如何使用pytorch写一个数字识别CNN卷积神经网络模型

在PyTorch中创建一个简单的数字识别CNN（Convolutional Neural Network）模型可以分为以下几个步骤：

1. **导入必要的库**:

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms

2. **数据预处理**:

transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]) # MNIST数据集通常需要标准化像素值
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)

3. **定义CNN模型**:

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1)  # 输入通道数，卷积核大小，步长，填充
        self.relu = nn.ReLU()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)  # 最大池化层
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
        self.fc1 = nn.Linear(64 * 7 * 7, 128)  # 全连接层，输入是经过卷积和pooling后的扁平化特征
        self.fc2 = nn.Linear(128, 10)  # 输出层，对应MNIST的10个类别

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = x.view(-1, 64 * 7 * 7)  # 扁平化
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

model = ConvNet()

4. **配置损失函数、优化器和学习率调整策略**:

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min', patience=3)

5. **训练模型**:

for epoch in range(num_epochs):  
    for inputs, labels in train_loader:
        optimizer.zero_grad()  # 清零梯度
        outputs = model(inputs)  # 前向传播
        loss = criterion(outputs, labels)  # 计算损失
        loss.backward()  # 反向传播
        optimizer.step()  # 更新参数
        scheduler.step(loss.item())  # 学习率调整

    print(f"Epoch {epoch+1}/{num_epochs}, Loss: {loss.item():.4f}")

6. **评估模型**:

# 添加测试集和评估代码
test_dataset = ...  # 加载测试集
test_loader = ...
model.eval()  # 转换到评估模式
correct = 0
total = 0
with torch.no_grad():
    for images, labels in test_loader:
        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: {accuracy:.2f}%")