Keras, problème de matrice clairsemée
J'essaie d'alimenter une énorme matrice clairsemée au modèle Keras. Comme l'ensemble de données ne rentre pas dans la RAM, la solution consiste à former le modèle sur des données générées lot par lot par un générateur.
Pour tester cette approche et m'assurer que ma solution fonctionne correctement, j'ai légèrement modifié un le MLP simple de Kera sur la tâche de classification des rubriques du fil de presse Reuters . L'idée est donc de comparer les modèles originaux et édités. Je viens de convertir numpy.ndarray en scipy.sparse.csr.csr_matrix et de le transmettre au modèle.
Mais mon modèle se bloque à un moment donné et j'ai besoin d'un coup de main pour trouver une raison.
Voici le modèle original et mes ajouts ci-dessous
from __future__ import print_function
import numpy as np
np.random.seed(1337) # for reproducibility
from keras.datasets import reuters
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.utils import np_utils
from keras.preprocessing.text import Tokenizer
max_words = 1000
batch_size = 32
nb_Epoch = 5
print('Loading data...')
(X_train, y_train), (X_test, y_test) = reuters.load_data(nb_words=max_words, test_split=0.2)
print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
nb_classes = np.max(y_train)+1
print(nb_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(nb_words=max_words)
X_train = tokenizer.sequences_to_matrix(X_train, mode='binary')
X_test = tokenizer.sequences_to_matrix(X_test, mode='binary')
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
print('Convert class vector to binary class matrix (for use with categorical_crossentropy)')
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
print('Y_train shape:', Y_train.shape)
print('Y_test shape:', Y_test.shape)
print('Building model...')
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(X_train, Y_train,
nb_Epoch=nb_Epoch, batch_size=batch_size,
verbose=1)#, validation_split=0.1)
#score = model.evaluate(X_test, Y_test,
# batch_size=batch_size, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1])
Il génère:
Loading data...
8982 train sequences
2246 test sequences
46 classes
Vectorizing sequence data...
X_train shape: (8982, 1000)
X_test shape: (2246, 1000)
Convert class vector to binary class matrix (for use with categorical_crossentropy)
Y_train shape: (8982, 46)
Y_test shape: (2246, 46)
Building model...
Epoch 1/5
8982/8982 [==============================] - 5s - loss: 1.3932 - acc: 0.6906
Epoch 2/5
8982/8982 [==============================] - 4s - loss: 0.7522 - acc: 0.8234
Epoch 3/5
8982/8982 [==============================] - 5s - loss: 0.5407 - acc: 0.8681
Epoch 4/5
8982/8982 [==============================] - 5s - loss: 0.4160 - acc: 0.8980
Epoch 5/5
8982/8982 [==============================] - 5s - loss: 0.3338 - acc: 0.9136
Test score: 1.01453569163
Test accuracy: 0.797417631398
Enfin, voici ma part
X_train_sparse = sparse.csr_matrix(X_train)
def batch_generator(X, y, batch_size):
n_batches_for_Epoch = X.shape[0]//batch_size
for i in range(n_batches_for_Epoch):
index_batch = range(X.shape[0])[batch_size*i:batch_size*(i+1)]
X_batch = X[index_batch,:].todense()
y_batch = y[index_batch,:]
yield(np.array(X_batch),y_batch)
model.fit_generator(generator=batch_generator(X_train_sparse, Y_train, batch_size),
nb_Epoch=nb_Epoch,
samples_per_Epoch=X_train_sparse.shape[0])
Le crash:
Exception Traceback (most recent call last)
<ipython-input-120-6722a4f77425> in <module>()
1 model.fit_generator(generator=batch_generator(X_trainSparse, Y_train, batch_size),
2 nb_Epoch=nb_Epoch,
----> 3 samples_per_Epoch=X_trainSparse.shape[0])
/home/kk/miniconda2/envs/tensorflow/lib/python2.7/site-packages/keras/models.pyc in fit_generator(self, generator, samples_per_Epoch, nb_Epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, **kwargs)
648 nb_val_samples=nb_val_samples,
649 class_weight=class_weight,
--> 650 max_q_size=max_q_size)
651
652 def evaluate_generator(self, generator, val_samples, max_q_size=10, **kwargs):
/home/kk/miniconda2/envs/tensorflow/lib/python2.7/site-packages/keras/engine/training.pyc in fit_generator(self, generator, samples_per_Epoch, nb_Epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size)
1356 raise Exception('output of generator should be a Tuple '
1357 '(x, y, sample_weight) '
-> 1358 'or (x, y). Found: ' + str(generator_output))
1359 if len(generator_output) == 2:
1360 x, y = generator_output
Exception: output of generator should be a Tuple (x, y, sample_weight) or (x, y). Found: None
Je pense que le problème est dû à une mauvaise configuration de samples_per_Epoch. J'apprécierais vraiment si quelqu'un pouvait commenter cela.
Voici ma solution.
def batch_generator(X, y, batch_size):
number_of_batches = samples_per_Epoch/batch_size
counter=0
shuffle_index = np.arange(np.shape(y)[0])
np.random.shuffle(shuffle_index)
X = X[shuffle_index, :]
y = y[shuffle_index]
while 1:
index_batch = shuffle_index[batch_size*counter:batch_size*(counter+1)]
X_batch = X[index_batch,:].todense()
y_batch = y[index_batch]
counter += 1
yield(np.array(X_batch),y_batch)
if (counter < number_of_batches):
np.random.shuffle(shuffle_index)
counter=0
Dans mon cas, matrice X-clairsemée, y-tableau.