当前位置：首页 > news >正文

yolov8添加ca注意力机制

news 2025/8/14 7:15:58

创建文件 coordAtt.py

位置：ultralytics/nn/modules/coordAtt.py

######################  CoordAtt  ####     start   by  AI&CV  ###############################
# https://zhuanlan.zhihu.com/p/655475515
import torch
import torch.nn as nn
import torch.nn.functional as Fclass h_sigmoid(nn.Module):def __init__(self, inplace=True):super(h_sigmoid, self).__init__()self.relu = nn.ReLU6(inplace=inplace)def forward(self, x):return self.relu(x + 3) / 6class h_swish(nn.Module):def __init__(self, inplace=True):super(h_swish, self).__init__()self.sigmoid = h_sigmoid(inplace=inplace)def forward(self, x):return x * self.sigmoid(x)class CoordAtt(nn.Module):def __init__(self, inp, reduction=32):super(CoordAtt, self).__init__()self.pool_h = nn.AdaptiveAvgPool2d((None, 1))self.pool_w = nn.AdaptiveAvgPool2d((1, None))mip = max(8, inp // reduction)self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)self.bn1 = nn.BatchNorm2d(mip)self.act = h_swish()self.conv_h = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)self.conv_w = nn.Conv2d(mip, inp, kernel_size=1, stride=1, padding=0)def forward(self, x):identity = xn, c, h, w = x.size()x_h = self.pool_h(x)x_w = self.pool_w(x).permute(0, 1, 3, 2)y = torch.cat([x_h, x_w], dim=2)y = self.conv1(y)y = self.bn1(y)y = self.act(y)x_h, x_w = torch.split(y, [h, w], dim=2)x_w = x_w.permute(0, 1, 3, 2)a_h = self.conv_h(x_h).sigmoid()a_w = self.conv_w(x_w).sigmoid()out = identity * a_w * a_hreturn out
######################  CoordAtt  ####     end   by  AI&CV  ###############################

conv.py中添加头文件

位置：ultralytics/nn/modules/conv.py
在这里插入图片描述

init.py中添加头文件

位置：ultralytics/nn/modules/init.py
在这里插入图片描述

tasks.py 文件

位置：ultralytics/nn/tasks.py

task.py文件添加头文件

在这里插入图片描述

task.py文件的方法中添加代码

        elif m is CoordAtt: # todo 源码修改 ~4"""ch[f]:上一层的args[0]:第0个参数c1:输入通道数c2:输出通道数"""c1, c2 = ch[f], args[0]# print("ch[f]:",ch[f])# print("args[0]:",args[0])# print("args:",args)# print("c1:",c1)# print("c2:",c2)if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)c2 = make_divisible(c2 * width, 8)args = [c1, *args[1:]]