我有大约 70,000 个训练图像的列表,每个图像的形状(颜色 channel 数、高度宽度)= (3, 30, 30),以及大约 20,000 个测试图像。我的卷积自动编码器定义为:
# Same as the code above, but with some params changed
# Now let's define the model.
# Set input dimensions:
input_img = Input(shape=(3, 30, 30))
# Encoder: define a chain of Conv2D and MaxPooling2D layers
x = Convolution2D(128, 3, 3,
activation='relu',
border_mode='same')(input_img)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same')(x)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(64, 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
# Decoder: a stack of Conv2D and UpSampling2D layers
x = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same')(x)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(128, 3, 3,
activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Convolution2D(1, 3, 3,
activation='sigmoid',
border_mode='same')(x)
autoencoder2 = Model(input_img, decoded)
autoencoder2.compile(optimizer='adadelta', loss='mse')
这是 here 中的自动编码器。
它抛出一个错误:
Error when checking model target: expected convolution2d_14 to have shape (None, 1, 28, 28) but got array with shape (76960, 3, 30, 30)
这很奇怪,因为我已经明确地将指定的输入形状更改为 (3, 30, 30)。我是否缺少一些实现技术?
最佳答案
您忘记在解码器的最后一个卷积层中添加 border_mode='same' 。
关于python - Keras 卷积自动编码器 : Layer Shapes,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/39181976/