YOLO11改进 | 卷积模块 | 减少冗余计算和内存访问的PConv【CVPR2023】

devtools/2024/12/22 20:15:05/

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💡💡💡


本文介绍了一个新的部分卷积(PConv),它能更有效地提取空间特征,同时减少冗余的计算和内存访问。基于PConv,进一步提出了FasterNet,这是一个新的神经网络家族,它在各种设备上实现了比其他网络更高的运行速度,同时不会在各种视觉任务上牺牲准确性。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

YOLOv8%E4%BB%A3%E7%A0%81-toc" style="margin-left:0px;">2. 将PConv添加到YOLO11代码

2.1 PConv代码实现

2.2 更改init.py文件

2.3 新增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:Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks ——点击即可跳转

官方代码:官方代码仓库——点击即可跳转

YOLOv8%E4%BB%A3%E7%A0%81">2. 将PConv添加到YOLO11代码

2.1 PConv代码实现

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

python">class PConv(nn.Module):def __init__(self, dim, ouc, n_div=4, forward='split_cat'):super().__init__()self.dim_conv3 = dim // n_divself.dim_untouched = dim - self.dim_conv3self.partial_conv3 = nn.Conv2d(self.dim_conv3, self.dim_conv3, 3, 1, 1, bias=False)self.conv = Conv(dim, ouc, k=1)if forward == 'slicing':self.forward = self.forward_slicingelif forward == 'split_cat':self.forward = self.forward_split_catelse:raise NotImplementedErrordef forward_slicing(self, x):# only for inferencex = x.clone()  # !!! Keep the original input intact for the residual connection laterx[:, :self.dim_conv3, :, :] = self.partial_conv3(x[:, :self.dim_conv3, :, :])x = self.conv(x)return xdef forward_split_cat(self, x):# for training/inferencex1, x2 = torch.split(x, [self.dim_conv3, self.dim_untouched], dim=1)x1 = self.partial_conv3(x1)x = torch.cat((x1, x2), 1)x = self.conv(x)return x

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 新增yaml文件

关键步骤三:在 \ultralytics\ultralytics\cfg\models\11下新建文件 yolo11_PConv.yaml并将下面代码复制进去

python"># 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, PConv, [128]] # 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)- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)
  • 语义分割
python"># 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, PConv, [128]] # 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)- [[16, 19, 22], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)
python"># 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 GFLOPss: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPsm: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPsl: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPsx: [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, PConv, [128]] # 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)- [[16, 19, 22], 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"># 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,

2.5 执行程序

在train.py中,将model的参数路径设置为yolo11_PConv.yaml的路径

建议大家写绝对路径,确保一定能找到

python">from ultralytics import YOLO
import warnings
warnings.filterwarnings('ignore')
from pathlib import Pathif __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 modelresults = 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">                   from  n    params  module                                       arguments0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]1                  -1  1       720  ultralytics.nn.modules.conv.PConv            [16, 32]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        [16, 19, 22]  1    464912  ultralytics.nn.modules.head.Detect           [80, [64, 128, 256]]
YOLO11_PConv summary: 321 layers, 2,620,128 parameters, 2,620,112 gradients, 25.3 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

通过上面的方法,改进就完成且成功了。在这里给大家推荐我的专栏YOLO11改进有效涨点专栏,本专栏目前是新建的,后期我会持续对各种前沿顶会进行论文复现,如果本文对你有帮助,欢迎订阅本专栏,关注后续更多的更新~如果有问题,可以随时问我


http://www.ppmy.cn/devtools/121273.html

相关文章

技术成神之路:设计模式(十六)代理模式

介绍 代理模式(Proxy Pattern)是一种结构性设计模式,它通过代理对象来控制对另一个对象的访问。代理对象在功能上与真实对象相似,但可以在访问真实对象前后添加一些额外的处理。代理模式常用于控制对某个对象的访问、延迟实例化、…

Solidity 设计模式:实现灵活与可扩展的智能合约架构

Solidity 作为以太坊智能合约的主要编程语言,拥有许多独特的设计模式,这些模式帮助开发者实现更加灵活、可扩展和安全的合约架构。设计模式不仅能够简化开发过程,还能减少常见的编程错误,并提高智能合约的可维护性和可升级性。本文…

计算机毕业设计 农场投入品运营管理系统的设计与实现 Java实战项目 附源码+文档+视频讲解

博主介绍:✌从事软件开发10年之余,专注于Java技术领域、Python人工智能及数据挖掘、小程序项目开发和Android项目开发等。CSDN、掘金、华为云、InfoQ、阿里云等平台优质作者✌ 🍅文末获取源码联系🍅 👇🏻 精…

Golang | Leetcode Golang题解之第448题找到所有数组中消失的数字

题目&#xff1a; 题解&#xff1a; func findDisappearedNumbers(nums []int) (ans []int) {n : len(nums)for _, v : range nums {v (v - 1) % nnums[v] n}for i, v : range nums {if v < n {ans append(ans, i1)}}return }

无水印短视频素材下载网站有哪些?十个高清无水印视频素材网站分享

你知道怎么下载无水印视频素材吗&#xff1f;今天小编就给大家推荐十个高清无水印视频素材下载的网站&#xff0c;如果你也是苦于下载高清无水印的短视频素材&#xff0c;赶紧来看看吧&#xff5e; 1. 稻虎网 首推的是稻虎网。这个网站简直就是短视频创作者的宝库。无论你需要…

34 指针与函数:值传递与引用传递、指针函数、函数指针、回调函数

目录 1 值传递 2 传递指针给函数 2.1 传地址或指针给函数 2.2 传数组给函数 3 指针函数&#xff08;返回指针的函数&#xff09; 3.1 语法格式 3.2 案例&#xff1a;返回静态局部变量 3.3 案例&#xff1a;返回字符串 3.4 案例&#xff1a;返回较长的字符串 3.5 案例…

网络安全的详细学习顺序

网络安全的详细学习顺序可以按照由浅入深、逐步递进的原则进行。以下是一个建议的网络安全学习顺序&#xff1a; 1. 基础知识学习 计算机网络基础&#xff1a;理解网络架构、TCP/IP协议栈、OSI七层模型、数据链路层到应用层的工作原理。 操作系统基础&#xff1a;了解Window…

基于Hive和Hadoop的用电量分析系统

本项目是一个基于大数据技术的用电量分析系统&#xff0c;旨在为用户提供全面的电力消耗信息和深入的用电量分析。系统采用 Hadoop 平台进行大规模数据存储和处理&#xff0c;利用 MapReduce 进行数据分析和处理&#xff0c;通过 Sqoop 实现数据的导入导出&#xff0c;以 Spark…