机器学习系列之线性回归

线性回归的从零开始实现

import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

num_inputs = 2
num_examples = 1000
w = [2, -3.4]
b = 4.2
features = torch.from_numpy(np.random.normal(0, 1, (num_examples, num_inputs)))
labels = w[0]*features[:, 0] + w[1]* features[:, 1] + b
labels += torch.from_numpy(np.random.normal(0, 0.01, size = labels.size()))

def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    random.shuffle(indices)
    for i in range(0, num_examples, batch_size):
        j = torch.LongTensor(indices[i:min(i + batch_size, num_examples)])
        yield features.index_select(0, j), labels.index_select(0, j)
        
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)))
b = torch.zeros(1)
w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

def linreg(X, w, b):
    return torch.mm(X, w) + b

def squared_loss(y_hat, y):
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

def sgd(params, lr, batch_size):
    for param in params:
        param.data -= lr * param.grad / batch_size

batch_size = 10
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).sum()
        l.backward()
        sgd([w, b], lr, batch_size)
        w.grad.data.zero_()
        b.grad.data.zero_()
    train_l = loss(net(features, w, b), labels)
    print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))

epoch 1, loss 0.033245
epoch 2, loss 0.000145
epoch 3, loss 0.000053

print(true_w, '\n', w)
print(true_b, '\n', b)

tensor([[ 2.0009], [-3.4001]], dtype=torch.float64, requires_grad=True)
tensor([[ 2.0009], [-3.4001]], dtype=torch.float64, requires_grad=True)
tensor([4.1995], requires_grad=True)
tensor([4.1995], requires_grad=True)

线性回归的简洁实现

import torch
import numpy as np

num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples,
num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

# 读取数据
import torch.utils.data as Data
batch_size = 10
# 将训练数据的特征和标签组合
dataset = Data.TensorDataset(features, labels)
# 随机读取小批量
data_iter = Data.DataLoader(dataset, batch_size, shuffle=True)

import torch.nn as nn

# class LinearNet(nn.Module):
#     def __init__(self, n_feature):
#         super(LinearNet, self).__init__()
#         self.linear = nn.Linear(n_feature, 1)
#         # forward 定义前向传播
#     def forward(self, x):
#         y = self.linear(x)
#         return y
    
# net = LinearNet(num_inputs)
from collections import OrderedDict
net = nn.Sequential(OrderedDict([
    ('linear', nn.Linear(num_inputs, 1))
    # ......
    ]))

from torch.nn import init
init.normal_(net[0].weight, mean=0, std=0.01)
init.constant_(net[0].bias, val=0) # 也可以直接修改bias的data:
net[0].bias.data.fill_(0)

loss = nn.MSELoss()

import torch.optim as optim
optimizer = optim.SGD(net.parameters(), lr=0.03)

num_epochs = 3
for epoch in range(1, num_epochs + 1):
    for X, y in data_iter:
        output = net(X)
        l = loss(output, y.view(-1, 1))
        optimizer.zero_grad() # 梯度清零,等价于net.zero_grad()
        l.backward()
        optimizer.step()
    print('epoch %d, loss: %f' % (epoch, l.item()))

epoch 1, loss: 0.000086
epoch 2, loss: 0.000026
epoch 3, loss: 0.000095

dense = net[0]
print(true_w, dense.weight)
print(true_b, dense.bias)

[2, -3.4] Parameter containing: tensor([[ 1.9999, -3.3998]], requires_grad=True)
4.2 Parameter containing: tensor([4.1996], requires_grad=True)