Question

我正在尝试为Keras博客https://blog.keras.io/building-autoencoders-in-keras.html上的Convolutional Autoencoder运行以下代码。但是，我收到了错误消息：

input_img = Input(shape=(1, 28, 28))

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)

# at this point the representation is (8, 4, 4) i.e. 128-dimensional

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)
print(decoded.get_shape())

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

autoencoder.fit(x_train, x_train,
                nb_epoch=50,
                batch_size=128,
                shuffle=True,
                validation_data=(x_test, x_test)
               )

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-25-5ca753acfdbb> in <module>()
     28                 batch_size=128,
     29                 shuffle=True,
---> 30                 validation_data=(x_test, x_test)
     31                )

C:\Users\Alexander\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, nb_epoch, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch)
   1036                                                            class_weight=class_weight,
   1037                                                            check_batch_dim=False,
-> 1038                                                            batch_size=batch_size)
   1039         # prepare validation data
   1040         if validation_data:

C:\Users\Alexander\Anaconda3\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_dim, batch_size)
    965                                    output_shapes,
    966                                    check_batch_dim=False,
--> 967                                    exception_prefix='model target')
    968         sample_weights = standardize_sample_weights(sample_weight,
    969                                                     self.output_names)

C:\Users\Alexander\Anaconda3\lib\site-packages\keras\engine\training.py in standardize_input_data(data, names, shapes, check_batch_dim, exception_prefix)
    109                                         ' to have shape ' + str(shapes[i]) +
    110                                         ' but got array with shape ' +
--> 111                                         str(array.shape))
    112     return arrays
    113 

Exception: Error when checking model target: expected convolution2d_92 to have shape (None, 4, 28, 1) but got array with shape (60000, 1, 28, 28)

我打印出来的解码维度为(?, 4, 28, 1)，在给定错误消息的情况下，似乎是模型所期望的。谢谢你的帮助。

Answer 1

问题在于，当我应该使用Tensorflow后端时，我意外地使用了Theano后端。在theano后端，第一个坐标表示单个张量的形状，但它在张量流中是相反的。例如，对于input_img，在Theano中它的形状为(1, 28, 28)，但在Tensorflow中为(28, 28, 1)。

张量错误的形状

1 个答案: