动手学深度学习01：线性回归的从零实现与简洁实现

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)