PyTorch线性回归实战-CSDN博客

import numpy as np
import matplotlib.pyplot as plt
from torch import  nn,optim
from  torch.autograd import Variable
import torch

x_data = np.random.rand(100)
noise = np.random.normal(0,0.01,x_data.shape)
y_data = x_data * 0.1 + 0.2 + noise

#plt.scatter(x_data,y_data)

#plt.show()

x_data = x_data.reshape(-1,1)
y_data = y_data.reshape(-1,1)

#把numpy转换成tensor
x_data = torch.FloatTensor(x_data)
y_data = torch.FloatTensor(y_data)

inputs = Variable(x_data)
target = Variable(y_data)

#构造神经网络模型
#一般把网络中具有可学习参数的层放在__init__()中
class LinearRegression(nn.Module):
    #定义网络结构
    def __init__(self):
        #初始化nn.Module
        super(LinearRegression,self).__init__()
        self.fc = nn.Linear(1,1)    #输入一个神经元，输出一个神经元

    #定义网络计算
    def forward(self,x):
        out = self.fc(x)
        return out

#定义模型
model = LinearRegression()
#定义代价函数
mse_loss = nn.MSELoss()     #均方差
#定义优化器
optimizer = optim.SGD(model.parameters(),lr=0.12)

for name,parameters in model.named_parameters():
    print('name:{},param{}'.format(name,parameters))


for i in range(1001):
    out = model(inputs)
    #计算loss
    loss = mse_loss(out,target)
    #梯度清0
    optimizer.zero_grad()
    #计算梯度
    loss.backward()
    #修改权值
    optimizer.step()

    if i%200 == 0:
        print(i,loss.item())

y_pred = model(inputs)
plt.scatter(x_data,y_data)
plt.plot(x_data,y_pred.data.numpy(),'r-',lw=3)
plt.show()

输出结果：

name:fc.weight,paramParameter containing:
tensor([[0.4223]], requires_grad=True)
name:fc.bias,paramParameter containing:
tensor([0.2428], requires_grad=True)
0 0.044960808008909225
200 9.83995632850565e-05
400 8.766111568547785e-05
600 8.763602090766653e-05
800 8.763596270000562e-05
1000 8.763596270000562e-05

Pytorch线性回归