手写数字识别问题代码

### 手写数字识别示例代码

对于手写数字识别的任务，采用PyTorch框架下的卷积神经网络(CNN)是一种常见且高效的方法。下面展示一段基于MNIST数据集的手写数字识别的简化版代码。

#### 设置计算设备并加载所需库

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

#### 数据预处理与加载
为了确保输入到模型的数据格式正确无误[^1]，需对原始图像执行标准化操作。

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

train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)

train_loader = DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=1000, shuffle=False)

#### 定义CNN架构
构建一个简单的两层卷积神经网络来提取特征，并通过全连接层完成分类任务。

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.fc1 = nn.Linear(64*7*7, 128)
        self.fc2 = nn.Linear(128, 10)
        
    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2(x), 2))
        x = x.view(-1, 64*7*7)
        x = F.relu(self.fc1(x))
        output = self.fc2(x)
        return output
model = Net()

#### 训练过程配置
选择合适的激活函数能够增强模型的表现力[^5]；同时定义损失函数和优化策略用于指导权重更新方向。

criterion = nn.CrossEntropyLoss()  
optimizer = optim.Adam(model.parameters(), lr=0.001)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model.to(device)
epochs = 10
for epoch in range(epochs):    
    model.train()
    running_loss = 0.0
    for data, target in train_loader:
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        outputs = model(data)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

print('Finished Training')

#### 测试评估性能
最后，在独立测试集中验证训练好的模型效果如何。

correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        images, labels = images.to(device), labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = 100 * correct / total
print(f'Test Accuracy of the model on {total} test images: {accuracy:.2f}% ')