pytorch快速入门--构建线性回归

偏执的太偏执、 2023-07-12 05:21 38阅读 0赞

## 准备数据 ##

这里用一组比较简单的数据

x_data = torch.Tensor([[1.0],[2.0],[3.0]])
    y_data = torch.Tensor([[3.0],[6.0],[9.0]])

## 构建线性回归模型 ##

#定义一个线性回归类
    class Model(torch.nn.Module):
        def __init__(self):
            super(Model,self).__init__()
            #模型只包含一个线性回归模型
            self.linear = torch.nn.Linear(1,1)
        #前向运算
        def forward(self,x):
            y_pred = self.linear(x)
            return y_pred

## 构建目标函数与优化方法 ##

#定义损失函数
    criterion = torch.nn.MSELoss(size_average = False)
    #随机梯度下降作为优化方法
    optimizer = torch.optim.SGD(model.parameters(),lr=0.01)

## 迭代过程 ##

#开始迭代
    for epoch in range(500):
        y_pred = model(x_data)
        求损失函数
        loss = criterion(y_pred,y_data)
        print("epoch: ",epoch,"   loss: ",loss.item())
        
        optimizer.zero_grad()
        #反向
        loss.backward()
        #优化
        optimizer.step()

## 全部代码 ##

import torch
    from torch.autograd import Variable
    
    x_data = torch.Tensor([[1.0],[2.0],[3.0]])
    y_data = torch.Tensor([[2.0],[4.0],[6.0]])
    
    class Model(torch.nn.Module):
        def __init__(self):
            super(Model,self).__init__()
            self.linear = torch.nn.Linear(1,1)
    
        def forward(self,x):
            y_pred = self.linear(x)
            return y_pred
    
    model = Model()
    
    criterion = torch.nn.MSELoss(size_average = False)
    optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
    
    for epoch in range(500):
        y_pred = model(x_data)
    
        loss = criterion(y_pred,y_data)
        print("epoch: ",epoch,"   loss: ",loss.item())
    
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    
    hour_val = torch.Tensor([[4.0]])
    print("after training:",4,model.forward(hour_val).data[0][0])

## 结果 ##

这里只展示最后的结果了

epoch:  496    loss:  0.0005511323106475174  
epoch:  497    loss:  0.0005431824829429388  
epoch:  498    loss:  0.0005353790475055575  
epoch:  499    loss:  0.0005277082673273981  
after training: 4 tensor(11.9736)

可以看出最后求得的结果是11.9736，很接近12