爆改YOLOv8 | yolov8添加CA注意力机制

不想敲代码！！！

已于 2024-08-23 09:45:19 修改

阅读量486

点赞数 8

分类专栏：爆改yolov8，即插即用文章标签： YOLO yolov8 目标检测计算机视觉深度学习

于 2024-08-18 10:11:10 首次发布

本文链接：https://blog.csdn.net/weixin_43986124/article/details/141292654

版权

爆改yolov8，即插即用专栏收录该内容

37 篇文章 39 订阅

订阅专栏

1，本文介绍

CA(坐标注意力)是一种结合了通道注意力和位置信息的注意力机制，旨在提升移动网络的性能。它通过将特征张量沿两个空间方向进行1D全局池化，分别捕获沿垂直和水平方向的特征，保留了精确的位置信息并捕获了长距离依赖性。这两个方向的特征图被单独编码成方向感知和位置敏感的注意力图，然后这些注意力图通过乘法作用于输入特征图，以突出感兴趣的对象表示。坐标注意力的引入，使得模型能够更准确地定位和识别感兴趣的对象，同时由于其轻量级和灵活性，它可以轻松集成到现有的移动网络架构中，几乎不会增加计算开销。

关于CA的详细介绍可以看论文：https://arxiv.org/pdf/2103.02907.pdf

本文将讲解如何将CA融合进yolov8

话不多说，上代码！

２，将CA融合进YOLＯｖ８

CA的核心代码如下，关于具体如何融入yolov8，可以查看作者前一篇文章：爆改YOLOv8 | yolov8添加ECA注意力机制-CSDN博客

具体添加方式都一样，名字换一下即可

import torch
import torch.nn as nn
import math
import torch.nn.functional as F
 
class 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) / 6
 
class 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__()
        oup = inp
        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, oup, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
        
 
    def forward(self, x):
        identity = x
        
        n,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_h
 
        return out

yaml文件

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 80  # number of classes
scales:  # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
 
# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, CoordAtt, []]  # 9
  - [-1, 1, SPPF, [1024, 5]]  # 10
 
# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 13
 
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]]  # Detect(P3, P4, P5)

# 关于CA添加的位置还可以放在颈部,针对不同数据集位置不同,效果不同

不知不觉已经看完了哦，动动小手留个点赞吧--_--

有问题可以留在评论区哦，博主看到了就会回复