当前位置：首页 > article >正文

YOLOv8改进 - 注意力篇 - 引入(A2-Nets)Double Attention Networks注意力机制

article 2024/11/20 2:40:42

一、本文介绍

作为入门性篇章，这里介绍了A2-Nets网络注意力在YOLOv8中的使用。包含A2-Nets原理分析，A2-Nets的代码、A2-Nets的使用方法、以及添加以后的yaml文件及运行记录。

二、A2-Nets原理分析

A2-Nets官方论文地址：A2-Nets文章

A2-Nets注意力机制(双重注意力机制):它从输入图像/视频的整个时空空间中聚集和传播信息全局特征，使后续卷积层能够有效地从整个空间中访问特征。采用双注意机制（包括Spatial Attention和Channel Attention。Spatial Attention用于捕获图像中不同空间位置的重要性，而Channel Attention用于捕获图像中不同通道的重要性），分两步进行设计，第一步通过二阶注意池将整个空间的特征聚集成一个紧凑的集合，第二步通过另一个注意自适应地选择特征并将其分配到每个位置。

相关代码：

A2-Nets注意力的代码，如下。

import numpy as np
import torch
from torch import nn
from torch.nn import init
from torch.nn import functional as F


class DoubleAttention(nn.Module):

    def __init__(self, in_channels, c_m=128, c_n=128, reconstruct=True):
        super().__init__()
        self.in_channels = in_channels
        self.reconstruct = reconstruct

        self.c_m = c_m
        self.c_n = c_n
        self.convA = nn.Conv2d(in_channels, c_m, 1)
        self.convB = nn.Conv2d(in_channels, c_n, 1)
        self.convV = nn.Conv2d(in_channels, c_n, 1)
        if self.reconstruct:
            self.conv_reconstruct = nn.Conv2d(c_m, in_channels, kernel_size=1)
        self.init_weights()

    def init_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant_(m.weight, 1)
                init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal_(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant_(m.bias, 0)

    def forward(self, x):
        b, c, h, w = x.shape
        assert c == self.in_channels
        A = self.convA(x)  # b,c_m,h,w
        B = self.convB(x)  # b,c_n,h,w
        V = self.convV(x)  # b,c_n,h,w
        tmpA = A.view(b, self.c_m, -1)
        attention_maps = F.softmax(B.view(b, self.c_n, -1))
        attention_vectors = F.softmax(V.view(b, self.c_n, -1), dim=-1)
        # step 1: feature gating
        global_descriptors = torch.bmm(tmpA, attention_maps.permute(0, 2, 1))  # b.c_m,c_n
        # step 2: feature distribution
        tmpZ = global_descriptors.matmul(attention_vectors)  # b,c_m,h*w
        tmpZ = tmpZ.view(b, self.c_m, h, w)  # b,c_m,h,w
        if self.reconstruct:
            tmpZ = self.conv_reconstruct(tmpZ)

        return tmpZ

四、YOLOv8中SK使用方法

1.YOLOv8中添加SK模块：

首先在ultralytics/nn/modules/conv.py最后添加DoubleAttention模块的代码。

2.在conv.py的开头__all__ = 内添加DoubleAttention模块的类别名(A2-Nets的类别名在本文中为DoubleAttention)

3.在同级文件夹下的__init__.py内添加A2-Nets的相关内容：（分别是from .conv import DoubleAttention ；以及在__all__内添加DoubleAttention）

4.在ultralytics/nn/tasks.py进行SK注意力机制的注册，以及在YOLOv8的yaml配置文件中添加DoubleAttention即可。

首先打开task.py文件，按住Ctrl+F，输入parse_model进行搜索。找到parse_model函数。在其最后一个else前面添加以下注册代码：(本文续接上篇文章，加在了CBAM、ECA、SKAttention的位置)

        elif m in {CBAM,ECA,SKAttention,DoubleAttention}:#添加注意力模块，没有CBAM、ECA、SKAttention的，将CBAM、ECA、SKAttention删除即可
            c1, c2 = ch[f], args[0]
            if c2 != nc:
                c2 = make_divisible(min(c2, max_channels) * width, 8)
            args = [c1, *args[1:]]

然后，就是新建一个名为YOLOv8_DoubleAttention.yaml的配置文件：（路径:ultralytics/cfg/models/v8/YOLOv8_DoubleAttention.yaml）

# 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 CPAM-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, DoubleAttention, [1024]]
  - [-1, 1, SPPF, [1024, 5]]  # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]]  # Detect(P3, P4, P5)

其中参数中nc，由自己的数据集决定。本文测试，采用的coco8数据集，有80个类别。

在根目录新建一个train.py文件，内容如下

from ultralytics import YOLO

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
# 加载一个模型
    model = YOLO('ultralytics/cfg/models/v8/YOLOv8_DoubleAttention.yaml')  # 从YAML建立一个新模型
# 训练模型
    results = model.train(data='ultralytics/cfg/datasets/coco8.yaml', epochs=1,imgsz=640,optimizer="SGD")

训练输出：