Fehler in Keras beim Erstellen von Autoencoder?

Question

Dies ist das Modell meines Autoencoder:

input_img = Input(shape=(1, 32, 32)) 

x = Convolution2D(16, 3, 3, activation='relu', border_mode='same')(input_img) 
x = MaxPooling2D((2, 2), border_mode='same')(x) 
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x) 
x = MaxPooling2D((2, 2), border_mode='same')(x) 
x = Convolution2D(8, 2, 2, activation='relu', border_mode='same')(x) 
encoded = MaxPooling2D((2, 2), border_mode='same')(x) 

x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(encoded) 
x = UpSampling2D((2, 2))(x) 
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x) 
x = UpSampling2D((2, 2))(x) 
x = Convolution2D(16, 3, 3, activation='relu')(x) 
x = UpSampling2D((2, 2))(x) 
decoded = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same')(x) 

autoencoder = Model(input_img, decoded) 
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy') 

Dies ist meine fit und Vorhersage-Funktion:

autoencoder.fit(X_train, X_train, 
      nb_epoch=10, 
      batch_size=128, 
      shuffle=True, 
      validation_data=(X_test, X_test)) 

decoded_imgs = autoencoder.predict(X_test) 

Wenn ich versuche, das ich die folgende Fehlermeldung erhalten, zu kompilieren. Alle Bilder meines Datasets sind 32x32 Pixel. Warum dieser Fehler dann?

Exception: Error when checking model target: expected convolution2d_7 to have shape (None, 1, 28, 28) but got array with shape (4200, 1, 32, 32) 

Welche Änderung muss ich in meinem Modell vornehmen, damit die Eingabeform (1,32,32) wird?

Answer 1

so einfach war:

input_img = Input(shape=(1, 32, 32)) 

x = Convolution2D(16, 3, 3, activation='relu', border_mode='same')(input_img) 
x = MaxPooling2D((2, 2), border_mode='same')(x) 
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x) 
x = MaxPooling2D((2, 2), border_mode='same')(x) 
x = Convolution2D(8, 2, 2, activation='relu', border_mode='same')(x) 
encoded = MaxPooling2D((2, 2), border_mode='same')(x) 

x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(encoded) 
x = UpSampling2D((2, 2))(x) 
x = Convolution2D(8, 3, 3, activation='relu', border_mode='same')(x) 
x = UpSampling2D((2, 2))(x) 
x = Convolution2D(16, 3, 3, activation='relu', border_mode='same')(x) 
x = UpSampling2D((2, 2))(x) 
decoded = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same')(x) 

autoencoder = Model(input_img, decoded) 
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy') 

Sie haben vergessen, über entsprechende border_mode='same' in der 6. Faltungsschicht hinzugefügt wird.