时间戳

首页 > 解决方案 > ValueError：“连接”层需要具有匹配形状的输入，连接轴除外。得到输入形状：[(None, 36, 36, 128) 等

python - ValueError：“连接”层需要具有匹配形状的输入，连接轴除外。得到输入形状：[(None, 36, 36, 128) 等

问题描述

ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: `[(None, 36, 36, 128), (None, 37, 37, 128)]`

def conv2d_block(input_tensor, n_filters, kernel_size=3, batchnorm=True):
    # first layer
    x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal",
               padding="same")(input_tensor)
    if batchnorm:
        x = BatchNormalization()(x)
    x = Activation("relu")(x)
    # second layer
    x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal",
               padding="same")(x)
    if batchnorm:
        x = BatchNormalization()(x)
    x = Activation("relu")(x)
    return x

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

关于我缺少什么的任何想法？异常出现在 u6 = concatenate([u6, c4])

我正在使用 python 3.9.1，我的导入主要涉及Keras使用TensorFlow后端。我也尝试删除一些 MaxPooling，但这并没有帮助，以及更改一些 MaxPulling 变量。

我的图像输入是：input_img = Input((300, 300, 1), name="img")

标签： pythontensorflowkerasvalueerrorunity3d-unet

解决方案

您的问题是图像没有 2 的幂的维度，例如具有 256 或 512 之类的维度不会产生此问题，这是因为在您的网络中，您有池化层生成一半大小的图像，当您将 300 除以 2 时，您会得到系列：150 和 75 并且 75 不能被 2 整除，因此当您尝试除以 75 时，您会得到 37 号，当您对下方级别进行移调时，您会得到 36 号.

我不知道这是否足够清楚：您正在尝试对具有奇数像素的图像进行最大池化，图像将变为 300 -> 150 -> 75 -> 37 -> 18 并且得到双倍的 18 -> 36 STOP, 36 和 37 不相等，网络无法连接

所以，快速解决方案：调整图像的大小，使其尺寸为 2 的幂，例如 512，或者至少可以被 8 整除的尺寸（因为你有 4 个最大池）

推荐阅读