Pytorch API实现线性回归

import torch
import numpy as np
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)


#读取数据集  data模块
# def load_array(data_arrays,batch_size,is_train=True):
#
#     dataset = data.TensorDataset(*data_arrays)
#     return data.DataLoader(dataset,batch_size,shuffle=is_train)

batch_size = 10
# data_iter = load_array((features,labels),batch_size)
data_iter = data.DataLoader(data.TensorDataset(*(features,labels)),batch_size=batch_size,shuffle=True)

# print(next(iter(data_iter)))  #使用iter构造成迭代器

from torch import nn

#在Pytorch中，全连接层在Linear类中定义  输入到输出
net = nn.Sequential(nn.Linear(2,1))  #2表示输入形状，1表示输出

# 设置参数
net[0].weight.data.normal_(0,0.01)
net[0].bias.data.fill_(0)

#定义损失函数
loss = nn.MSELoss()

#定义优化算法
trainer = torch.optim.SGD(net.parameters(),lr = 0.03)
#SGD表示随机梯度下降算法

num_epochs = 3
for epoch in range(num_epochs):
    for x, y in data_iter:
        l = loss(net(x),y)  #1.计算损失
        trainer.zero_grad()
        l.backward()  #计算梯度
        trainer.step()  #通过优化器更新模型参数
    l = loss(net(features),labels)
    print(f'epoch{epoch+1},loss{1:f}')

w = net[0].weight.data
print('w的估计误差：', true_w - w.reshape(true_w.shape))
b = net[0].bias.data
print('b的估计误差：', true_b - b)