“‘连接’层需要具有匹配形状的输入，连接轴除外。”如何解决这个问题？

Question

下面是我的 unet 模型，我用 kerasImageDataGenerator 加载了 360X480 的图像 暗淡，但是在编译模型时。 但是如果 dim 是 128X128 、 256X256 则符合模型，要加载此 dim 应该更改哪些参数以及为什么会抛出连接错误，我有过滤器并且对应的是相同的。

IMG_HEIGHT=360
IMG_WIDTH=480
IMG_CHANNELS=3
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_CHANNELS))

c1 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (inputs)
c1 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c1)
c1 = Dropout(0.1) (c1)
p1 = MaxPooling2D((2, 2)) (c1)

c2 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p1)
c2 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c2)
c2 = Dropout(0.1) (c2)
p2 = MaxPooling2D((2, 2)) (c2)

c3 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p2)
c3 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c3)
c3 = Dropout(0.2) (c3)

p3 = MaxPooling2D((2, 2)) (c3)

c4 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p3)
c4 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c4)
c4 = Dropout(0.2) (c4)

p4 = MaxPooling2D(pool_size=(2, 2)) (c4)

c5 = Conv2D(256, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (p4)
c5 = Conv2D(256, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c5)
c5 = Dropout(0.3) (c5)


u6 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same') (c5)
u6 = concatenate([u6, c4])
c6 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u6)
c6 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c6)
c6 = Dropout(0.2) (c6)


u7 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same') (c6)
u7 = concatenate([u7, c3])
c7 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u7)
c7 = Conv2D(128, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c7)
c7 = Dropout(0.2) (c7)


u8 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same') (c7)
u8 = concatenate([u8, c2])
c8 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u8)
c8 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c8)
c8 = Dropout(0.1) (c8)


u9 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same') (c8)
u9 = concatenate([u9, c1], axis=3)
c9 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (u9)
c9 = Conv2D(64, (3, 3), activation='elu', kernel_initializer='he_normal', padding='same') (c9)
c9 = Dropout(0.1) (c9)


outputs = Conv2D(3, (1, 1), activation='sigmoid') (c9)

model = Model(inputs=[inputs], outputs=[outputs])
model.compile(optimizer='adam', loss='binary_crossentropy',metrics = ['accuracy'])
model.summary()

抛出以下错误：

'inputs with matching shapes '
    361                              'except for the concat axis. '
--> 362                              'Got inputs shapes: %s' % (input_shape))
    363 
    364     def _merge_function(self, inputs):

ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 44, 60, 128), (None, 45, 60, 128)]

Answer 1

由于您的输入大小不是正方形图像，因此在对特征提取步骤产生的特征进行上采样时，您必须特别注意形状。我建议您将输入重塑为方形图像。

这将强制重塑你的标签面具，你可以看看here 知道怎么做。

最后，这是一个带有方形图像的 uNet 的工作实现：

# Credits to https://github.com/zhixuhao/unet/blob/master/model.py
def unet(pretrained_weights = None,input_size = (256,256,1)):
    inputs = Input(input_size)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)

    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
    merge6 = concatenate([drop4,up6], axis = 3)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    merge7 = concatenate([conv3,up7], axis = 3)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    merge8 = concatenate([conv2,up8], axis = 3)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    merge9 = concatenate([conv1,up9], axis = 3)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)

    model = Model(input = inputs, output = conv10)

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy'])

我阅读了 UNet 论文，作者声明：

为了实现输出分割图的无缝平铺（参见图 2），重要的是选择输入平铺大小，以便将所有 2x2 最大池化操作应用于具有偶数 x 和 y 大小的层.

因此，请根据这些限制调整图像大小。