线性回归的简洁实现

1、生成数据集

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)

2、读取数据集

def load_array(data_arrays, batch_size, is_train=True): 
    # 布尔值is_train表示是否希望数据迭代器对象在每个迭代周期内打乱数据
    """构造一个PyTorch数据迭代器"""
    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)
next(iter(data_iter))

结果：

3、定义模型

from torch import nn
net = nn.Sequential(nn.Linear(2, 1))

4、初始化模型参数

net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)
#均值为 0，标准差为 0.01

5、定义损失函数

loss = nn.MSELoss()

6、定义优化算法

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

7、训练

num_epochs = 5
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}')

结果：

来源李沐老师，仅供学习