动手学深度学习-线性回归的从零开始实现代码解读

对代码增加了一些注释，希望能帮到部分朋友

#features就是X，labels就是y

def normal(x, mu, sigma):
    p = 1 / math.sqrt(2 * math.pi * sigma**2)
    return p * np.exp(-0.5 / sigma**2 * (x - mu)**2)
```正态分布函数
def synthetic_data(w, b, num_examples):  #w权重，b偏置，num_example样本数
    """生成 y = Xw + b + 噪声。"""
    X = torch.normal(0, 1, (num_examples, len(w)))#x是均值为0标准差为1的正态分布取值，形状为（num_example,w的尺寸）
    y = torch.matmul(X, w) + b#torch.matlmul是点乘，对应相乘
    y += torch.normal(0, 0.01, y.shape)#噪声
    return X, y.reshape((-1, 1))#reshape（-1，1）是指改为一列，补全行数

true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)

print('features:', features[0], '\nlabel:', labels[0])#其中一个样本

def data_iter(batch_size, features, labels):#迭代器
    num_examples = len(features)
    indices = list(range(num_examples))#给每个数据标签
    # 这些样本是随机读取的，没有特定的顺序
    random.shuffle(indices)#打乱顺序
    for i in range(0, num_examples, batch_size):
        batch_indices = torch.tensor(indices[i:min(i + batch_size, num_examples)])#去从i到i+batch_size 的batch_size个元素
        yield features[batch_indices], labels[batch_indices]#yield就是到这里停止返回对应的features跟labels

batch_size = 10

for X, y in data_iter(batch_size, features, labels):
    print(X, '\n', y)
    break

w = torch.normal(0, 0.01, size=(2, 1), requires_grad=True)#随机取一个权重
b = torch.zeros(1, requires_grad=True)#定义一个偏置

def linreg(X, w, b): 
    """线性回归模型。"""
    return torch.matmul(X, w) + b

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

def sgd(params, lr, batch_size): 
    """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_()

lr = 0.03#学习率
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}')

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}')