pytorch语义分割最终分类代码

以下是一个简单的 PyTorch 语义分割的分类代码，仅供参考：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import transforms, datasets

# 定义数据预处理
transform = transforms.Compose([
    transforms.Resize((256, 256)),
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

# 加载数据集
train_dataset = datasets.Cityscapes('./data', split='train', mode='fine', target_type='semantic', transform=transform)
train_loader = DataLoader(train_dataset, batch_size=4, shuffle=True)

# 定义模型
class SegNet(nn.Module):
    def __init__(self):
        super(SegNet, self).__init__()
        self.encoder = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 128, kernel_size=3, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(128, 256, kernel_size=3, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 512, kernel_size=3, padding=1),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )
        self.decoder = nn.Sequential(
            nn.ConvTranspose2d(512, 256, kernel_size=2, stride=2),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.ConvTranspose2d(256, 128, kernel_size=2, stride=2),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.ConvTranspose2d(128,64, kernel_size=2, stride=2),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.ConvTranspose2d(64, 34, kernel_size=2, stride=2)
        )

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
model = SegNet()
model.train()
for epoch in range(10):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    print('[%d] loss: %.3f' % (epoch + 1, running_loss / len(train_loader)))

# 测试模型
test_dataset = datasets.Cityscapes('./data', split='val', mode='fine', target_type='semantic', transform=transform)
test_loader = DataLoader(test_dataset, batch_size=4, shuffle=True)
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for data in test_loader:
        images, labels = data
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0) * labels.size(1) * labels.size(2)
        correct += (predicted == labels).sum().item()
    print('Accuracy of the network on the test images: %d %%' % (100 * correct / total))