在练习3.12-权重衰减时，运行如下代码报错：

#定义和训练测试
batch_size,num_epochs,lr = 1,100,0.003
net,loss = d2l.linreg,d2l.squared_loss

dataset = torch.utils.data.TensorDataset(train_features,train_labels)
train_iter = torch.utils.data.DataLoader(dataset,batch_size,shuffle=True)

def fit_and_plot(lambd):
    w,b = init_params()
    train_ls,test_ls = [],[]
    for _ in range(num_epochs):
        for X,y in train_iter:
            #添加了L2范数惩罚项
            l = loss(net(X,w,b),y) + lambd * l2_penalty(w)
            l = l.sum()
            
            if w.grad is not None:
                w.grad.data.zero_()
                b.grad.data.zero_()
            l.backward()
            d2l.sgd([w,b],lr,batch_size)
        train_ls.append(loss(net(train_features,w,b),train_labels).mean().item())
        test_ls.append(loss(net(test_features,w,b),test_labels).mean().item())
        d2l.semilogy(range(1,num_epochs + 1),tr