編譯autoencoder時keras錯誤？

Question

這是我的自動編碼的模型：

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') 

這是我的配合和預測功能：

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) 

當我嘗試編譯此我碰到下面的錯誤。 我的數據集的所有圖像都是32x32像素。爲什麼這個錯誤呢？

​​

我需要在我的模型中做什麼改變，使輸入形狀變成（1,32,32）？

Answer 1

這很簡單：

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') 

你忘了在6卷積層加入適量border_mode='same'。