线性回归LinearRegression的代码

这段代码整理自：《动手深度学习》

一，理论部分：

代码部分至今有一点不理解的是backward函数是怎么进行梯度累加的

# 随机梯度下降函数
def sgd(params, lr, batch_size):
    for param in params:
        param.data -= lr * param.grad / batch_size

图片其中β与上面sgd函数的batch_size是一个意思，代表同一个含义
lr表示η

二，代码

使用pycharm或者datashell来运行ipynb文件

%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
# num_examples行，num_inputs列的numpy数组，特征值
features = torch.from_numpy(np.random.normal(0, 1, (num_examples, num_inputs)))
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.from_numpy(np.random.normal(0, 0.01, size=labels.size()))

print(features[0], labels[0])


def use_svg_display():
    display.set_matplotlib_formats('svg')


def set_figsize(figsize=(3.5, 2.5)):
    use_svg_display()
    plt.rcParams['figure.figsize'] = figsize


set_figsize()
# 0.5是代表一个点的大小
# features[:, 1].numpy()是所有的特征x1，x2
# labels.numpy()是所有的预测结果
plt.scatter(features[:, 1].numpy(), labels.numpy(), 0.5)


def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    # 把indices列表彻底的打乱顺序，改变indices列表
    random.shuffle(indices)
    for i in range(0, num_examples, batch_size):
        j = torch.LongTensor(indices[i:min(i + batch_size, num_examples)])
        yield features.index_select(0, j), labels.index_select(0, j)


batch_size = 10
for x, y in data_iter(batch_size, features, labels):
    print(x, y)
    break
# 随机产生的符合正态分布的权重w数组
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.double)
b = torch.zeros(1, dtype=torch.double)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)


# 矩阵相乘
def linreg(X, w, b):
    return torch.mm(X, w) + b

# 平方误差函数
def squared_loss(y_hat, y):
	#view与reshape函数基本等价
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

# 随机梯度下降函数
def sgd(params, lr, batch_size):
    for param in params:
        param.data -= lr * param.grad / batch_size


lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
# 训练模型需要num_epochs个迭代周期
for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y).sum()
        l.backward()
        sgd([w, b], lr, batch_size)
		#w，b都进行梯度归零，防止梯度累加
        w.grad.data.zero_()
        b.grad.data.zero_()
    train_l = loss(net(features, w, b), labels)
    print('epoch %d ,loss %f' % (epoch + 1, train_l.mean().item()))

print('true_w = ', true_w)
print('w = ', w)
print('true_b = ', true_b)
print('b = ', b)

三，运行结果

如图所示：