### 使用 PyTorch 实现 UNet 网络 #### 1. 导入必要的库 为了构建和训练 UNet 模型，首先需要导入所需的 Python 库。 ```python import torch from torch import nn, optim from torchvision import transforms from torch.utils.data import DataLoader, Dataset import os ``` #### 2. 定义 UNet 架构 UNet 是一种常用于图像分割任务的卷积神经网络架构。下面是一个简单的 UNet 实现： ```python 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=False): 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 ``` 此代码定义了一个完整的 UNet 结构[^1][^2]。 #### 3. 数据集准备与加载器设置 对于实际应用来说，还需要准备好相应的数据集并创建合适的 `DataLoader` 来提供给模型进行训练。 ```python transform = transforms.Compose([ transforms.ToTensor(), ]) train_dataset = CustomDataset(train_data_path, transform=transform) val_dataset = CustomDataset(val_data_path, transform=transform) train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True) val_loader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=False) ``` 这里假设有一个自定义的数据集类 `CustomDataset` 可以处理特定格式的数据输入[^3]。 #### 4. 损失函数、优化器以及训练过程 最后一步是设定损失函数（如交叉熵）、选择适当的优化算法（比如 Adam），并且编写循环来迭代整个训练流程。 ```python device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = UNet(n_channels=3, n_classes=num_classes).to(device) criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=learning_rate) for epoch in range(num_epochs): model.train() running_loss = 0.0 for images, masks in train_loader: images = images.to(device) masks = masks.to(device) optimizer.zero_grad() outputs = model(images) loss = criterion(outputs, masks) loss.backward() optimizer.step() running_loss += loss.item() print(f"Epoch [{epoch+1}/{num_epochs}], Loss: {running_loss/len(train_loader)}") # Validation phase can be added here as well. ``` 这段代码展示了如何初始化模型、定义损失计算方式及更新权重的过程[^4]。