当前位置:网站首页>Pytorch实现简单线性回归Demo
Pytorch实现简单线性回归Demo
2022-07-06 09:16:00 【想成为风筝】
Pytorch实现简单线性回归
import numpy as np
x_values = [i for i in range(11)]
x_train = np.array(x_values,dtype=np.float32)
x_train = x_train.reshape(-1,1)
print(x_train.shape)
y_values = [2*i+1 for i in x_values]
y_train = np.array(y_values,dtype=np.float32)
y_train = y_train.reshape(-1,1)
print(y_train.shape)
import torch
import torch.nn as nn
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
class LinearRegressionModel(nn.Module):
def __init__(self,input_dim,output_dim):
super(LinearRegressionModel, self).__init__()
self.Linear = nn.Linear(input_dim,output_dim)
def forward(self,x):
out = self.Linear(x)
return out
input_dim = 1
output_dim = 1
model = LinearRegressionModel(input_dim,output_dim)
model.to(device)
losses = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(),lr=0.01)
epochs = 1000
for epoch in range(epochs):
epoch += 1
inputs = torch.from_numpy(x_train).to(device)
outputs = torch.from_numpy(y_train).to(device)
optimizer.zero_grad()
out = model(inputs)
loss = losses(out,outputs)
loss.backward()
optimizer.step()
if epoch % 50 == 0:
print('epoch {},loss {}'.format(epoch,loss))
#预测
predicted =model(torch.from_numpy(x_train).requires_grad_()).data.numpy()
print(predicted)
# #保存
# torch.save(model.state_dict(),'model.pkl') #保存模型的参数 w b
# #加载
# model.load_state_dict(torch.load('model.pkl')) #加载
边栏推荐
- MySQL START SLAVE Syntax
- 【yarn】CDP集群 Yarn配置capacity调度器批量分配
- ES6 let 和 const 命令
- Some concepts often asked in database interview
- Password free login of distributed nodes
- R & D thinking 01 ----- classic of embedded intelligent product development process
- wangeditor富文本引用、表格使用问题
- 快来走进JVM吧
- Integration test practice (1) theoretical basis
- Vs2019 desktop app quick start
猜你喜欢
随机推荐
SQL time injection
L2-001 紧急救援 (25 分)
Common regular expression collation
List and set
error C4996: ‘strcpy‘: This function or variable may be unsafe. Consider using strcpy_ s instead
Word typesetting (subtotal)
vs2019 第一个MFC应用程序
Encodermappreduce notes
[Bluebridge cup 2021 preliminary] weight weighing
Codeforces Round #771 (Div. 2)
使用lambda在循环中传参时,参数总为同一个值
XML file explanation: what is XML, XML configuration file, XML data file, XML file parsing tutorial
Funny cartoon: Programmer's logic
express框架详解
Password free login of distributed nodes
Codeforces Round #771 (Div. 2)
误删Path变量解决
vs2019 使用向导生成一个MFC应用程序
Detailed explanation of nodejs
Vert. x: A simple TCP client and server demo