当前位置： 首页 > article >正文

YOLO11改进 | 注意力机制 | 结合静态和动态上下文信息的注意力机制

article 2024/10/12 5:43:13

秋招面试专栏推荐 ：深度学习算法工程师面试问题总结【百面算法工程师】——点击即可跳转

💡💡💡本专栏所有程序均经过测试，可成功执行💡💡💡

上下文Transformer（CoT）块是一种新颖的Transformer风格模块，用于视觉识别。它充分利用输入键之间的上下文信息来指导动态注意力矩阵的学习，从而加强了视觉表示的能力。CoT块首先通过3×3卷积对输入键进行上下文化编码，得到输入的静态上下文表示。然后，将编码后的键与输入查询连接起来，通过两个连续的1×1卷积来学习动态的多头注意力矩阵。最后，将静态和动态上下文表示的融合作为输出。文章在介绍主要的原理后，将手把手教学如何进行模块的代码添加和修改，并将修改后的完整代码放在文章的最后，方便大家一键运行，小白也可轻松上手实践。以帮助您更好地学习深度学习目标检测YOLO系列的挑战。

专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅

目录

1.论文

2. 将CoTAttention添加到YOLO11中

2.1 CoTAttention代码实现

2.2 更改init.py文件

2.3 添加yaml文件

2.4 在task.py中进行注册

2.5 执行程序

3.修改后的网络结构图

4. 完整代码分享

5. GFLOPs

6. 进阶

7.总结

1.论文

论文地址：Contextual Transformer Networks for Visual Recognition——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. 将CoTAttention添加到YOLO11中

2.1 CoTAttention代码实现

关键步骤一: 将下面代码粘贴到在/ultralytics/ultralytics/nn/modules/block.py中

class CoTAttention(nn.Module):

    def __init__(self, dim=512, kernel_size=3):
        super().__init__()
        self.dim = dim
        self.kernel_size = kernel_size

        self.key_embed = nn.Sequential(
            nn.Conv2d(dim, dim, kernel_size=kernel_size, padding=kernel_size // 2, groups=4, bias=False),
            nn.BatchNorm2d(dim),
            nn.SiLU()
        )
        self.value_embed = nn.Sequential(
            nn.Conv2d(dim, dim, 1, bias=False),
            nn.BatchNorm2d(dim)
        )

        factor = 4
        self.attention_embed = nn.Sequential(
            nn.Conv2d(2 * dim, 2 * dim // factor, 1, bias=False),
            nn.BatchNorm2d(2 * dim // factor),
            nn.SiLU(),
            nn.Conv2d(2 * dim // factor, kernel_size * kernel_size * dim, 1)
        )

    def forward(self, x):
        bs, c, h, w = x.shape
        k1 = self.key_embed(x)  # bs,c,h,w
        v = self.value_embed(x).view(bs, c, -1)  # bs,c,h,w

        y = torch.cat([k1, x], dim=1)  # bs,2c,h,w
        att = self.attention_embed(y)  # bs,c*k*k,h,w
        att = att.reshape(bs, c, self.kernel_size * self.kernel_size, h, w)
        att = att.mean(2, keepdim=False).view(bs, c, -1)  # bs,c,h*w
        k2 = F.softmax(att, dim=-1) * v
        k2 = k2.view(bs, c, h, w)

        return k1 + k2

2.2 更改init.py文件

关键步骤二：修改modules文件夹下的__init__.py文件，先导入函数

然后在下面的__all__中声明函数

2.3 添加yaml文件

关键步骤三：在/ultralytics/ultralytics/cfg/models/11下面新建文件yolo11_CoTA.yaml文件，粘贴下面的内容

  • 目标检测
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n 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, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
  - [ -1, 1, CoTAttention, [1024] ]

  - [[16, 19, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)
  • 语义分割
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n 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, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
  - [ -1, 1, CoTAttention, [1024] ]

  - [[16, 19, 23], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)
  • 旋转目标检测
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 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=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n 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, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
  - [ -1, 1, CoTAttention, [1024] ]

  - [[16, 19, 23], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)

温馨提示：本文只是对yolo11基础上添加模块，如果要对yolo11n/l/m/x进行添加则只需要指定对应的depth_multiple 和 width_multiple。

# YOLO11n
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.25  # layer channel multiple
max_channel：1024
 
# YOLO11s
depth_multiple: 0.50  # model depth multiple
width_multiple: 0.50  # layer channel multiple
max_channel：1024
 
# YOLO11m
depth_multiple: 0.50  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512
 
# YOLO11l 
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.00  # layer channel multiple
max_channel：512 
 
# YOLO11x
depth_multiple: 1.00  # model depth multiple
width_multiple: 1.50 # layer channel multiple
max_channel：512

2.4 在task.py中进行注册

关键步骤四：在task.py的parse_model函数中进行注册，

 先在task.py导入函数

然后在task.py文件下找到parse_model这个函数，如下图，添加CoTAttention

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

2.5 执行程序

关键步骤五：在ultralytics文件中新建train.py，将model的参数路径设置为yolo11_CoTA.yaml的路径即可

from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Path
 
if __name__ == '__main__':
 
