Comment utiliser perceptron multi-couche de Keras pour la classification multi-classe

Question

J'ai essayé de suivre l'instruction here, où il a déclaré que il utilise Reuter dataset.

from keras.datasets import reuters 

(X_train, y_train), (X_test, y_test) = reuters.load_data(path="reuters.pkl", 
                 nb_words=None, 
                 skip_top=0, 
                 maxlen=None, 
                 test_split=0.1) 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Activation 
from keras.optimizers import SGD 

model = Sequential() 
# Dense(64) is a fully-connected layer with 64 hidden units. 
# in the first layer, you must specify the expected input data shape: 
# here, 20-dimensional vectors. 
model.add(Dense(64, input_dim=20, init='uniform')) 
model.add(Activation('tanh')) 
model.add(Dropout(0.5)) 
model.add(Dense(64, init='uniform')) 
model.add(Activation('tanh')) 
model.add(Dropout(0.5)) 
model.add(Dense(10, init='uniform')) 
model.add(Activation('softmax')) 

sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) 
model.compile(loss='categorical_crossentropy', 
       optimizer=sgd, 
       metrics=['accuracy']) 

#breaks here 
model.fit(X_train, y_train, 
      nb_epoch=20, 
      batch_size=16) 

score = model.evaluate(X_test, y_test, batch_size=16) 

Mais le code se brise sur l'ajustement du modèle. Comment puis-je résoudre le problème?

Mise à jour: Ceci est l'erreur que j'ai eue.

In [21]: model.fit(X_train, y_train, 
    ....:   nb_epoch=20, 
    ....:   batch_size=16) 
--------------------------------------------------------------------------- 
Exception         Traceback (most recent call last) 
<ipython-input-21-4b227e56e5a9> in <module>() 
     1 model.fit(X_train, y_train, 
     2   nb_epoch=20, 
----> 3   batch_size=16) 

//anaconda/lib/python2.7/site-packages/keras/models.pyc in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, **kwargs) 
    400        shuffle=shuffle, 
    401        class_weight=class_weight, 
--> 402        sample_weight=sample_weight) 
    403 
    404  def evaluate(self, x, y, batch_size=32, verbose=1, 

//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight) 
    969               class_weight=class_weight, 
    970               check_batch_dim=False, 
--> 971               batch_size=batch_size) 
    972   # prepare validation data 
    973   if validation_data: 

//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_dim, batch_size) 
    909       in zip(y, sample_weights, class_weights, self.sample_weight_modes)] 
    910   check_array_lengths(x, y, sample_weights) 
--> 911   check_loss_and_target_compatibility(y, self.loss_functions, self.internal_output_shapes) 
    912   if self.stateful and batch_size: 
    913    if x[0].shape[0] % batch_size != 0: 

//anaconda/lib/python2.7/site-packages/keras/engine/training.pyc in check_loss_and_target_compatibility(targets, losses, output_shapes) 
    182    if y.shape[1] == 1: 
    183     raise Exception('You are passing a target array of shape ' + str(y.shape) + 
--> 184         ' while using as loss `categorical_crossentropy`. ' 
    185         '`categorical_crossentropy` expects ' 
    186         'targets to be binary matrices (1s and 0s) ' 

Exception: You are passing a target array of shape (10105, 1) while using as loss `categorical_crossentropy`. `categorical_crossentropy` expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via: 
``` 
from keras.utils.np_utils import to_categorical 
y_binary = to_categorical(y_int) 
``` 

Alternatively, you can use the loss function `sparse_categorical_crossentropy` instead, which does expect integer targets. 

Answer 1

Ceci est une erreur de débutant assez commun avec Keras. Contrairement aux autres frameworks Deep Learning, Keras n'utilise pas d'étiquettes entières pour la perte de crossentropy habituelle, mais attend un vecteur binaire (appelé «one-hot»), où le vecteur est juste 0 et 1 sur l'index de la bonne classe.

Vous pouvez facilement convertir vos étiquettes à ce format avec le code suivant:

from keras.utils.np_utils import to_categorical 
y_train = to_categorical(y_train) 
y_test = to_categorical(y_test) 

Avant model.fit. Une alternative consiste à remplacer la perte par "sparse_categorical_crossentropy", ce qui suppose des étiquettes entières.