Hasta este punto, todo funciona perfectamente, sin embargo, cuando aplico el algoritmo anterior a mi conjunto de datos, la precisión se atasca.

Mi código es el siguiente:

import os

import pandas as pd

from sklearn.cross_validation import train_test_split

from keras.models import Sequential
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dense, Activation, Dropout, Flatten
from keras.utils import np_utils

import AudioProcessing as ap
import ImageTools as it

batch_size = 128
nb_classes = 2
nb_epoch = 10  


for i in range(20):
    print "\n"
# Generate spectrograms if necessary
if(len(os.listdir("./AudioNormalPathalogicClassification/Image")) > 0):
    print "Audio files are already processed. Skipping..."
else:
    print "Generating spectrograms for the audio files..."
    ap.audio_2_image("./AudioNormalPathalogicClassification/Audio/","./AudioNormalPathalogicClassification/Image/",".wav",".png",(28,28))

# Read the result csv
df = pd.read_csv('./AudioNormalPathalogicClassification/Result/result.csv', header = None)

df.columns = ["RegionName","IsNormal"]

bool_mapping = {True : 1, False : 0}

nb_classes = 2

for col in df:
    if(col == "RegionName"):
        a = 3      
    else:
        df[col] = df[col].map(bool_mapping)

y = df.iloc[:,1:].values

y = np_utils.to_categorical(y, nb_classes)

# Load images into memory
print "Loading images into memory..."
X = it.load_images("./AudioNormalPathalogicClassification/Image/",".png")

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)

X_train = X_train.reshape(X_train.shape[0], 784)
X_test = X_test.reshape(X_test.shape[0], 784)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255

print("X_train shape: " + str(X_train.shape))
print(str(X_train.shape[0]) + " train samples")
print(str(X_test.shape[0]) + " test samples")

model = Sequential()


model.add(Dense(output_dim = 100, input_dim = 784, activation= "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = 200, activation = "relu"))
model.add(Dense(output_dim = nb_classes, activation = "softmax"))

model.compile(loss = "categorical_crossentropy", optimizer = "adam")

print model.summary()

model.fit(X_train, y_train, batch_size = batch_size, nb_epoch = nb_epoch, show_accuracy = True, verbose = 1, validation_data = (X_test, y_test))
score = model.evaluate(X_test, y_test, show_accuracy = True, verbose = 1)
print("Test score: ", score[0])
print("Test accuracy: ", score[1])

AudioProcessing.py

import os
import scipy as sp
import scipy.io.wavfile as wav
import matplotlib.pylab as pylab
import Image

def save_spectrogram_scipy(source_filename, destination_filename, size):
    dt = 0.0005
    NFFT = 1024       
    Fs = int(1.0/dt)  
    fs, audio = wav.read(source_filename)
    if(len(audio.shape) >= 2):
        audio = sp.mean(audio, axis = 1)
    fig = pylab.figure()    
    ax = pylab.Axes(fig, [0,0,1,1])    
    ax.set_axis_off()
    fig.add_axes(ax) 
    pylab.specgram(audio, NFFT = NFFT, Fs = Fs, noverlap = 900, cmap="gray")
    pylab.savefig(destination_filename)
    img = Image.open(destination_filename).convert("L")
    img = img.resize(size)
    img.save(destination_filename)
    pylab.clf()
    del img

def audio_2_image(source_directory, destination_directory, audio_extension, image_extension, size):
    nb_files = len(os.listdir(source_directory));
    count = 0
    for file in os.listdir(source_directory):
        if file.endswith(audio_extension):        
            destinationName = file[:-4]
            save_spectrogram_scipy(source_directory + file, destination_directory + destinationName + image_extension, size)
            count += 1
            print ("Generating spectrogram for files " + str(count) + " / " + str(nb_files) + ".")

ImageTools.py

import os
import numpy as np
import matplotlib.image as mpimg
def load_images(source_directory, image_extension):
    image_matrix = []
    nb_files = len(os.listdir(source_directory));
    count = 0
    for file in os.listdir(source_directory):
        if file.endswith(image_extension):
            with open(source_directory + file,"r+b") as f:
                img = mpimg.imread(f)
                img = img.flatten()                
                image_matrix.append(img)
                del img
                count += 1
                #print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
    return np.asarray(image_matrix)

Entonces ejecuto el código anterior y recibo:

Audio files are already processed. Skipping...
Loading images into memory...
X_train shape: (2394L, 784L)
2394 train samples
1027 test samples
--------------------------------------------------------------------------------
Initial input shape: (None, 784)
--------------------------------------------------------------------------------
Layer (name)                  Output Shape                  Param #
--------------------------------------------------------------------------------
Dense (dense)                 (None, 100)                   78500
Dense (dense)                 (None, 200)                   20200
Dense (dense)                 (None, 200)                   40200
Dense (dense)                 (None, 2)                     402
--------------------------------------------------------------------------------
Total params: 139302
--------------------------------------------------------------------------------
None
Train on 2394 samples, validate on 1027 samples
Epoch 1/10
2394/2394 [==============================] - 0s - loss: 0.6898 - acc: 0.5455 - val_loss: 0.6835 - val_acc: 0.5716
Epoch 2/10
2394/2394 [==============================] - 0s - loss: 0.6879 - acc: 0.5522 - val_loss: 0.6901 - val_acc: 0.5716
Epoch 3/10
2394/2394 [==============================] - 0s - loss: 0.6880 - acc: 0.5522 - val_loss: 0.6842 - val_acc: 0.5716
Epoch 4/10
2394/2394 [==============================] - 0s - loss: 0.6883 - acc: 0.5522 - val_loss: 0.6829 - val_acc: 0.5716
Epoch 5/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 6/10
2394/2394 [==============================] - 0s - loss: 0.6887 - acc: 0.5522 - val_loss: 0.6832 - val_acc: 0.5716
Epoch 7/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6859 - val_acc: 0.5716
Epoch 8/10
2394/2394 [==============================] - 0s - loss: 0.6882 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
Epoch 9/10
2394/2394 [==============================] - 0s - loss: 0.6885 - acc: 0.5522 - val_loss: 0.6836 - val_acc: 0.5716
Epoch 10/10
2394/2394 [==============================] - 0s - loss: 0.6877 - acc: 0.5522 - val_loss: 0.6849 - val_acc: 0.5716
1027/1027 [==============================] - 0s
('Test score: ', 0.68490593621422047)
('Test accuracy: ', 0.57156767283349563)

Intenté cambiar la red, agregando más épocas, pero siempre obtengo el mismo resultado sin importar qué. No entiendo por qué obtengo el mismo resultado.

Cualquier ayuda sería apreciada. Gracias.

Editar: Encontré un error donde los valores de píxeles no se leían correctamente. Arreglé el ImageTools.py a continuación como:

import os
import numpy as np
from scipy.misc import imread

def load_images(source_directory, image_extension):
    image_matrix = []
    nb_files = len(os.listdir(source_directory));
    count = 0
    for file in os.listdir(source_directory):
        if file.endswith(image_extension):
            with open(source_directory + file,"r+b") as f:
                img = imread(f)                
                img = img.flatten()                        
                image_matrix.append(img)
                del img
                count += 1
                #print ("File " + str(count) + " / " + str(nb_files) + " loaded.")
    return np.asarray(image_matrix)

Ahora realmente obtengo valores de píxeles en escala de grises de 0 a 255, así que ahora dividirlo por 255 tiene sentido. Sin embargo, sigo obteniendo el mismo resultado.