李沐《动手学深度学习》权重衰退(正则化)python代码实现

一、L2正则化手动实现

# 权重衰退手动实现
%matplotlib inline
import torch
from d2l import torch as d2l
from torch import nn

# n_train个训练样本,n_test个测试样本，输入数据维度是200维
n_train, n_test, num_inputs, batch_size = 20, 200, 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)

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]

def L2_penalty(w):
    return torch.sum(w.pow(2)) / 2

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='epoch', ylabel='loss', yscale='log', 
                            xlim=[5, num_epochs], legend=['trian', 'test'])
    
    for epoch in range(num_epochs):
        for X, y in train_iter:
            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())    
    
train(5)

二、L2正则化利用torch框架实现

# 权重衰退简洁实现
%matplotlib inline
import torch
from d2l import torch as d2l
from torch import nn

# n_train个训练样本,n_test个测试样本，输入数据维度是200维
n_train, n_test, num_inputs, batch_size = 20, 200, 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)


def train_concise(lambd):
    net = nn.Sequential(nn.Linear(num_inputs, 1))
    for param in net.parameters():
        param.data.normal_(0, 0.1)
    loss = nn.MSELoss(reduction='none')
    num_epochs, lr= 100, 0.003
    
    trainer = torch.optim.SGD([
        {"params":net[0].weight, "weight_decay":lambd},
        {"params":net[0].bias}
    ], lr=lr)
    
    animator = d2l.Animator(xlabel='epoch', ylabel='loss', yscale='log',
                        xlim=[5, num_epochs], legend=['trian', 'test'])
    for epoch in range(num_epochs):
        for X, y in train_iter:
            trainer.zero_grad()
            l = loss(net(X), y) / batch_size
            l.sum().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：', torch.norm(net[0].weight).item())
    
train_concise(5)