李沐线性回归1import random import torch from d2l import torch as d2l #构造数据集 def synthetic_data(w,b,num_exa

import random
import torch
from d2l import torch as d2l
#构造数据集
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)
    return x,y.reshape(-1,1)

#生成批量
def data_iter(batch_size,features,labels):
    num_examples=len(features)
    indices=list(range(num_examples))
    #随机读取样本
    random.shuffle(indices)
    for i in range(0,num_examples,batch_size):
        batch_indices=torch.tensor(
            indices[i:min(i+batch_indices,num_examples)])
        #yield不断地返回直到完成为止
        yield features[batch_indices],labels[batch_indices]
def squared_loss(y_hat,y):
    return (y_hat-y.reshape(y_hat.shape))**2/2
def sgd(params,lr,batch_size):
    with torch.no_grad():
        for param in params:
            param-=lr*param.grad/batch_size
            param.grad.zero_()
w=torch.tensor([2,-3.4])
b=4.2
features,labels=synthetic_data(w,b,1000)
#数据集可视化
'''
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
d2l.plt.show()'''
batch_size=10
'''for x,y in data_iter(batch_size,features,labels)
    print(x,'\n',y)'''
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():
            train1=loss(net(features,w,b),labels)
            print(loss)