训练的套路

1.定义网络net(X)

2.定义损失函数l=loss(net(X),Y)

数据集（X,Y）

def squared_loss(y_hat, y):  #@save
    """均方损失。"""
    return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2

3.定义优化算法

def sgd(params, lr, batch_size):  #@save
    """小批量随机梯度下降。"""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()

4.训练

• 初始化参数
• 重复，直到完成
  • 计算梯度
  • 更新参数
• 
  ```python 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}')

<a name="QEsQU"></a>
## 简洁实现
定义网络
```python
# `nn` 是神经网络的缩写
from torch import nn

net = nn.Sequential(nn.Linear(2, 1))

初始化参数

net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)

定义损失函数

loss = nn.MSELoss()

3.定义优化函数

trainer = torch.optim.SGD(net.parameters(), lr=0.03)

4.训练

num_epochs = 3
for epoch in range(num_epochs):
    for X, y in data_iter:
        l = loss(net(X) ,y)
           """梯度清零"""
        trainer.zero_grad()
        """计算梯度"""
        l.backward()
        """执行优化步骤"""
        trainer.step()
    l = loss(net(features), labels)
    print(f'epoch {epoch + 1}, loss {l:f}')