retina 负样本回归增强loss

目前没看到明显改善

  

   

    

     

    
    

     

      import configparser
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      import torch
     
    
   

    

     

    
    

     

      import torch.nn as nn
     
    
   

    

     

    
    

     

      import torch.nn.functional as F
     
    
   

    

     

    
    

     

      from torch.autograd import Variable
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      from focal_loss import FocalLoss
     
    
   

    

     

    
    

     

      from utils.box_utils import match, log_sum_exp
     
    
   

    

     

    
    

     

      from data import cfg_mnet
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      GPU = cfg_mnet['gpu_train']
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      class MultiBoxLoss(nn.Module):
     
    
   

    

     

    
    

     
    """SSD Weighted Loss Function
     
    
   

    

     

    
    

     

       Compute Targets:
     
    
   

    

     

    
    

     

       1) Produce Confidence Target Indices by matching ground truth boxes
     
    
   

    

     

    
    

     

       with (default) 'priorboxes' that have jaccard index > threshold parameter
     
    
   

    

     

    
    

     

       (default threshold: 0.5).
     
    
   

    

     

    
    

     

       2) Produce localization target by 'encoding' variance into offsets of ground
     
    
   

    

     

    
    

     

       truth boxes and their matched 'priorboxes'.
     
    
   

    

     

    
    

     

       3) Hard negative mining to filter the excessive number of negative examples
     
    
   

    

     

    
    

     

       that comes with using a large number of default bounding boxes.
     
    
   

    

     

    
    

     

       (default negative:positive ratio 3:1)
     
    
   

    

     

    
    

     

      
     
    
  
 

文章来源: blog.csdn.net，作者：AI视觉网奇，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/104706256