题外话

$\quad </annotation> </semantics> </math>$

网络架构

这就是整个网络的结构，大体分为收缩和扩张路径来组成。因为形似一个字母U，得名Unet。收缩路径仍然是利用传统卷积神经网络的卷积池化组件，其中经过一次下采样之后，channels变为原来的2倍。扩张路径由2 * 2的反卷积，反卷机的输出通道为原来通道数的一半，再与原来的feature map（裁剪之后）串联，得到和原来一样多的通道数的feature map，再经过2个尺寸为3 * 3的卷积和ReLU的作用。裁剪特征图是必要的，因为在卷积的过程中会有边界像素的丢失。在最后一层通过卷积核大小为1 * 1的卷积作用得到想要的目标种类。在Unet中一共有23个卷积层。但是这个网络需要谨慎的选择输入图片的尺寸，以保证所有的Max Pooling操作作用于长宽为偶数的feature map。

Trick1: 对于尺寸较大的图像：Overlap-tile strategy

$\quad </annotation> </semantics> </math>$

数据集可以用数据量较少

$\quad </annotation> </semantics> </math>$

相同物体间的间隔不容易分割出来

$\quad </annotation> </semantics> </math>$

主要贡献

$\quad </annotation> </semantics> </math>$

总结

$\quad </annotation> </semantics> </math>$

代码实现

#coding=utf-8
from keras.models import *
from keras.layers import *

def Unet (nClasses, optimizer=None, input_width=512, input_height=512):
    input_size = (input_height, input_width, 3)
    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(nClasses, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)

    o_shape = Model(inputs, conv9).output_shape
    outputHeight = o_shape[1]
    outputWidth = o_shape[2]
    conv9 = Reshape((nClasses, input_height * input_width))(conv9)
    conv9 = Permute((2, 1))(conv9)

    conv10 = (Activation('softmax'))(conv9)

    model = Model(inputs, conv10)
    model.outputWidth = outputWidth
    model.outputHeight = outputHeight
    return model

训练请看：
https://github.com/BBuf/Keras-Semantic-Segmentation

《Unet》论文理解

题外话

网络架构

Trick1: 对于尺寸较大的图像：Overlap-tile strategy

数据集可以用数据量较少

相同物体间的间隔不容易分割出来

主要贡献

总结

代码实现