李沐动手学深度学习: 手写线性回归

复写:线性回归(不使用pytorch)

%matplotlib inline
import torch
import random
from d2l import torch as d2l

#生成数据集
def synthetic_data(w,b,num_examples):
    #生成y = wX+b+噪声
    #X(生成样本):均值为0,方差为1,size=(num_examples,len(w))
    X = torch.normal(0,1,(num_examples,len(w)))
    #matmul()矩阵乘法
    y = torch.matmul(X,w) + b
    #加上噪声
    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)

#读取数据集:打乱并以小批量的方式获取数据
def data_iter(batch_size,features,labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    #随机读取样本
    random.shuffle(indices)
    for i in range(0,num_examples,batch_size):
        batch_indices = torch.tensor(
        indices[i:min(i+batch_size,num_examples)])
        yield features[batch_indices],labels[batch_indices]

#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)

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

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

#定义优化算法
def sgd(params,lr,batch_size):
    #小批量梯度下降
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()

#训练
lr = 0.03
num_epochs = 3
net = linreg
loss = squared_loss
batch_size = 10

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()
        #使用参数的梯度更新参数
        sgd([w,b],lr,batch_size)
        with torch.no_grad():
            train_l = loss(net(features,w,b),labels)
    print(f'epoch{epoch+1},loss:{float(train_l.mean()):f}')

结果

线性回归简洁实现

import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l

#生成数据集
def synthetic_data(w,b,num_examples):
    #生成y = wX+b+噪声
    #X(生成样本):均值为0,方差为1,size=(num_examples,len(w))
    X = torch.normal(0,1,(num_examples,len(w)))
    #matmul()矩阵乘法
    y = torch.matmul(X,w) + b
    #加上噪声
    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)

#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)

#定义模型
from torch import nn
net = nn.Sequential(nn.Linear(2,1))

#初始化模型参数
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)

#训练
num_epochs = 3
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