李沐深度学习-03.01线性回归的实现

从零开始实现源代码总结：

#练习 线性回归的从零开始实现
import random
import torch
from d2l import torch as d2l

# 1.生成数据集
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
from torch.utils import data
batch_size = 10
data_iter = data.DataLoader(features,batch_size,shuffle=True)
label_iter = data.DataLoader(labels,batch_size,shuffle=True)

# 3.初始化模型参数
w = torch.normal(0,0.01,size=(2,1),requires_grad = True)
b = torch.zeros(1,requires_grad = True)

# 4.定义模型
def linreg(x,w,b):#线性回归模型
    return torch.matmul(x,w)+b

# 5.定义损失函数 ----均方差
def squard_loss(y_hat,y):
    return (y_hat - y.reshape(y_hat.shape)) ** 2/2

# 6.定义优化算法
def SGD(params,lr,batch_size):
""""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()

# 7.训练
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss

for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y)  # X和y的小批量损失
        # 因为l形状是(batch_size,1)，而不是一个标量。l中的所有元素被加到一起，
        # 并以此计算关于[w,b]的梯度
        l.sum().backward()
        sgd([w, b], lr, batch_size)  # 使用参数的梯度更新参数
    with torch.no_grad():
        train_l = loss(net(features, w, b), labels)
        print(f'epoch {epoch + 1}, loss {float(train_l.mean()):f}')

此处为画图,使用matplotlib

import matplotlib.pyplot as plt
def synthetic_data(w, b, num_examples):  #@save
    """生成y=Xw+b+噪声"""
    X = torch.normal(0, 1, (num_examples, len(w)))
    y = torch.matmul(X, w) + b
    y += torch.normal(0, 0.01, y.shape)
    return X, y.reshape((-1, 1))

true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)
features, labels
plt.scatter(features[:,(1)],labels)
plt.show()

简洁实现代码总结

# 线性回归的简介实现
import numpy
import torch
from torch.utils import data
from d2l import torch as d2l

# 1.生成数据集
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
batch_size = 20
data_iter = data.DataLoader(features,batch_size,shuffle = True)
labels_iter = data.DataLoader(labels,batch_size,shuffle = True)

# 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)  #此处尝试不知零

# 5.定义损失函数
loss = nn.MSELoss()

# 6.定义优化算法
lr = 0.03
trainer = torch.optim.SGD(net.parameters(), lr)

# 7.训练
#先做损失，
num_epochs = 3
for eopch in range(num_epochs):
    for x, y in zip(data_iter,labels_iter):
        l = loss1(net(x),y)#计算损失
        trainer.zero_grad()#梯度置零
        l.backward()#反向传播计算梯度
        trainer.step()#更新梯度
    l = loss(net(features),labels)
    print(f'epoch {epoch + 1}, loss {l: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)

额外的笔记

#接收批量大小的数据
import random
def data_iter(batch_size, features, labenls):
    num_examples = len(features)
    indices = list(range(num_examples)) #indices指标
    random.shuffle(indices) #打乱顺序

读取数据使用DataLOader(data,batch_size)