### 使用 PyTorch 构建 UNet 进行语义分割 构建 UNet 模型的关键在于其独特的架构设计，该网络由收缩路径（下采样）和扩展路径（上采样）组成[^1]。通过这种方式，UNet 能够捕捉到输入图像中的多尺度特征并保留空间信息。 #### 定义编码器部分 编码器负责提取高层次的抽象特征表示。每一层通常包含两个卷积操作以及一个最大池化层来减少尺寸： ```python import torch.nn as nn import torch class DoubleConv(nn.Module): """(convolution => [BN] => ReLU) * 2""" def __init__(self, in_channels, out_channels): super().__init__() self.double_conv = nn.Sequential( nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_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) 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) ``` #### 定义解码器部分 解码器旨在恢复原始的空间分辨率，并融合来自编码阶段的信息以提高精度。这通常是通过对称结构完成的，在这里会应用转置卷积来进行放大处理： ```python class Up(nn.Module): """Upscaling then double conv""" def __init__(self, in_channels, out_channels, bilinear=True): super().__init__() # 如果使用双线性插值，则不采用转置卷积 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) 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) ``` #### 组合完整的 U-Net 结构 最后一步是将上述组件组合起来形成整个 U-Net 网络框架： ```python class UNet(nn.Module): def __init__(self, n_channels, n_classes, bilinear=True): super(UNet, self).__init__() self.n_channels = n_channels self.n_classes = n_classes self.bilinear = bilinear 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 ``` 为了使模型能够适应特定的应用场景，可以根据实际需求调整通道数和其他超参数设置。此外，还可以考虑引入预训练权重或者更复杂的损失函数来优化性能表现[^2]。