使用Pytorch实现高分遥感图像图像语义分割

### 使用PyTorch实现高分辨率遥感图像语义分割 #### 1. 数据准备 为了进行高分辨率遥感图像的语义分割，首先需要准备好高质量的数据集。这些数据通常由卫星或无人机拍摄而成，具有较高的空间分辨率和丰富的光谱信息。数据集中应包含标注好的像素级标签，用于监督学习。 对于遥感图像而言，常见的公开数据集有ISPRS Potsdam、Massachusetts Buildings Dataset等[^4]。在实际应用中，可能还需要对原始数据进行裁剪、缩放以及标准化预处理操作。 ```python import numpy as np from PIL import Image from torchvision.transforms import Compose, ToTensor, Normalize def preprocess(image_path, label_path=None): image = Image.open(image_path).convert('RGB') if label_path is not None: label = Image.open(label_path) transform_image = Compose([ ToTensor(), Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ]) transformed_image = transform_image(image) if label_path is not None: return transformed_image, np.array(label) else: return transformed_image ``` #### 2. U-Net模型构建 U-Net是一种经典的卷积神经网络架构，在医学影像分析领域取得了显著效果，并被广泛应用于其他类型的图像分割任务上。其结构特点是对称设计——编码器负责提取特征；解码器则通过逐步放大尺寸恢复细节并预测最终掩模。 下面是一个基于PyTorch框架定义的标准U-Net模型： ```python import torch.nn as nn import torch.nn.functional as F 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), nn.BatchNorm2d(mid_channels), nn.ReLU(inplace=True), nn.Conv2d(mid_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 ``` #### 3. 训练流程 完成上述准备工作之后就可以进入正式训练阶段了。这里简单列举几个重要环节：设定损失函数（如交叉熵）、选择合适的优化算法（Adam较为常用），并通过多次迭代调整权重直至收敛为止。 ```python device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = UNet(n_channels=3, n_classes=num_classes).to(device) optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate) loss_fn = nn.CrossEntropyLoss() for epoch in range(num_epochs): model.train() running_loss = 0.0 for images, labels in dataloader: images, labels = images.to(device), labels.long().to(device) optimizer.zero_grad() outputs = model(images) loss = loss_fn(outputs, labels.squeeze(dim=1)) loss.backward() optimizer.step() running_loss += loss.item() avg_loss = running_loss / len(dataloader) print(f"Epoch [{epoch+1}/{num_epochs}], Loss: {avg_loss:.4f}") ``` --- ####