一、前言

经过慎重考虑，决定新开一个系列，该系列文章主要的目的就是利用PyTorch、Python实现深度学习中的一些经典模型，接下来一段时间的安排如下：

• UNet
• ResNet
• VggNet
• AlexNet

本文首先实现UNet，关于UNet的详细介绍请移步深度学习模型解析系列文章–白话详解UNet

二、网络结构详解

UNet总体上分为编码器和解码器，其中编码器负责提取特征信息，解码器负责还原特征信息；编码器主要由4个块组成，每个块分别由2个卷积层、1个最大池化层组成。解码器也是由4个块组成，每个块都是由1个上采样层、2个卷积层组成，详细信息请见下图。

三、网络组成部分实现

• 第1步：导入需要的包

import torch
import torch.nn as nn
import torch.nn.functional as F

• 第2步：我们需要自定义一个卷积的基础块，该基础块由2个卷积层组成。

class DoubleConv(nn.Module):
    """(convolution => [BN] => ReLU) * 2"""

    def __init__(self, in_channels, out_channels, mid_channels=None):
        super().__init__()
        if not mid_channels:
            mid_channels = out_channels
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        return self.double_conv(x)

• 第3步：我们需要自定义一个编码器的基础块，该块由1个最大池化层和第2步的卷积基础块组成。

class Down(nn.Module):
    """Downscaling with maxpool then double conv"""

    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        )

    def forward(self, x):
        return self.maxpool_conv(x)

• 第4步：我们需要自定义一个解码器的基础块，该基础块由1个上采样层和2个卷积层组成。

class Up(nn.Module):
    """Upscaling then double conv"""

    def __init__(self, in_channels, out_channels, bilinear=True):
        super().__init__()

        # if bilinear, use the normal convolutions to reduce the number of channels
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)  # 双线性插值
            self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
        else:
            self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)  # 转置卷积
            self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        # input is CHW
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]

        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)
        return self.conv(x)

• 第5步：定义一个最后的输出层

class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        return self.conv(x)

四、网络结构实现

• 第1步：我们需要把上述定义的类一股脑的导入到你要定义的网络文件中，因为每个人的文件夹不同，这里就不详细讲述。
• 第2步：初始化你的网络模型参数
• 第3步：编写前向传播方法

class UNet(nn.Module):
    def __init__(self, args, n_channels, n_classes, bilinear=True):
        super(UNet, self).__init__()  # 简单点讲：就是子类使用父类的初始化方法进行初始化，这会使得代码非常的整洁
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.bilinear = bilinear
        """DoubleConv <-> (convolution => [BN] => ReLU) * 2"""
        self.inc = DoubleConv(n_channels, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        factor = 2 if bilinear else 1
        self.down4 = Down(512, 1024 // factor)
        self.up1 = Up(1024, 512 // factor, bilinear)
        self.up2 = Up(512, 256 // factor, bilinear)
        self.up3 = Up(256, 128 // factor, bilinear)
        self.up4 = Up(128, 64, bilinear)
        self.outc = OutConv(64, n_classes)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        logits = self.outc(x)
        return logits

至此，UNet经典网络结构就编写好了，是不是非常的简单呢？如果您觉得写的还不错，欢迎一键三连，这对我真的帮助很大，非常感谢！我也会继续努力，提升文章的质量与数量！