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

# 定义基本的残差块
class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out

# 定义 ResNet-18 模型
class ResNet18(nn.Module):
    def __init__(self, block, layers, num_classes=1000):
        super(ResNet18, self).__init__()
        self.in_channels = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if stride != 1 or self.in_channels != out_channels * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * block.expansion),
            )

        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x

# 初始化模型
model = ResNet18(BasicBlock, [2, 2, 2, 2])

# 设置设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

# 加载数据集
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'path_to_imagenet_dataset'
image_datasets = {x: datasets.ImageFolder(root=data_dir + x, transform=data_transforms[x])
                  for x in ['train', 'val']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=100,
                             shuffle=True, num_workers=4)
               for x in ['train', 'val']}

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# 训练模型
num_epochs = 10
for epoch in range(num_epochs):
    for phase in ['train', 'val']:
        if phase == 'train':
            model.train()  # 设置模型为训练模式
        else:
            model.eval()   # 设置模型为评估模式

        running_loss = 0.0
        running_corrects = 0

        for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)

            optimizer.zero_grad()

            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)

                if phase == 'train':
                    loss.backward()
                    optimizer.step()

            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / len(image_datasets[phase])
        epoch_acc = running_corrects.double() / len(image_datasets[phase])

        print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')

print('Finished Training')

       在这段代码中，我们定义了一个基本的残差块 BasicBlock 和一个完整的 ResNet-18 模型。我们还定义了一个训练循环，该循环包含训练阶段和验证阶段，以便监控模型在验证集上的性能。

       请注意，为了使这段代码能够运行，你需要替换 'path_to_imagenet_dataset' 为你的 ImageNet 数据集的实际路径。此外，根据你的硬件条件，你可能需要调整批量大小 (batch_size) 和其他超参数以适应你的计算资源。如果要使用其他变体（如 ResNet-34、ResNet-50 等），则需要修改 ResNet18 类中的 _make_layer 方法，并更改 ResNet18 构造函数中的 layers 参数。

ResNet残差神经网络的实现 - 集智数据集