import random
import torch
from d2l import torch as d2l

# 人造数据集
def synthetic_data(w,b,num_examples):
    X=torch.normal(0,1,(num_examples,len(w)))
    y=torch.matmul(X,w)+b
    y+=torch.normal(0,0.01,y.shape) # 加入噪声
    return X,y.reshape(-1,1) # y从行向量转为列向量
true_w=torch.tensor([2,-3.4])
true_b=4.2
features,labels=synthetic_data(true_w,true_b,1000)

print('features:',features[0],'\nlabels:',labels[0])

#绘图展示
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),
                labels.detach().numpy(),1);
d2l.plt.show()
# 读数据集
def data_iter(batch_size,features,labels):
    num_examples=len(features) #看一下有多少个样本
    indices=list(range(num_examples))# 生成0-999的元组，然后将range()返回的可迭代对象转为一个列表
    random.shuffle(indices)# 将序列的所有元素随机排序(打乱下标)
    for i in range(0,num_examples,batch_size): #从0到最后，每次取batch_size个大小
        batch_indices=torch.tensor(indices[i:min(i+batch_size,num_examples)]) #超出样本个数没有拿满的话取最小值
        yield features[batch_indices],labels[batch_indices]

batch_size=10
for X,y in data_iter(batch_size,features,labels):#给一些样本标号，每一次随机从里面选取b个样本返回
    print(X,'\n',y)
    break


#定义初始化模型参数
w=torch.normal(0,0.01,size=(2,1),requires_grad=True)
b=torch.zeros(1,requires_grad=True)
#定义模型
def linreg(X,w,b):
    return torch.matmul(X,w)+b

#定义损失函数
def squared_loss(y_hat,y): #均方损失
    return (y_hat-y.reshape(y_hat.shape))**2/2
#定义优化算法
def sgd(params,lr,batch_size):
    with torch.no_grad():
        for param in params:
            param-=lr*param.grad/batch_size
            param.grad.zero_()

#训练过程
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)
        l.sum().backward()
        sgd([w,b],lr,batch_size)
    with torch.no_grad():
        train_l=loss(net(features,w,b),labels)
        print(f'epoch{epoch+1},loss{float(train_l.mean()):f}')

#比较真实参数和训练得来的参数评估训练的成功程度
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}')

运行结果