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】

kay_5452024-10-13 13:47

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. 将极化自注意力添加到YOLOv8中)

[2.1 PSA代码实现](#2.1 PSA代码实现)

[2.2 更改init.py文件](#2.2 更改init.py文件)

[2.3 添加yaml文件](#2.3 添加yaml文件)

[2.4 在task.py中进行注册](#2.4 在task.py中进行注册)

[2.5 执行程序](#2.5 执行程序)

3.修改后的网络结构图

[4. 完整代码分享](#4. 完整代码分享)

[5. GFLOPs](#5. GFLOPs)

[6. 进阶](#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

python 复制代码 
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
python 复制代码 
# 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
python 复制代码 
# 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
python 复制代码 
# 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。

python 复制代码 
# 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

python 复制代码 
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

python 复制代码 
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🚀

python 复制代码 
                   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

相关推荐
无脑敲代码，bug漫天飞2 分钟前
COR 损失函数
人工智能·机器学习
幽兰的天空6 分钟前
Python 中的模式匹配：深入了解 match 语句
开发语言·python
HPC_fac130520678161 小时前
以科学计算为切入点：剖析英伟达服务器过热难题
服务器·人工智能·深度学习·机器学习·计算机视觉·数据挖掘·gpu算力
网易独家音乐人Mike Zhou3 小时前
【卡尔曼滤波】数据预测Prediction观测器的理论推导及应用 C语言、Python实现（Kalman Filter）
c语言·python·单片机·物联网·算法·嵌入式·iot
安静读书4 小时前
Python解析视频FPS(帧率)、分辨率信息
python·opencv·音视频
小陈phd4 小时前
OpenCV从入门到精通实战(九)——基于dlib的疲劳监测 ear计算
人工智能·opencv·计算机视觉
Guofu_Liao5 小时前
大语言模型---LoRA简介；LoRA的优势；LoRA训练步骤；总结
人工智能·语言模型·自然语言处理·矩阵·llama
小二·5 小时前
java基础面试题笔记（基础篇）
java·笔记·python
小喵要摸鱼7 小时前
Python 神经网络项目常用语法
python
一念之坤8 小时前
零基础学Python之数据结构 -- 01篇
数据结构·python
热门推荐
01(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明02PyTorch机器学习实现液态神经网络03【HarmonyOS】HUAWEI DevEco Studio 下载地址汇总04玄机平台应急响应—webshell查杀05Coze扣子平台完整体验和实践（附国内和国际版对比）06Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO07【目标跟踪】相机运动补偿08Unity中PICO实现 隔空取物 和 接触抓取物体09RAG 实践- Ollama+RagFlow 部署本地知识库10怎样让音频速度变慢？请跟随以下方法进行操作