Unet

Ronneberger O , Fischer P , Brox T .U-Net: Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer International Publishing, 2015.DOI:10.1007/978-3-319-24574-4_28.

结构

编码器

由每个阶段重复的 $3\times 3$ 卷积层组成，每个卷积层后，ReLU 激活函数被逐元素地应用到每个特征上。在每个阶段之间，$2\times 2$ 的最大池化操作对特征进行下采样，步长为 2。

解码器

在每个阶段之间，使用 $2\times 2$ 卷积层将通道数减半。

跳过连接（skip connection）

复制编码器对应部分的特征，并将其与解码器相对应的阶段连接起来。这意味着后续的卷积层可以同时操作解码器与编码器的特征。

实现（Pytorch）

导入库

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

基础双卷积模块

每个下采样/上采样阶段的基础特征提取单元。

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, bias=False),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

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

下采样

通过 MaxPooling 实现 2 倍下采样。

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)

上采样

• 支持双线性插值或转置卷积
• 通过 torch.cat 实现跳跃连接
• 自动处理特征图尺寸对齐

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)
            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)
            self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        # input is CHW
        # 处理尺寸对齐问题
        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)

输出层

将通道数映射到分类数。

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)

UNet

class UNet(nn.Module):
    def __init__(self, n_channels, n_classes, bilinear=False):
        super(UNet, self).__init__()
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.bilinear = bilinear
        # Encoder
        self.inc = (DoubleConv(n_channels, 64))
        self.down1 = (Down(64, 128))
        self.down2 = (Down(128, 256))
        self.down3 = (Down(256, 512))
        # 是否使用双线性插值上采样
        factor = 2 if bilinear else 1
        self.down4 = (Down(512, 1024 // factor))
        # Decoder
        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):
        # Encoder路径
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)

        # Decoder路径 + skip connections
        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

    def use_checkpointing(self):
        self.inc = torch.utils.checkpoint(self.inc)
        self.down1 = torch.utils.checkpoint(self.down1)
        self.down2 = torch.utils.checkpoint(self.down2)
        self.down3 = torch.utils.checkpoint(self.down3)
        self.down4 = torch.utils.checkpoint(self.down4)
        self.up1 = torch.utils.checkpoint(self.up1)
        self.up2 = torch.utils.checkpoint(self.up2)
        self.up3 = torch.utils.checkpoint(self.up3)
        self.up4 = torch.utils.checkpoint(self.up4)
        self.outc = torch.utils.checkpoint(self.outc)