### 基于 PyTorch 的 UNet 实现简介 UNet 是一种常用于图像分割任务的卷积神经网络架构，最初由 Ronneberger 等人在 2015 年提出。它通过编码器-解码器结构实现了高分辨率特征图的重建[^6]。以下是基于 PyTorch 的简单 UNet 实现代码示例： #### UNet 架构实现 以下是一个简单的 UNet 模型定义，适用于初学者理解其基本原理。 ```python import torch import torch.nn as nn 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) 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) 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 ``` 此代码展示了如何构建一个完整的 UNet 结构，其中包含了双层卷积模块 `DoubleConv`、下采样模块 `Down`、上采样模块 `Up` 和最终输出模块 `OutConv`[^7]。 --- ### 数据准备与训练流程概述 为了完成整个训练过程，还需要准备数据加载器以及优化器配置。下面提供了一个简化版本的数据加载和训练逻辑： ```python from torch.utils.data import DataLoader import torchvision.transforms as transforms from torchvision.datasets import DatasetFolder # 定义数据转换操作 transform = transforms.Compose([ transforms.Resize((512, 512)), transforms.ToTensor(), ]) # 创建自定义数据集类（假设输入为图片文件夹） dataset = DatasetFolder(root="path_to_data", loader=lambda x: Image.open(x), extensions=".png", transform=transform) # 划分训练集和验证集 train_loader = DataLoader(dataset, batch_size=4, shuffle=True) val_loader = DataLoader(dataset, batch_size=4, shuffle=False) # 初始化模型、损失函数和优化器 model = UNet(n_channels=3, n_classes=1).cuda() criterion = nn.BCEWithLogitsLoss().cuda() optimizer = torch.optim.Adam(model.parameters(), lr=0.001) # 训练循环 for epoch in range(epochs): model.train() for images, masks in train_loader: images, masks = images.cuda(), masks.cuda() optimizer.zero_grad() outputs = model(images) loss = criterion(outputs, masks.unsqueeze(1)) loss.backward() optimizer.step() print(f'Epoch {epoch}, Loss: {loss.item()}') ``` 以上代码片段涵盖了从数据加载到模型训练的核心部分[^8]。 ---