动手学深度学习01:线性回归的从零实现与简洁实现
参考:李沐 《动手学深度学习》 http://zh.d2l.ai/
从零实现
import random
import torch
from d2l import torch as d2l
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)
print('features:', features[0],'\nlabel:', labels[0])
def data_iter(batch_size, features, labels):
num_examples = len(features) # 所有样本的个数
indices = list(range(num_examples)) # 将样本随机打乱
# 这些样本是随机读取的,没有特定的顺序
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]
batch_size = 10
# 得到一组小批量的数据
for X, y in data_iter(batch_size, features, labels):
print(X, '\n', y)
break
# 初始化模型参数
w = torch.normal(0, 0.01, size=(2,1), requires_grad=True) # 均值为0,标准差为0.01
b = torch.zeros(1, requires_grad=True)
# 定义模型
def linreg(X, w, b): #@save
"""线性回归模型"""
return torch.matmul(X, w) + b
# 定义损失函数
def squared_loss(y_hat, y): #@save
"""均方损失"""
return (y_hat - y.reshape(y_hat.shape)) ** 2 / 2 # 将真实值的形状变成与预测值一样
# 定义参数优化算法
def sgd(params, lr, batch_size): #@save
"""小批量随机梯度下降"""
with torch.no_grad(): # 更新的时候不需要进行梯度计算
for param in params:
param -= lr * param.grad / batch_size
param.grad.zero_() # 梯度会累计,计算完梯度后清0
# 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}')
简洁实现
import numpy as np
import torch
from torch.utils import data
from d2l import torch as d2l
from torch import nn
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = d2l.synthetic_data(true_w, true_b, 1000)
def load_array(data_arrays, batch_size, is_train=True): #@save
"""构造一个PyTorch数据迭代器"""
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)
# print(next(iter(data_iter)))
net = nn.Sequential(nn.Linear(2, 1)) # 输入特征形状为 2,输出为标量 1
# 模型参数初始化
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() # 计算梯度前将梯度归为0
l.backward()
trainer.step()
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)