当前位置： 首页 > article >正文

YOLO11改进 | 注意力机制 | 迈向高质量像素级回归的极化自注意力【全网独家】

article 2024/10/19 17:25:55

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💡💡💡

虽然深度卷积神经网络中的注意力机制已经变得流行，用于增强长距离依赖，但元素特定的注意力，如Nonlocal块，学习起来非常复杂且对噪声敏感，而且大多数简化的注意力混合方法试图在多种类型的任务之间达到最佳的折衷。为此研究人员提出了极化自注意力（PSA）块，它结合了两个关键设计，以实现高质量的像素级回归。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. 将极化自注意力添加到YOLOv8中

2.1 PSA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：Polarized Self-Attention: Towards High-quality Pixel-wise Regression——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. 将极化自注意力添加到YOLO11中

2.1 PSAttention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 PSAttention(nn.Module):
 
    def __init__(self, channel=512):
        super().__init__()
        self.ch_wv = nn.Conv2d(channel, channel // 2, kernel_size=(1, 1))
        self.ch_wq = nn.Conv2d(channel, 1, kernel_size=(1, 1))
        self.softmax_channel = nn.Softmax(1)
        self.softmax_spatial = nn.Softmax(-1)
        self.ch_wz = nn.Conv2d(channel // 2, channel, kernel_size=(1, 1))
        self.ln = nn.LayerNorm(channel)
        self.sigmoid = nn.Sigmoid()
        self.sp_wv = nn.Conv2d(channel, channel // 2, kernel_size=(1, 1))
        self.sp_wq = nn.Conv2d(channel, channel // 2, kernel_size=(1, 1))
        self.agp = nn.AdaptiveAvgPool2d((1, 1))
 
    def forward(self, x):
        b, c, h, w = x.size()
 
        # Channel-only Self-Attention
        channel_wv = self.ch_wv(x)  # bs,c//2,h,w
        channel_wq = self.ch_wq(x)  # bs,1,h,w
        channel_wv = channel_wv.reshape(b, c // 2, -1)  # bs,c//2,h*w
        channel_wq = channel_wq.reshape(b, -1, 1)  # bs,h*w,1
        channel_wq = self.softmax_channel(channel_wq)
        channel_wz = torch.matmul(channel_wv, channel_wq).unsqueeze(-1)  # bs,c//2,1,1
        channel_weight = self.sigmoid(self.ln(self.ch_wz(channel_wz).reshape(b, c, 1).permute(0, 2, 1))).permute(0, 2,
                                                                                                                 1).reshape(
            b, c, 1, 1)  # bs,c,1,1
        channel_out = channel_weight * x
 
        # Spatial-only Self-Attention
        spatial_wv = self.sp_wv(channel_out)  # bs,c//2,h,w
        spatial_wq = self.sp_wq(channel_out)  # bs,c//2,h,w
        spatial_wq = self.agp(spatial_wq)  # bs,c//2,1,1
        spatial_wv = spatial_wv.reshape(b, c // 2, -1)  # bs,c//2,h*w
        spatial_wq = spatial_wq.permute(0, 2, 3, 1).reshape(b, 1, c // 2)  # bs,1,c//2
        spatial_wq = self.softmax_spatial(spatial_wq)
        spatial_wz = torch.matmul(spatial_wq, spatial_wv)  # bs,1,h*w
        spatial_weight = self.sigmoid(spatial_wz.reshape(b, 1, h, w))  # bs,1,h,w
        spatial_out = spatial_weight * channel_out
        return spatial_out

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_PSA.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, PSAttention, [ 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, PSAttention, [ 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, PSAttention, [ 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

elif m is PSAttention:
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                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_PSA.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    132481  ultralytics.nn.modules.block.PSAttention     [256]
 24        [16, 19, 23]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_PSA summary: 330 layers, 2,756,561 parameters, 2,756,545 gradients, 6.7 GFLOPs

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/356140.html

相关文章：

  • 基于SpringBoot+Vue+uniapp微信小程序的宿舍报修系统的详细设计和实现
  • 代理 IP：促进在线教育资源普及与公平的新助力
  • 数据仓库构建的两种方法：自上向下、自下向上
  • 《OpenCV计算机视觉》——人脸检测__Haar特征、级联分类器
  • nnUnet 大模型学习笔记（续）：训练网络（3d_fullres）以及数据集标签的处理
  • Java项目-基于Springboot的招生管理系统项目(源码+说明).zip
  • 网络变压器在PCIe网口应用的案例
  • 《师兄啊师兄》：家国大义，不忘初心
  • Java项目-基于springboot框架的智能热度分析和自媒体推送平台项目实战(附源码+文档)
  • C++：priority_queue优先队列
  • Spring Boot视频网站：构建高性能的视频服务
  • ASO优化手机游戏的秘密功能
  • Ubuntu安装运行 xx.AppImage 文件
  • KCC@广州活动预告：开源共融，粤创未来
  • 基于SpringBoot+Vue+uniapp的涪陵区特色农产品交易系统的详细设计和实现(源码+lw+部署文档+讲解等)
  • Linux 系统常用命令
  • 鸿蒙-键盘弹出时 promptAction.showToast 被遮盖
  • KubeSphere部署Elasticsearch+Kibana
  • vulnhub（15）：lemonsqueezy（hydra爆破、计划任务提权）
  • Vue是一套构建用户界面的渐进式框架，常用于构建单页面应用