4

我已经训练了以下自动编码器模型：

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, 3, 3, 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='RMSprop', loss='binary_crossentropy')

autoencoder.fit(X_train, X_train,
            nb_epoch=1,
            batch_size=128,
            shuffle=True,
            validation_data=(X_test, X_test)]
            )

在训练这个自动编码器之后，我想将训练有素的编码器用于受监督的线路。我怎样才能只提取这个自动编码器模型的训练有素的编码器部分？

4

1 回答 1

3

您可以在训练后创建一个仅使用编码器的模型：

autoencoder = Model(input_img, encoded)

如果您想在编码部分之后添加更多层，您也可以这样做：

classifier = Dense(nb_classes, activation='softmax')(encoded)
model = Model(input_img, classifier)
于 2016-09-17T22:07:57.197 回答