1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
|
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
for epoch in range(num_epochs):
for X, y in data_iter(batch_size, features, labels):
l = loss(net(X, w, b), y) # X和y的小批量损失
# 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,
# 并以此计算关于[w,b]的梯度
l.sum().backward()
sgd([w, b], lr, batch_size) # 使用参数的梯度更新参数
with torch.no_grad():
train_l = loss(net(features, w, b), labels)
print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')
# epoch 1, loss 0.037387
# epoch 2, loss 0.000139
# epoch 3, loss 0.000052
# 误差
print(f'w的估计误差: {true_w - w.reshape(true_w.shape)}')
print(f'b的估计误差: {true_b - b}')
# w的估计误差: tensor([ 0.0004, -0.0006], grad_fn=<SubBackward0>)
# b的估计误差: tensor([0.0007], grad_fn=<RsubBackward1>)
|