深度学习08线性回归的简洁实现

#线性回归的简洁实现
import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l

true_w = torch.tensor([2,-3.4])
true_b = 4.2
features,labels = d2l.synthetic_data(true_w,true_b,1000)

def load_array(data_arrays,batch_size,is_train=True):
    #构造一个pytorch数据迭代器
    #将输入的两类数据进行一一对应
    dataset = data.TensorDataset(*data_arrays)
    #重新排序
    return data.DataLoader(dataset,batch_size,shuffle=is_train)

batch_size = 10
data_iter = load_array((features,labels),batch_size)

print(next(iter(data_iter))) #得到一组数据
#nn是神经网络的缩写
from torch import nn
#Sequential 一个有序的容器 神经网络模块按照传入构造器的顺序依次被添加到计算图中执行
net = nn.Sequential(nn.Linear(2,1))#输入是2 输出是1

net[0].weight.data.normal_(0,0.01)#w 正太分布 0 0.01
net[0].bias.data.fill_(0)#偏差

loss = nn.MSELoss() #计算均方MESLoss 也称为平方范数

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

num_epochs=3
for epoch in range(num_epochs):
    for x,y in data_iter:
        l = loss(net(x),y)
        trainer.zero_grad()
        l.backward()
        trainer.step()
    l = loss(net(features),labels)
    print(f'epoch {epoch+1}, loss {l:f}')