lenet5手写数字识别pytorch

以下是使用PyTorch实现LeNet-5手写数字识别的示例代码：

1. 导入所需的库

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

2. 定义LeNet-5模型

class LeNet5(nn.Module):
    def __init__(self):
        super(LeNet5, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, kernel_size=5, stride=1)
        self.pool1 = nn.AvgPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(6, 16, kernel_size=5, stride=1)
        self.pool2 = nn.AvgPool2d(kernel_size=2, stride=2)
        self.fc1 = nn.Linear(16*4*4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool1(torch.relu(self.conv1(x)))
        x = self.pool2(torch.relu(self.conv2(x)))
        x = x.view(-1, 16*4*4)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

3. 定义训练函数

def train(model, train_loader, criterion, optimizer, device):
    model.train()
    running_loss = 0.0
    for i, (inputs, labels) in enumerate(train_loader, 0):
        inputs, labels = inputs.to(device), labels.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

    epoch_loss = running_loss / len(train_loader)
    return epoch_loss

4. 定义测试函数

def test(model, test_loader, criterion, device):
    model.eval()
    correct = 0
    total = 0
    running_loss = 0.0
    with torch.no_grad():
        for data in test_loader:
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            running_loss += loss.item()
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    epoch_loss = running_loss / len(test_loader)
    epoch_accuracy = 100 * correct / total
    return epoch_loss, epoch_accuracy

5. 加载数据集并进行数据预处理

transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.1307,), (0.3081,))])

train_data = MNIST(root='data', train=True, download=True, transform=transform)
test_data = MNIST(root='data', train=False, download=True, transform=transform)

train_loader = DataLoader(train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(test_data, batch_size=64, shuffle=False)

6. 设置超参数并进行训练

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = LeNet5().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())

num_epochs = 10
for epoch in range(num_epochs):
    train_loss = train(model, train_loader, criterion, optimizer, device)
    test_loss, test_accuracy = test(model, test_loader, criterion, device)
    print(f"Epoch {epoch+1}/{num_epochs} - train_loss: {train_loss:.4f} - test_loss: {test_loss:.4f} - test_accuracy: {test_accuracy:.2f}%")

运行以上代码后，即可对MNIST手写数字进行识别。