 
    # 加载模型
    model = YOLO("ultralytics/cfg/11/yolo11.yaml")  # 你要选择的模型yaml文件地址
    # Use the model
    results = model.train(data=r"你的数据集的yaml文件地址",
                          epochs=100, batch=16, imgsz=640, workers=4, name=Path(model.cfg).stem)  # 训练模型

 🚀运行程序，如果出现下面的内容则说明添加成功🚀

                   from  n    params  module                                       arguments
  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]
  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]
  2                  -1  1      6640  ultralytics.nn.modules.block.C3k2            [32, 64, 1, False, 0.25]
  3                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]
  4                  -1  1     26080  ultralytics.nn.modules.block.C3k2            [64, 128, 1, False, 0.25]
  5                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]
  6                  -1  1     87040  ultralytics.nn.modules.block.C3k2            [128, 128, 1, True]
  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]
  8                  -1  1    346112  ultralytics.nn.modules.block.C3k2            [256, 256, 1, True]
  9                  -1  1    164608  ultralytics.nn.modules.block.SPPF            [256, 256, 5]
 10                  -1  1    249728  ultralytics.nn.modules.block.C2PSA           [256, 256, 1]
 11                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 12             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 13                  -1  1    111296  ultralytics.nn.modules.block.C3k2            [384, 128, 1, False]
 14                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']
 15             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 16                  -1  1     32096  ultralytics.nn.modules.block.C3k2            [256, 64, 1, False]
 17                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]
 18            [-1, 13]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 19                  -1  1     86720  ultralytics.nn.modules.block.C3k2            [192, 128, 1, False]
 20                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]
 21            [-1, 10]  1         0  ultralytics.nn.modules.conv.Concat           [1]
 22                  -1  1    378880  ultralytics.nn.modules.block.C3k2            [384, 256, 1, True]
 23                  -1  1    577024  ultralytics.nn.modules.block.CoTAttention    [256]
 24        [16, 19, 23]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_CoTAttention summary: 332 layers, 3,201,104 parameters, 3,201,088 gradients, 7.1 GFLOPs
wAAACH5BAEKAAAALAAAAAABAAEAAAICRAEAOw==

3.修改后的网络结构图

4. 完整代码分享

这个后期补充吧~，先按照步骤来即可

5. GFLOPs

关于GFLOPs的计算方式可以查看：百面算法工程师 | 卷积基础知识——Convolution

未改进的YOLO11n GFLOPs

改进后的GFLOPs

6. 进阶

可以与其他的注意力机制或者损失函数等结合，进一步提升检测效果

7.总结

通过以上的改进方法，我们成功提升了模型的表现。这只是一个开始，未来还有更多优化和技术深挖的空间。在这里，我想隆重向大家推荐我的专栏——《YOLO11改进有效涨点》。这个专栏专注于前沿的深度学习技术，特别是目标检测领域的最新进展，不仅包含对YOLO11的深入解析和改进策略，还会定期更新来自各大顶会（如CVPR、NeurIPS等）的论文复现和实战分享。

为什么订阅我的专栏？ ——《YOLO11改进有效涨点》

  1. 前沿技术解读：专栏不仅限于YOLO系列的改进，还会涵盖各类主流与新兴网络的最新研究成果，帮助你紧跟技术潮流。

  2. 详尽的实践分享：所有内容实践性也极强。每次更新都会附带代码和具体的改进步骤，保证每位读者都能迅速上手。

  3. 问题互动与答疑：订阅我的专栏后，你将可以随时向我提问，获取及时的答疑。

  4. 实时更新，紧跟行业动态：不定期发布来自全球顶会的最新研究方向和复现实验报告，让你时刻走在技术前沿。

专栏适合人群：

  • 对目标检测、YOLO系列网络有深厚兴趣的同学

  • 希望在用YOLO算法写论文的同学

  • 对YOLO算法感兴趣的同学等


http://www.kler.cn/news/343681.html

相关文章：

  • 基于AnolisOS 8.6安装SNMPTT
  • K210 Maxi bit 适合于新手的各种教程文章（保姆级教程）
  • ansible学习之ansible-vault
  • QD1-P19 HTML 总结
  • 云计算第四阶段 CLOUD2周目 01-03
  • 【数据结构-栈】力扣155. 最小栈
  • react中的重定向Redirect
  • windows C++-在启用 COM 的应用程序中使用并发(一)
  • 为什么云服务器加了安全组端口还是无法访问？
  • vscode gitlens收费破解
  • poi通过在word中写入了表格，通过libreoffice转换成PDF后，word中刚才画的表格宽度无限拉伸问题的解决。
  • 基于微信小程序的家校联动平台管理系统的设计与实现（毕业论文）
  • 思维链ChatGPT
  • windows server 2019中安装.net framework 3.5功能出错
  • [AWS云]kafka调用和创建
  • leetcode15:三数之和
  • R语言统计分析——气泡图
  • 100套深度学习毕业设计项目合集【含源码 + 操作文档】
  • 笔试强训day37
  • 基于华为云智慧生活生态链设计的智能鱼缸