Question

我正在尝试在Keras中构建深层卷积自动编码器，但它会不断输出错误的形状。

代码：

def build_network(input_shape):
    input_input =  Input(shape=input_shape)

    #Encode
    x = Conv2D(16, (3, 3), activation='relu', padding = 'same')(input_input)
    x = MaxPooling2D((2, 2), padding='same')(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = MaxPooling2D((2, 2), padding='same')(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = MaxPooling2D((2, 2), padding='same')(x)

    #Decode
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = UpSampling2D((2, 2))(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = UpSampling2D((2, 2))(x)
    x = Conv2D(16, (3, 3), activation='relu', padding='same')(x) 
    x = UpSampling2D((2, 2))(x)
    decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
    autoencoder = Model(input_input, decoded)
    return autoencoder


if __name__ == "__main__":
    print(build_network((1, 32, 32)).layers[-1].output)

我希望输出形状与输入形状相同，但对于(8, 32, 1)，它应该是(1, 32, 32)

Answer 1

尝试使用print(build_network((32,32,1)).layers[-1].output)。或者，如果您要先使用频道，而不需要像这样更改模型，

def build_network(input_shape):
    input_input =  Input(shape=input_shape)

    #Encode
    x = Conv2D(16, (3, 3), activation='relu', padding = 'same')(input_input)
    x = MaxPooling2D((2, 2), padding='same')(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = MaxPooling2D((2, 2), padding='same')(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = MaxPooling2D((2, 2), padding='same')(x)

    #Decode
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = UpSampling2D(size=(2, 2),data_format="channels_first")(x)
    x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
    x = UpSampling2D(size=(2, 2),data_format="channels_first")(x)
    x = Conv2D(16, (3, 3), activation='relu', padding='same')(x) 
    decoded = UpSampling2D(size=(2, 2),data_format="channels_first")(x)
    # decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
    autoencoder = Model(input_input, decoded)
    return autoencoder

if __name__ == "__main__":
    print(build_network((1, 32, 32)).layers[-1].output)

由于在UpSampling2D中，默认值为“ channels_last”。

Keras自动编码器输出了错误的形状

1 个答案: