PyTorch实战示例01——regression

Topic：

用神经网络模型来建立一条拟合曲线，帮助了解一群数据的关联关系。

核心知识点讲解：

part01: 创建数据集

import torch 
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt
import numpy as np

x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data(tensor),shape=(100,1)
y = x.pow(2) + 0.2*torch.rand(x.size())  # add nosiy y data(tensor),shape=(100,1)

# torch can only train on Variable, so convert them to Variabel
# the code below is deprecated in PyTorch ,Now ,autograd directly supports tensors
x, y = Variable(x), Variable(y)
# 可视化
plt.scatter(x.data.numpy(), y.data.numpy())
plt.show()

part02: 创建神经网络模型

class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()  # 第一句话，调用父类的构造函数
        self.hidden = torch.nn.Linear(n_feature, n_hidden)  # hidden layer
        self.predict = torch.nn.Linear(n_hidden, n_output)  # output layer
        
    def forward(self, x):
        x = F.relu(self.hidden(x))  # activation function for hidden layer
        x = self.predict(x)  # linear output
        return x

net = Net(n_feature=1, n_hidden=10, n_output=1)  # 输入特征为1，隐藏层10个神经元，输出单变量
print(net)  # net architecture
>>>
Net(
  (hidden): Linear(in_features=1, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=1, bias=True)
)

part03: 构建优化器

具体参考：PyTorch中如何构建一个优化器

optimizer = torch.optim.SGD(net.parameters(), lr=0.2)
loss_func = torch.nn.MSELoss() # this is for regression mean squared loss

part04: 迭代过程可视化

具体参考：Python中使用plt.ion()和plt.ioff()画动态图

plt.ion()  # something about plotting

for t in range(200):
    prediction = net(x)  # input x and predict based on x
    
    loss = loss_func(prediction, y)  # must be (1. nn output, 2. target)
    optimizer.zero_grad()  # clear gradients for next train
    loss.backward()  # backpropagation, compute gradients
    optimizer.step() # apply gradients
    
    if t % 5 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x.data.numpy(), y.data.numpy())
        plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw =5)
        plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size':20,'color':'red'})
        plt.pause(0.1)
        
plt.ioff()
plt.show()