pytorch 构建网络模型的方法

灰太狼 2023-03-14 08:14 35阅读 0赞

1.常规

class Logistic\_regression\_1(nn.Module):  
    def \_\_init\_\_(self):  
        super(Logistic\_regression\_1, self).\_\_init\_\_()  
        self.lr = nn.Linear(2, 1)  
        self.sm = nn.Sigmoid()  
      
    def forward(self, x):  
        x = self.lr(x)  
        x = self.sm(x)  
        return x

2.sequential

class Logistic_regression_2(nn.Module):
        def __init__(self):
            super(Logistic_regression_2, self).__init__()
            self.lr = torch.nn.Sequential(
                nn.Linear(2, 1)
            )
            self.sm = torch.nn.Sequential(
                nn.Sigmoid()
            )
    
        def forward(self, x):
            x = self.lr(x)
            x = self.sm(x)
            return x

3.add\_module

class Logistic_regression_3(torch.nn.Module):
        def __init__(self):
            super(Logistic_regression_3, self).__init__()
            self.lr = torch.nn.Sequential()
            self.lr.add_module("lr",torch.nn.Linear(2, 1))
            
            self.sm = torch.nn.Sequential()
            self.sm.add_module("sm",torch.nn.Sigmoid())
           
    
        def forward(self, x):
            x = self.lr(x)
            x = self.sm(x)
            return x

4.OrderedDict

import torch
    from collections import OrderedDict
    class Logistic_regression_4(torch.nn.Module):
        def __init__(self):
            super(Logistic_regression_4, self).__init__()
            self.lr = torch.nn.Sequential(
                OrderedDict(
                    [
                        ("lr", torch.nn.Linear(2, 1)),
                        
                    ]
                ))
    
            self.sm = torch.nn.Sequential(
                OrderedDict([
                     ("sm", torch.nn.Sigmoid()),
                    
                ])
            )
        
        def forward(self, x):
            x = self.lr(x)
            x = self.sm(x)
            return x
    
    model = Net4()
    
    print(model)