python 和 torch 交叉熵损失

  

   

    

     

    
    

     

      import math
     
    
   

    

     

    
    

     

      import numpy as np   # 导入 math 模块
     
    
   

    

     

    
    

     

      import torch
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      x=0.9
     
    
   

    

     

    
    

     

      y=0.1
     
    
   

    

     

    
    

     

      print("math.log",-x* math.log(1-y))
     
    
   

    

     

    
    

     

      print("n p.log",-x* np.log(1-y))
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      x_tensor = torch.tensor([x])
     
    
   

    

     

    
    

     

      y_tensor = torch.tensor([y])
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      loss_tensor = (- x_tensor * torch.log(1-y_tensor)).sum()
     
    
   

    

     

    
    

     

      print(loss_tensor)
     
    
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/103811407