### 使用 PyTorch 实现 UNet 模型进行图像分割 为了使用 PyTorch 实现 UNet 模型并应用于图像分割任务，需先确保环境中有必要的依赖库被安装。这可以通过执行命令 `pip install torch torchvision numpy matplotlib` 来完成[^2]。 #### 安装依赖项 ```bash pip install torch torchvision numpy matplotlib ``` 接着定义 UNet 的网络结构，在此提供一段简化版的 UNet 构建代码作为示例： #### 创建 UNet 类 ```python import torch from torch import nn import torch.nn.functional as F 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 UNet(nn.Module): def __init__(self, n_channels, n_classes): super(UNet, self).__init__() self.inc = DoubleConv(n_channels, 64) self.down1 = Down(64, 128) self.down2 = Down(128, 256) self.up1 = Up(384, 128) self.up2 = Up(192, 64) self.outc = OutConv(64, n_classes) def forward(self, x): x1 = self.inc(x) x2 = self.down1(x1) x3 = self.down2(x2) x = self.up1(x3, x2) x = self.up2(x, x1) logits = self.outc(x) return logits 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) 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) 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) 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) ``` 上述代码展示了如何构建一个基础版本的 UNet 网络架构，其中包含了编码器（下采样路径）、解码器（上采样路径），以及跳跃连接来融合不同层次的信息。 对于更详细的实践指导和完整的训练流程，可以参考开源项目中的具体实现方式，例如位于 https://gitcode.com/open-source-toolkit/431f6 的 `unet-pytorch-main.zip` 提供了更多细节上的说明与配置文件[^3]。