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