怎么才能在百度上打广告_短视频关键词seo优化_王通seo赚钱培训_软文什么意思范例

1.权重衰减是最广泛使用的正则化技术之一

%matplotlib inline
import torch
from torch import nn
from d2l import torch as d2l

2.生成数据

n_train, n_test, num_inputs, batch_size = 20, 100, 200, 5
true_w, true_b = torch.ones((num_inputs, 1)) * 0.01, 0.05
train_data = d2l.synthetic_data(true_w, true_b, n_train)
train_iter = d2l.load_array(train_data, batch_size)
test_data = d2l.synthetic_data(true_w, true_b, n_test)
test_iter = d2l.load_array(test_data, batch_size, is_train=False)

3.初始化模型参数

def init_params():w = torch.normal(0, 1, size=(num_inputs, 1), requires_grad=True)b = torch.zeros(1, requires_grad=True)return [w, b]

4.定义L2范数惩罚

def l2_penalty(w):return torch.sum(w.pow(2)) / 2

5.定义训练代码实现

def train(lambd):w, b = init_params()net, loss = lambda X: d2l.linreg(X, w, b), d2l.squared_lossnum_epochs, lr = 100, 0.003animator = 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())

6.忽略正则化直接训练

train(lambd=0)

7.使用权重衰减来运行代码。这里训练误差增大，但测试误差减小。

train(lambd=3)

8.简洁实现

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},{"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())

9.训练过程中使用train_concise方法查看损失函数（loss）变化情况

train_concise(0)

​​​​​​​train_concise(3)