© 2023 yanghn. All rights reserved. Powered by Obsidian
4.5 权重衰退
要点
- 是一种正则化技术,基本所有类型的网络都适用
1. 定义
对于参数我们增加一个对 w 的 L2 正则项的惩罚:
笔记
通常不限制
计算梯度:
这个
2. 权重衰退的复杂实现
def train(lambd):
w, b = init_params()
net, loss = lambda X: d2l.linreg(X, w, b), d2l.squared_loss
num_epochs, lr = 100, 0.003
animator = d2l.Animator(xlabel='epochs', ylabel='loss', yscale='log',
xlim=[5, num_epochs], legend=['train', 'test'])
for epoch in range(num_epochs):
for X, y in train_iter:
# 增加了L2范数惩罚项,
# 广播机制使l2_penalty(w)成为一个长度为batch_size的向量
l = loss(net(X), y) + lambd * l2_penalty(w)
l.sum().backward()
d2l.sgd([w, b], lr, batch_size)
if (epoch + 1) % 5 == 0:
animator.add(epoch + 1, (d2l.evaluate_loss(net, train_iter, loss),
d2l.evaluate_loss(net, test_iter, loss)))
print('w的L2范数是:', torch.norm(w).item())
3. 权重衰退的的简洁实现
笔记
权重衰退既可以写在损失函数里面,也可以写在优化器里面
def train_concise(wd):
net = nn.Sequential(nn.Linear(num_inputs, 1))
for param in net.parameters():
param.data.normal_()
loss = nn.MSELoss(reduction='none')
num_epochs, lr = 100, 0.003
# 偏置参数没有衰减
trainer = torch.optim.SGD([
{"params":net[0].weight,'weight_decay': wd}, # 这里设置权重衰退
{"params":net[0].bias}], lr=lr)
animator = d2l.Animator(xlabel='epochs', ylabel='loss', yscale='log',
xlim=[5, num_epochs], legend=['train', 'test'])
for epoch in range(num_epochs):
for X, y in train_iter:
trainer.zero_grad()
l = loss(net(X), y)
l.mean().backward()
trainer.step()
if (epoch + 1) % 5 == 0:
animator.add(epoch + 1,
(d2l.evaluate_loss(net, train_iter, loss),
d2l.evaluate_loss(net, test_iter, loss)))
print('w的L2范数:', net[0].weight.norm().item())