动手深度学习-3.3 线性回归的简洁实现

深度学习框架为我们实现了：数据迭代器、损失函数、优化器、神经网络层等。

3.2.1 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)

3.2.2 读取数据集

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)

-使用iter构造Python迭代器，并使用next从迭代器中获取第一项。

next(iter(data_iter))

3.3.3 定义模型

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

3.3.4 初始化模型参数

net[0].weight.data.normal_(0, 0.01)
net[0].bias.data.fill_(0)

3.3.5 定义损失函数

loss = nn.MSELoss()

3.3.6 定义优化算法

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

3.3.7 训练

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

• 比较真实参数和训练模型获得的模型参数

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)