3.2.linear-regression-scratch

1
lr = 0.03
2
num_epochs = 3
3
net = linreg
4
loss = squared_loss
5

6
for epoch in range(num_epochs):
7
    for X, y in data_iter(batch_size, features, labels):
8
        l = loss(net(X, w, b), y)  # X和y的小批量损失
9
        # 因为l形状是(batch_size,1)，而不是一个标量。l中的所有元素被加到一起，
10
        # 并以此计算关于[w,b]的梯度
11
        l.sum().backward()
12
        sgd([w, b], lr, batch_size)  # 使用参数的梯度更新参数
13
    with torch.no_grad():
14
        train_l = loss(net(features, w, b), labels)
15
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')