PyTorch——简洁实现线性回归

参考链接

1. https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter03_DL-basics/3.3_linear-regression-pytorch

人工构建数据集

为了简便，人工构建一个样本数为1000，特征数为2的数据集，模型的真实权重设为${\left[2,-3.4\right]}^T$，偏差为4.2，并为数据添加了服从$N\left(0,0.01\right)$分布的噪声。

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)

加载数据

使用PyTorch的DataLoader可以方便地小批量加载数据。

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)

线性回归模型

使用一个全连接层就可以了。

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

模型参数初始化

from torch.nn import init

init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)  # 也可以直接修改bias的data: net.linear.bias.data.fill_(0)

损失函数

使用PyTorch自带的MSE损失。

loss = nn.MSELoss()

优化方法

import torch.optim as optim

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

开始训练

依然需要注意梯度清零操作。

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()))

完整代码

import torch
import numpy as np
import torch.nn as nn

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)

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)


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 torch.nn import init

init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)  # 也可以直接修改bias的data: net.linear.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()))

dense = net.linear
print(true_w, dense.weight)
print(true_b, dense.bias)