线性回归3

本章节直接使用pytorch的Module模块进行处理

数据获取

为了便于分析，我们使用y = 5x+6模拟生成一些数据

import torch as tt
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random
num_inputs = 1#特征个数，这里是验证一元线性回归，因此只有一个
num_examples = 2000#样本数量
true_w = 5
true_b = 6
features = tt.from_numpy(np.random.normal(0,1,(num_examples, num_inputs)))
labels = true_w * features[:,0] + true_b

features.shape , labels.shape

(torch.Size([2000, 1]), torch.Size([2000]))

增加一些噪声数据表示干扰数据

labels +=tt.from_numpy(np.random.normal(0,1, size = labels.size()))

plt.plot([-3, 3],[true_w*-3 + true_b,true_w*3 + true_b])#实际直线
plt.scatter(features[:,0].numpy(), labels.numpy(),1, c='#ff0000')#待预测点

使用torch data方式

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)
# 随机读取小批量数据
data_iter = Data.DataLoader(dataset, batch_size, shuffle=True)

for X, y in data_iter:
    print(X, y)
    break

tensor([[ 0.8268],
        [-0.3417],
        [ 1.0532],
        [-0.7464],
        [ 0.2127],
        [ 1.5058],
        [-1.8164],
        [ 0.3935],
        [-1.7147],
        [ 0.4632]], dtype=torch.float64) tensor([10.1198,  0.1464, 12.5457,  3.1294,  5.1193, 13.0932, -1.6789,  8.5371,
        -3.2574,  7.9574], dtype=torch.float64)

定义模型

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)
print(net) # 使⽤用print可以打印
for param in net.parameters():
    print(param)

LinearNet(
  (linear): Linear(in_features=1, out_features=1, bias=True)
)
Parameter containing:
tensor([[0.3936]], requires_grad=True)
Parameter containing:
tensor([-0.7839], requires_grad=True)

初始化模型参数

from torch.nn import init
init.normal_(net.linear.weight, mean = 0, std = 0.01 )
init.constant_(net.linear.bias, val = 0)

Parameter containing:
tensor([0.], requires_grad=True)

print(net) # 使⽤用print可以打印
for param in net.parameters():
    print(param)

LinearNet(
  (linear): Linear(in_features=1, out_features=1, bias=True)
)
Parameter containing:
tensor([[0.0089]], requires_grad=True)
Parameter containing:
tensor([0.], requires_grad=True)

优化算法

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

SGD (
Parameter Group 0
    dampening: 0
    lr: 0.03
    momentum: 0
    nesterov: False
    weight_decay: 0
)

optimizer.param_groups 

[{'params': [Parameter containing:
   tensor([[0.0089]], requires_grad=True),
   Parameter containing:
   tensor([0.], requires_grad=True)],
  'lr': 0.03,
  'momentum': 0,
  'dampening': 0,
  'weight_decay': 0,
  'nesterov': False}]

训练模型

num_epochs = 3
loss = nn.MSELoss()
for epoch in range(1, num_epochs+1):
    for x, y in data_iter:
        output = net(x.float())#模型输出
        l = loss(output.float(), y.view(-1,1).float())#计算损失指
        net.zero_grad()#梯度清零
        l.backward()#反向传播
        optimizer.step()#更新权重参数
    print('--------------epoch {}, loss {}'.format(epoch, l))
    for param in net.parameters():
        print(param)

--------------epoch 1, loss 1.6837152242660522
Parameter containing:
tensor([[5.0119]], requires_grad=True)
Parameter containing:
tensor([5.9765], requires_grad=True)
--------------epoch 2, loss 0.9597989320755005
Parameter containing:
tensor([[4.9659]], requires_grad=True)
Parameter containing:
tensor([5.9982], requires_grad=True)
--------------epoch 3, loss 1.4597216844558716
Parameter containing:
tensor([[4.9286]], requires_grad=True)
Parameter containing:
tensor([6.0770], requires_grad=True)

如上所示，训练3个epochs既可以达到真实的精度了