YOLOv8如何添加注意力模块？

news2024/9/27 23:22:37

分为两种：有参注意力和无参注意力。
eg:
有参：

import torch
from torch import nn

class EMA(nn.Module):
    def __init__(self, channels, factor=8):
        super(EMA, self).__init__()
        self.groups = factor
        assert channels // self.groups > 0
        self.softmax = nn.Softmax(-1)
        self.agp = nn.AdaptiveAvgPool2d((1, 1))
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))
        self.gn = nn.GroupNorm(channels // self.groups, channels // self.groups)
        self.conv1x1 = nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size=1, stride=1, padding=0)
        self.conv3x3 = nn.Conv2d(channels // self.groups, channels // self.groups, kernel_size=3, stride=1, padding=1)

    def forward(self, x):
        b, c, h, w = x.size()
        group_x = x.reshape(b * self.groups, -1, h, w)  # b*g,c//g,h,w
        x_h = self.pool_h(group_x)
        x_w = self.pool_w(group_x).permute(0, 1, 3, 2)
        hw = self.conv1x1(torch.cat([x_h, x_w], dim=2))
        x_h, x_w = torch.split(hw, [h, w], dim=2)
        x1 = self.gn(group_x * x_h.sigmoid() * x_w.permute(0, 1, 3, 2).sigmoid())
        x2 = self.conv3x3(group_x)
        x11 = self.softmax(self.agp(x1).reshape(b * self.groups, -1, 1).permute(0, 2, 1))
        x12 = x2.reshape(b * self.groups, c // self.groups, -1)  # b*g, c//g, hw
        x21 = self.softmax(self.agp(x2).reshape(b * self.groups, -1, 1).permute(0, 2, 1))
        x22 = x1.reshape(b * self.groups, c // self.groups, -1)  # b*g, c//g, hw
        weights = (torch.matmul(x11, x12) + torch.matmul(x21, x22)).reshape(b * self.groups, 1, h, w)
        return (group_x * weights.sigmoid()).reshape(b, c, h, w)

无参：

import torch
import torch.nn as nn


class SimAM(torch.nn.Module):
    def __init__(self, e_lambda=1e-4):
        super(SimAM, self).__init__()

        self.activaton = nn.Sigmoid()
        self.e_lambda = e_lambda

    def __repr__(self):
        s = self.__class__.__name__ + '('
        s += ('lambda=%f)' % self.e_lambda)
        return s

    @staticmethod
    def get_module_name():
        return "simam"

    def forward(self, x):
        b, c, h, w = x.size()

        n = w * h - 1

        x_minus_mu_square = (x - x.mean(dim=[2, 3], keepdim=True)).pow(2)
        y = x_minus_mu_square / (4 * (x_minus_mu_square.sum(dim=[2, 3], keepdim=True) / n + self.e_lambda)) + 0.5

        return x * self.activaton(y)

1、在nn文件夹下新建attention.py文件，把上面俩代码放进去
在这里插入图片描述

2、在tasks.py文件里面导入俩函数
在这里插入图片描述
3、在解析函数里面添加解析代码

c1:上一层的输出通道数，也是这一层的输入通道数
C2:该层的输出通道数，即将成为下一层的输入通道数
args[]:每个带参数的模块，都要指定这个东西，这个包括[c1,c2,剩下的参数]，然后传给该层的模块，有些模块不需要额外参数，就只传一个输出通道数给这一层就行
切记！！！C2是这一层的输出通道数，而args[]里的输入输出通道数是给模块的
4、新建模型配置文件
在这里插入图片描述
4、快速验证配置文件，新建main.py文件，然后运行

from ultralytics import YOLO

if __name__=='__main__':
    print('11111111111')
    model=YOLO('/home/xxxxxxxx/v8/yolov8-main/ultralytics/models/v8/yolov8-att.yaml')