yolov5和yolov5-face nms比较

yolov5中，

prediction.shape[2] -5  # number of classes，代表分类数，5后面是多分类，coco是80个分类。

shape[2]是85

  

   

    

     

    
    

     

      def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, labels=()):
     
    
   

    

     

    
    

     
 """Performs Non-Maximum Suppression (NMS) on inference results
     
    
   

    

     

    
    

     

      
     
    
   

    

     

    
    

     

       Returns:
     
    
   

    

     

    
    

     

       detections with shape: nx6 (x1, y1, x2, y2, conf, cls)
     
    
   

    

     

    
    

     

       """
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       nc = prediction.shape[2] -5  # number of classes
     
    
  
 

yolov5-face中，

prediction.shape[2]中5后面10个是5个关键点坐标，分类数

shape[2]是16

nc = prediction.shape[2] - 15  # number of classes

  

   

    

     

    
    

     

      def non_max_suppression_face(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, labels=()):
     
    
   

    

     

    
    

     
 """Performs Non-Maximum Suppression (NMS) on inference results
     
    
   

    

     

    
    

     

       Retu
     
    
  
 

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/118399994