位置不共享卷积

Involution的一个特点：输入通道和输出通道必须是一样的，如果想实现输入和输出不一样，文末有方法。

实现1：

https://github.com/d-li14/involution/blob/21c3158fcbb4ecda8ed4626fcae8b01be511a598/cls/mmcls/models/utils/involution_naive.py

以来mmcv

mmcv安装：

pip install mmcv

  

   

    

     

    
    

     

      import torch.nn as nn
     
    
   

    

     

    
    

     

      from mmcv.cnn import ConvModule
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      class involution(nn.Module):
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 def __init__(self,
     
    
   

    

     

    
    

     

       channels,
     
    
   

    

     

    
    

     

       kernel_size,
     
    
   

    

     

    
    

     

       stride):
     
    
   

    

     

    
    

     

       super(involution, self).__init__()
     
    
   

    

     

    
    

     

       self.kernel_size = kernel_size
     
    
   

    

     

    
    

     

       self.stride = stride
     
    
   

    

     

    
    

     

       self.channels = channels
     
    
   

    

     

    
    

     

       reduction_ratio = 4
     
    
   

    

     

    
    

     

       self.group_channels = 16
     
    
   

    

     

    
    

     

       self.groups = self.channels // self.group_channels
     
    
   

    

     

    
    

     

       self.conv1 = Con
     
    
  
 

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/118633994