Python,keras,卷积自动编码器

时间:2017-06-09 20:23:03

标签: python keras conv-neural-network autoencoder

我正在尝试在keras中创建我的第一个卷积自动编码器,但我遇到了图层输出形状的问题。有我的代码:

input_img = Input(shape=X_train.shape[1:])

x = Conv2D(32, (3, 3), activation='relu', padding='same', kernel_constraint=maxnorm(3))(input_img)
x = MaxPooling2D(pool_size=(2, 2), padding='same')(x)
x = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_constraint=maxnorm(3))(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)

x = Conv2D(16, (3, 3), activation='relu', padding='same', kernel_constraint=maxnorm(3))(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same', kernel_constraint=maxnorm(3))(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
print(autoencoder.summary())
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(X_train, X_train, epochs=50, batch_size=32)

和结果:

_________________________________________________________________
Layer (type)                 Output Shape              Param   
=================================================================
input_87 (InputLayer)        (None, 32, 32, 3)         0         
_________________________________________________________________
conv2d_327 (Conv2D)          (None, 32, 32, 3)         9248      
_________________________________________________________________
max_pooling2d_136 (MaxPoolin (None, 32, 16, 2)         0         
_________________________________________________________________
conv2d_328 (Conv2D)          (None, 16, 16, 2)         4624      
_________________________________________________________________
max_pooling2d_137 (MaxPoolin (None, 16, 8, 1)          0         
_________________________________________________________________
conv2d_329 (Conv2D)          (None, 16, 8, 1)          2320      
_________________________________________________________________
up_sampling2d_124 (UpSamplin (None, 16, 16, 2)         0         
_________________________________________________________________
conv2d_330 (Conv2D)          (None, 32, 16, 2)         4640      
_________________________________________________________________
up_sampling2d_125 (UpSamplin (None, 32, 32, 4)         0         
_________________________________________________________________
conv2d_331 (Conv2D)          (None, 1, 32, 4)          289       
=================================================================
Total params: 21,121
Trainable params: 21,121
Non-trainable params: 0
_________________________________________________________________
None

当然是错误:

ValueError: Error when checking target: expected conv2d_331 to have shape (None, 1, 32, 4) but got array with shape (50000, 32, 32, 3)

你知道我做错了什么吗?为什么上次UpSampling2D会返回那个形状?

1 个答案:

答案 0 :(得分:1)

因此,您的keras似乎已将其图片维度设置为channel_first(可能Theano作为后端),这意味着您的输入的最后两个维度被视为空间维度而不是第二和第三。另一件事是您的输出应该有3个过滤器而不是1,这将最终导致目标维度不匹配。总结一下:

  1. 要正确设置输入,您需要切换到tensorflow并将频道订购更改为channel_last或通过以下方式转置输入:

    X = X.transpose([0, 3, 1, 2])
    
  2. 更改以下行:

    decoded = Conv2D(3, (3, 3), activation='sigmoid', padding='same')(x)