pytorch：使用两个优化器实现对w，b的区别控制，并只对w进行权重衰减（正则）

def fit_and_plot_pytorch(wd):
    # 对权重参数衰减。权重名称一般是以weight结尾
    net = nn.Linear(num_inputs, 1)
    nn.init.normal_(net.weight, mean=0, std=1)
    nn.init.normal_(net.bias, mean=0, std=1)
    optimizer_w = torch.optim.SGD(params=[net.weight], lr=lr, weight_decay=wd) # 对权重参数衰减
    optimizer_b = torch.optim.SGD(params=[net.bias], lr=lr)  # 不对偏差参数衰减
    
    train_ls, test_ls = [], []
    for _ in range(num_epochs):
        for X, y in train_iter:
            l = loss(net(X), y).mean()
            optimizer_w.zero_grad()
            optimizer_b.zero_grad()
            
            l.backward()
            
            # 对两个optimizer实例分别调用step函数，从而分别更新权重和偏差
            optimizer_w.step()
            optimizer_b.step()
        train_ls.append(loss(net(train_features), train_labels).mean().item())
        test_ls.append(loss(net(test_features), test_labels).mean().item())
    d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
                 range(1, num_epochs + 1), test_ls, ['train', 'test'])
    print('L2 norm of w:', net.weight.data.norm().item())