ResNet18实现Cifar10分类

好的，以下是使用PyTorch实现ResNet18对Cifar10数据集进行分类的步骤：

1. 导入必要的库和模块：

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

2. 定义数据预处理：

transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

3. 加载数据集：

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                         shuffle=False, num_workers=2)

4. 定义ResNet18模型：

class ResNet18(nn.Module):
    def __init__(self, num_classes=10):
        super(ResNet18, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(64)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(128)
        )
        self.layer3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(256),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(256)
        )
        self.layer4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(512),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1, bias=False),
            nn.BatchNorm2d(512)
        )
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.layer1(x) + x
        x = self.layer2(x) + x
        x = self.layer3(x) + x
        x = self.layer4(x) + x
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

5. 定义损失函数和优化器：

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=5e-4)

6. 定义训练函数：

def train(net, trainloader, criterion, optimizer, epoch):
    net.train()

    train_loss = 0
    correct = 0
    total = 0

    for batch_idx, (inputs, targets) in enumerate(trainloader):
        inputs, targets = inputs.to(device), targets.to(device)
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()

    print('Epoch: %d | Loss: %.3f | Acc: %.3f%% (%d/%d)' %
          (epoch+1, train_loss/(batch_idx+1), 100.*correct/total, correct, total))

7. 定义测试函数：

def test(net, testloader, criterion, epoch):
    net.eval()

    test_loss = 0
    correct = 0
    total = 0

    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs, targets = inputs.to(device), targets.to(device)
            outputs = net(inputs)
            loss = criterion(outputs, targets)

            test_loss += loss.item()
            _, predicted = outputs.max(1)
            total += targets.size(0)
            correct += predicted.eq(targets).sum().item()

    print('Epoch: %d | Loss: %.3f | Acc: %.3f%% (%d/%d)' %
          (epoch+1, test_loss/(batch_idx+1), 100.*correct/total, correct, total))

8. 开始训练和测试：

device = 'cuda' if torch.cuda.is_available() else 'cpu'
net = ResNet18().to(device)

for epoch in range(200):
    train(net, trainloader, criterion, optimizer, epoch)
    test(net, testloader, criterion, epoch)

    if (epoch + 1) % 50 == 0:
        optimizer.param_groups[0]['lr'] /= 10

最后，训练完毕后可以保存模型，以便后续使用：

torch.save(net.state_dict(), 'resnet18_cifar10.pth')