多输出 Keras 模型中消失的维度

Question

当我尝试训练下面描述的自动编码器时，我收到一个错误 ' 形状为 (256, 28, 28, 1) 的目标数组被传递用于形状输出 (None, 0, 28, 1) 作为损失`binary_crossentropy。此损失预计目标与输出具有相同的形状。' 输入和输出维度应均为 (28,28,1)，其中 256 为批量大小。运行.summary() 确认解码器模型的输出是正确的 (28,28,1)，但是当编码器和解码器一起编译时，这似乎发生了变化。知道这里发生了什么吗？三个函数在生成网络的时候依次调用。

def buildEncoder():
    input1 = Input(shape=(28,28,1))
    input2 = Input(shape=(28,28,1))
    merge = concatenate([input1,input2])
    convEncode1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(merge)
    maxPoolEncode1 = MaxPooling2D(pool_size=(2, 1))(convEncode1)
    convEncode2 = Conv2D(16, (3,3), activation = 'sigmoid', padding = 'same')(maxPoolEncode1)
    convEncode3 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convEncode2)
    model = Model(inputs = [input1,input2], outputs = convEncode3)
    model.compile(loss='binary_crossentropy', optimizer=adam)
    return model

def buildDecoder():
    input1 = Input(shape=(28,28,1))
    upsample1 = UpSampling2D((2,1))(input1)
    convDecode1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(upsample1)
    crop1 = Cropping2D(cropping = ((0,28),(0,0)))(convDecode1)
    crop2 = Cropping2D(cropping = ((28,0),(0,0)))(convDecode1)
    convDecode2_1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(crop1)
    convDecode3_1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(crop2)
    convDecode2_2 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convDecode2_1)
    convDecode3_2 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convDecode3_1)
    model = Model(inputs=input1, outputs=[convDecode2_2,convDecode3_2])
    model.compile(loss='binary_crossentropy', optimizer=adam)
    return model

def buildAutoencoder():   
    autoInput1 = Input(shape=(28,28,1))
    autoInput2 = Input(shape=(28,28,1))
    encode = encoder([autoInput1,autoInput2])
    decode = decoder(encode)
    model = Model(inputs=[autoInput1,autoInput2], outputs=[decode[0],decode[1]])
    model.compile(loss='binary_crossentropy', optimizer=adam)
    return model

运行 model.summary() 函数确认了这个

的最终输出维度

Answer 1

看来您的编码器形状计算有误。您假设解码器将获得 (None, 28, 28, 1) 但您的编码器实际上输出 (None, 14, 28, 28, 1).

print(encoder) # Tensor("model_1/conv2d_3/Sigmoid:0", shape=(?, 14, 28, 1), dtype=float32)

现在在你的解码器中你正在裁剪等，假设你有 (28, 28, 1)，这可能会把它切成 0。模型自己工作，当你连接它们时会发生不匹配。

多输出 Keras 模型中消失的维度

Disappearing Dimensions in Multi-Output Keras Model

python

machine-learning

autoencoder

keras

tensorflow