pytorch学习：一元线性回归代码

最新推荐文章于 2025-06-03 14:58:58 发布

xckkcxxck

最新推荐文章于 2025-06-03 14:58:58 发布

阅读量516

点赞数

CC 4.0 BY-SA版权

分类专栏：机器学习 pytorch

本文链接：https://blog.youkuaiyun.com/xckkcxxck/article/details/81479090

机器学习同时被 2 个专栏收录

29 篇文章

订阅专栏

pytorch

23 篇文章

订阅专栏

本文通过使用PyTorch库实现线性回归模型，详细介绍了如何准备数据、定义模型结构、设置损失函数与优化器，并通过迭代训练提高模型准确性。最终展示了训练结果及预测曲线。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# -*- coding: utf-8 -*-
"""
Created on Tue Aug  7 11:15:54 2018

@author: www
"""
import numpy as np
import torch
from torch import nn
from torch import optim
from torch.autograd import Variable
import matplotlib.pyplot as plt


x_train = np.array([ [3.3], [4.4], [5.5],[6.71], [6.93], [4.168],
                     [9.779], [6.182], [7.59], [2.167], [7.042],
                     [10.791], [5.313], [7.997], [3.1]] , dtype=np.float32)

y_train = np.array([ [3.3], [4.4], [55],[6.71], [6.93], [4.168],
                     [9.779], [6.182], [7.59], [2.167], [7.042],
                     [10.791], [5.313], [7.997], [3.1]] , dtype=np.float32)

x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)

class LinearRegression(nn.Module):
     def __init__(self):
          super(LinearRegression, self).__init__()
          self.linear = nn.Linear(1, 1)     #input and output is 1 dimension
          
     def forward(self, x):
          out = self.linear(x)
          return out
if torch.cuda.is_available():
     model = LinearRegression().cuda()
else:
     model = LinearRegression()
     
criterion = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr = 1e-3)

num_epochs = 1000
for epoch in range(num_epochs):
     if torch.cuda.is_available():
          inputs = Variable(x_train).cuda()
          target = Variable(y_train).cuda()
     else:
          inputs = Variable(x_train)
          target = Variable(y_train)
          
     #forwards
     out = model(inputs)
     loss = criterion(out, target)
     #backward
     optimizer.zero_grad()
     loss.backward()
     optimizer.step()
     
     if(epoch+1) % 20 ==0:
          print('Epoch [{}/{}], loss:{:.6f}'.format(epoch+1, num_epochs, loss.data[0]))
          
model.eval()
predict = model(Variable(x_train))
predict = predict.data.numpy()
plt.plot(x_train.numpy(), y_train.numpy(), 'ro', label = 'Original data')
plt.plot(x_train.numpy(), predict, label='Fitting Line')
plt.show()