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

# 定义AlexNet模型
class AlexNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x

# 初始化模型
model = AlexNet()

# 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 AlexNet 模型，并设置了数据预处理步骤，包括随机裁剪、翻转以及归一化。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。

AlexNet神经网络基本架构的实现 - 集智数据集