神经网络图像分类代码

使用深度学习中的神经网络进行图像分类，通常会采用卷积神经网络（Convolutional Neural Networks，CNN），因为它们特别适合处理网格状的数据结构，如图片。这里有一个简单的例子，展示如何使用PyTorch构建一个基础的CNN进行图像分类：

import torch
import torchvision
import torchvision.transforms as transforms

# 定义预处理步骤
transform = transforms.Compose([
    transforms.Resize((224, 224)),  # 调整图片尺寸
    transforms.ToTensor(),  # 将像素值转为0-1之间
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 归一化
])

# 加载MNIST数据集
train_dataset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
test_dataset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)

# 数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=32, shuffle=False)

# 构建LeNet-5风格的CNN模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)  # CIFAR10有10个类别

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()

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

# 训练过程
num_epochs = 10
for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    print(f"Epoch {epoch+1}, Loss: {running_loss/len(train_loader)}")

# 测试模型
correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f"Accuracy of the network on the 10000 test images: {100 * correct / total}%")

这个例子使用的是LeNet-5模型，它在原始MNIST数据上已经足够好，但对于更复杂的CIFAR10，可能需要更深的网络或者数据增强等手段。