尝试执行转置卷积但缺少像素

Question

def get_unet(input_img, n_filters=16, dropout=0.5, batchnorm=True):

    # contracting path
    c1 = conv2d_block(input_img, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)
    p1 = MaxPooling2D((2, 2))(c1)
    p1 = Dropout(dropout * 0.5)(p1)

    c2 = conv2d_block(p1, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)
    p2 = MaxPooling2D((2, 2))(c2)
    p2 = Dropout(dropout)(p2)

    c3 = conv2d_block(p2, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)
    p3 = MaxPooling2D((2, 2))(c3)
    p3 = Dropout(dropout)(p3)

    c4 = conv2d_block(p3, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)
    p4 = MaxPooling2D(pool_size=(2, 2))(c4)
    p4 = Dropout(dropout)(p4)

    c5 = conv2d_block(p4, n_filters=n_filters * 16, kernel_size=3, batchnorm=batchnorm)

    # expansive path
    u6 = Conv2DTranspose(n_filters * 8, (3, 3), strides=(2, 2), padding='same')(c5)
    u6 = concatenate([u6, c4])
    u6 = Dropout(dropout)(u6)
    c6 = conv2d_block(u6, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)

    u7 = Conv2DTranspose(n_filters * 4, (3, 3), strides=(2, 2), padding='same')(c6)
    u7 = concatenate([u7, c3])
    u7 = Dropout(dropout)(u7)
    c7 = conv2d_block(u7, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)

    u8 = Conv2DTranspose(n_filters * 2, (3, 3), strides=(2, 2), padding='same')(c7)
    u8 = concatenate([u8, c2])
    u8 = Dropout(dropout)(u8)
    c8 = conv2d_block(u8, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)

    u9 = Conv2DTranspose(n_filters * 1, (3, 3), strides=(2, 2), padding='same')(c8)
    u9 = concatenate([u9, c1], axis=3)
    u9 = Dropout(dropout)(u9)
    c9 = conv2d_block(u9, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)

    outputs = Conv2D(1, (1, 1), activation='sigmoid')(c9)
    model = Model(inputs=[input_img], outputs=[outputs])
    return model

我从这里得到了这个 Keras 模型。我似乎遇到了错误：

  File "train.py", line 87, in get_unet
  u8 = concatenate([u8, c2])
ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 256, 184, 32), (None, 256, 185, 32)]

所以我打印了每个张量的值，我得到了：

c1: Tensor("activation_2/Relu:0", shape=(?, 512, 370, 16), dtype=float32)
c2: Tensor("activation_4/Relu:0", shape=(?, 256, 185, 32), dtype=float32)
c3: Tensor("activation_6/Relu:0", shape=(?, 128, 92, 64), dtype=float32)
c4: Tensor("activation_8/Relu:0", shape=(?, 64, 46, 128), dtype=float32)
c5: Tensor("activation_10/Relu:0", shape=(?, 32, 23, 256), dtype=float32)
u6: Tensor("dropout_5/cond/Merge:0", shape=(?, 64, 46, 256), dtype=float32)
u7: Tensor("dropout_6/cond/Merge:0", shape=(?, 128, 92, 128), dtype=float32)
u8: Tensor("conv2d_transpose_3/BiasAdd:0", shape=(?, ?, ?, 32), dtype=float32)

C2 发生了什么事？为什么u8的第二个维度是184，而C2的第二个维度好像是185。而且，C3的第二个维度好像是从184被maxpool了2倍（可能是由于 floor 函数）

我将如何解决这个问题？我是否必须更改正在输入的图像的大小，或者我是否必须在进行转置卷积时设计一些东西？我是否需要为一个额外的像素执行插值？

Answer 1

发生这种情况是因为你的第二维在你的 C2 层中除以 2 时甚至还没有。
你最大池化 185 2 倍，这给你 92.5 -> floor to 92
但是当你以另一种方式进行操作时，你将 92 上采样 2 倍，得到 184。

为了避免这种情况，您可以简单地使用 zeropad U8 来与 C2 兼容，如下所示：

u8 = Conv2DTranspose(n_filters * 2, (3, 3), strides=(2, 2), padding='same')(c7)
u8 = ZeroPadding2D(padding=((0, 0), (0, 1)))(u8)
u8 = concatenate([u8, c2])

如果你不想使用 zeropad，你可以重塑你的输入图像，使其具有对应于 2 的幂的维度或可以被二分多次而不给出奇数的维度，比如224（可以除以5次再给7）。

希望对您有所帮助！

尝试执行转置卷积但缺少像素

Trying to perform transposed convolution but missing a pixel

python-3.x

tensorflow

keras

tensor

deconvolution