YOLOv8改进：注意力系列篇 | Triplet注意力模，效果优于cbam、se、BAM等，涨点明显

会AI的学姐

已于 2023-10-22 17:14:50 修改

阅读量1.4k

点赞数 5

分类专栏： YOLOv8实战改进教程文章标签： python 深度学习开发语言 YOLO 计算机视觉目标检测

于 2023-10-22 16:33:07 首次发布

本文链接：https://blog.csdn.net/CV_20231007/article/details/133974345

版权

YOLOv8实战改进教程专栏收录该内容

30 篇文章

订阅专栏

本文介绍了如何将TripletAttention引入YOLOv8，一种改进的注意力模型，旨在解决跨维度交互问题，提高对象检测的性能。作者提供了代码实现和不同配置文件的示例，展示了如何在YOLOv8的backbone和head部分集成这种机制。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

🚀🚀🚀本文改进：TripletAttention，引入到YOLOv8，多种实现方式

🚀🚀🚀TripletAttention在不同检测领域中应用广泛

🚀🚀🚀YOLOv8改进专栏：http://t.csdnimg.cn/hGhVK

学姐带你学习YOLOv8，从入门到创新，轻轻松松搞定科研；

1.Triplet注意力介绍

论文：https://arxiv.org/pdf/2010.03045.pdf

本文提出了可以有效解决跨维度交互的triplet attention。相较于以往的注意力方法，主要有两个优点：

1.可以忽略的计算开销

2.强调了多维交互而不降低维度的重要性，因此消除了通道和权重之间的间接对应。

传统的计算通道注意力的方法为了计算这些通道的权值，输入张量在空间上通过全局平均池化分解为一个像素。这导致了空间信息的大量丢失，因此在单像素通道上计算注意力时，通道维数和空间维数之间的相互依赖性也不存在。后面提出基于Spatial和Channel的CBAM模型缓解了空间相互依赖的问题，但是通道注意和空间注意是分离的，计算是相互独立的。基于建立空间注意力的方法，本文提出了跨维度交互作用(cross dimension interaction)的概念，通过捕捉空间维度和输入张量通道维度之间的交互作用，解决了这一问题。

所提出的Triplet Attention如下图所示，Triplet Attention由3个平行的Branch组成，其中两个负责捕获通道C和空间H或W之间的跨维交互。最后一个Branch类似于CBAM，用于构建Spatial Attention，最终3个Branch的输出使用平均求和。

效果优于CBAM、SE

2.TripletAttention加入YOLOv8

2.1加入ultralytics/nn/attention/attention.py


import torch
import torch.nn as nn
from torch.nn import functional as F

###################### TripletAttention  ####     start   ###############################

class BasicConv(nn.Module):  # https://arxiv.org/pdf/2010.03045.pdf
    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True,
                 bn=True, bias=False):
        super(BasicConv, self).__init__()
        self.out_channels = out_planes
        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding,
                              dilation=dilation, groups=groups, bias=bias)
        self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True) if bn else None
        self.relu = nn.ReLU() if relu else None

    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.relu is not None:
            x = self.relu(x)
        return x


class ZPool(nn.Module):
    def forward(self, x):
        return torch.cat((torch.max(x, 1)[0].unsqueeze(1), torch.mean(x, 1).unsqueeze(1)), dim=1)


class AttentionGate(nn.Module):
    def __init__(self):
        super(AttentionGate, self).__init__()
        kernel_size = 7
        self.compress = ZPool()
        self.conv = BasicConv(2, 1, kernel_size, stride=1, padding=(kernel_size - 1) // 2, relu=False)

    def forward(self, x):
        x_compress = self.compress(x)
        x_out = self.conv(x_compress)
        scale = torch.sigmoid_(x_out)
        return x * scale


class TripletAttention(nn.Module):
    def __init__(self, no_spatial=False):
        super(TripletAttention, self).__init__()
        self.cw = AttentionGate()
        self.hc = AttentionGate()
        self.no_spatial = no_spatial
        if not no_spatial:
            self.hw = AttentionGate()

    def forward(self, x):
        x_perm1 = x.permute(0, 2, 1, 3).contiguous()
        x_out1 = self.cw(x_perm1)
        x_out11 = x_out1.permute(0, 2, 1, 3).contiguous()
        x_perm2 = x.permute(0, 3, 2, 1).contiguous()
        x_out2 = self.hc(x_perm2)
        x_out21 = x_out2.permute(0, 3, 2, 1).contiguous()
        if not self.no_spatial:
            x_out = self.hw(x)
            x_out = 1 / 3 * (x_out + x_out11 + x_out21)
        else:
            x_out = 1 / 2 * (x_out11 + x_out21)
        return x_out

2.2 修改tasks.py

首先TripletAttention进行注册

from ultralytics.nn.attention.attention import *

函数def parse_model(d, ch, verbose=True): # model_dict, input_channels(3)进行修改

        elif m in (TripletAttention,):
            c1, c2 = ch[f], args[0]
            if c2 != nc:
                c2 = make_divisible(min(c2, max_channels) * width, 8)
            args = [c1, *args[1:]]

2.3 yaml实现

2.3.1 yolov8_TripletAttention.yaml

加入backbone SPPF后

# 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, SPPF, [1024, 5]]  # 9
  - [-1, 1, TripletAttention, [1024]]  # 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)

2.3.2 yolov8_TripletAttention2.yaml

neck里的连接Detect的3个C2f结合

# 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, 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, TripletAttention, [256]]  # 16

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 19 (P4/16-medium)
  - [-1, 1, TripletAttention, [512]]  # 20

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 23 (P5/32-large)
  - [-1, 1, TripletAttention, [1024]]  # 24

  - [[16, 20, 24], 1, Detect, [nc]]  # Detect(P3, P4, P5)

2.3.3 yolov8_TripletAttention3.yaml

放入neck的C2f后面

# Ultralytics YOLO 🚀, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
 
# Parameters
nc: 1  # 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, 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, TripletAttention, [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, TripletAttention, [256]]  # 17 (P5/32-large)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 20 (P4/16-medium)
  - [-1, 1, TripletAttention, [512]]  # 21 (P5/32-large)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [1024]]  # 24 (P5/32-large)
  - [-1, 1, TripletAttention, [1024]]  # 25 (P5/32-large)
 
  - [[17, 21, 25], 1, Detect, [nc]]  # Detect(P3, P4, P5)