数据挖掘 - 在没有填充的情况下实现 U-Net 分割模型 - 吾爱随笔录

我正在尝试按照此处发表的论文实施 U-Net CNN 。

我已经尽可能地遵循了论文架构，但是在尝试执行第一个连接时遇到了错误：

从图中可以看出，第 8 个 Conv2D 应该与第一个 UpSampling2D 操作的结果合并，但是该Concatenate()操作会引发形状不匹配的异常：

def model(image_size = (572, 572) + (1,)):

    # Input / Output layers
    input_layer = Input(shape=(image_size), 32)

    """ Begin Downsampling """

    # Block 1
    conv_1 = Conv2D(64, 3, activation = 'relu')(input_layer)
    conv_2 = Conv2D(64, 3, activation = 'relu')(conv_1)

    max_pool_1 = MaxPool2D(strides=2)(conv_2)

    # Block 2
    conv_3 = Conv2D(128, 3, activation = 'relu')(max_pool_1)
    conv_4 = Conv2D(128, 3, activation = 'relu')(conv_3)

    max_pool_2 = MaxPool2D(strides=2)(conv_4)

    # Block 3
    conv_5 = Conv2D(256, 3, activation = 'relu')(max_pool_2)
    conv_6 = Conv2D(256, 3, activation = 'relu')(conv_5)

    max_pool_3 = MaxPool2D(strides=2)(conv_6)

    # Block 4
    conv_7 = Conv2D(512, 3, activation = 'relu')(max_pool_3)
    conv_8 = Conv2D(512, 3, activation = 'relu')(conv_7)

    max_pool_4 = MaxPool2D(strides=2)(conv_8)

    """ Begin Upsampling """

    # Block 5
    conv_9 = Conv2D(1024, 3, activation = 'relu')(max_pool_4)
    conv_10 = Conv2D(1024, 3, activation = 'relu')(conv_9)

    upsample_1 = UpSampling2D()(conv_10)

    # Connect layers
    merge_1 = Concatenate()([conv_8, upsample_1])

错误：

Exception has occurred: ValueError
A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(32, 64, 64, 512), (32, 56, 56, 1024)]

请注意，这些值64与56架构正确对齐。

我不明白如何实现论文中的模型。如果我更改我的代码以接受形状图像(256, 256)并添加padding='same'到 Conv2D 图层，则代码将在大小对齐时起作用。

这似乎违背了作者在其实施中具体陈述的内容：

有人可以为我指出正确实施该模型的正确方向吗？