4.5.weight-decay

1
def train_concise(wd):
2
    net = nn.Sequential(nn.Linear(num_inputs, 1))
3
    for param in net.parameters():
4
        param.data.normal_()
5
    loss = nn.MSELoss(reduction='none')
6
    num_epochs, lr = 100, 0.003
7
    # 偏置参数没有衰减
8
    trainer = torch.optim.SGD([
9
        {"params":net[0].weight,'weight_decay': wd},
10
        {"params":net[0].bias}], lr=lr)
11
    animator = d2l.Animator(xlabel='epochs', ylabel='loss', yscale='log',
12
                            xlim=[5, num_epochs], legend=['train', 'test'])
13
    for epoch in range(num_epochs):
14
        for X, y in train_iter:
15
            trainer.zero_grad()
8 collapsed lines
16
            l = loss(net(X), y)
17
            l.mean().backward()
18
            trainer.step()
19
        if (epoch + 1) % 5 == 0:
20
            animator.add(epoch + 1,
21
                         (d2l.evaluate_loss(net, train_iter, loss),
22
                          d2l.evaluate_loss(net, test_iter, loss)))
23
    print('w的L2范数：', net[0].weight.norm().item())