pytorch使用正则化

PyTorch中使用正则化可以通过在模型的定义中加入相应的正则化项来实现。常见的正则化方法有L1正则化和L2正则化。

以L2正则化为例，可以在模型定义中的优化器中添加weight_decay参数，即可实现L2正则化。具体代码如下：

import torch
import torch.nn as nn
import torch.optim as optim

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)

    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

# 定义模型
net = Net()

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

# 训练模型
for epoch in range(10):  # 多批次循环
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # 获取输入
        inputs, labels = data

        # 梯度清零
        optimizer.zero_grad()

        # 正向传播，反向传播，优化
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 统计损失值
        running_loss += loss.item()
        if i % 2000 == 1999:  # 每2000批次打印一次平均损失值
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

在优化器中设置weight_decay参数即可实现L2正则化。其中weight_decay参数的值越大，L2正则化的程度越大。