cifar10数据集分类（注意力机制）

🚀 提升你的深度学习体验！ 🚀

大家好，我是小P学长！我分享了一个 ResNet 模型的 PyTorch 实现，用于训练和测试 CIFAR-10 数据集。这是一个很好的起点，但如果你想在训练时使用 GPU 并添加注意力机制，我有一个特别版本可供博客支持者获取。

💡 特别版本亮点：

• GPU 支持，让你的训练更快速。
• 增加了注意力机制，提升模型性能。

🌟 如何获取特别版本？

1. 支持我的博客https://studentp.cloud/p/search.html?text=，输入关键词查找此项目（比如“注意力机制”、“cifar”等）。
2. 获取宝藏内容。

🎉 感谢你的支持！ 🎉

---

下面是免费分享的代码

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


# Define the Residual Block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1):
        super(ResidualBlock, 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 = nn.Sequential()
        if stride != 1 or in_channels != out_channels:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels)
            )

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


# Define the ResNet-like CNN
class ResNet(nn.Module):
    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 64
        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 = self.make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self.make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self.make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self.make_layer(block, 512, num_blocks[3], stride=2)
        self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, out_channels, num_blocks, stride):
        strides = [stride] + [1] * (num_blocks - 1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_channels, out_channels, stride))
            self.in_channels = out_channels
        return nn.Sequential(*layers)

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


# Load CIFAR-10 dataset
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.RandomCrop(32, padding=4),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False, num_workers=2)

# Define the ResNet model
resnet = ResNet(ResidualBlock, [2, 2, 2, 2])

# Define loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(resnet.parameters(), lr=0.001, momentum=0.9)

print("Training Begin")
# Training the model
for epoch in range(5):  # Change the number of epochs as needed
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()

        outputs = resnet(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()

        if i % 200 == 199:  # Print every 200 batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 200))
            running_loss = 0.0

    # Test the model
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            outputs = resnet(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print(f'epoch:{epoch}')
    print('Accuracy on the test set: %d %%' % (100 * correct / total))

print('Finished Training')