当前位置： 首页 > news >正文

YOLO11改进 | 卷积模块 | 轻量化GSConv替换普通的conv

news 2025/5/6 19:40:17

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

为什么订阅我的专栏？

  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

目标检测是计算机视觉中一项重要的下游任务。对于边缘计算平台而言，庞大的模型难以满足实时检测的需求。而由大量深度可分离卷积层构建的轻量级模型又无法达到足够的精度。本文介绍了一种新的轻量级卷积技术 GSConv，旨在减轻模型负担的同时保持精度。GSConv 在模型的精度和速度之间取得了出色的平衡。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. 代码实现

2.1 添加GSConv到YOLO11代码中

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：Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles——点击即可跳转

官方代码：官方代码仓库——点击即可跳转

2. 代码实现

2.1 添加GSConv到YOLO11代码中

关键步骤一：在/ultralytics/ultralytics/nn/modules/下面新建GSConv.py，并将下面的代码复制进去，

import torch
from torch import nndef autopad(k, p=None):  # kernel, padding# Pad to 'same'if p is None:p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-padreturn pclass Conv(nn.Module):# Standard convolutiondef __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groupssuper().__init__()self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)self.bn = nn.BatchNorm2d(c2)self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())def forward(self, x):return self.act(self.bn(self.conv(x)))def forward_fuse(self, x):return self.act(self.conv(x))class GSConv(nn.Module):# GSConv https://github.com/AlanLi1997/slim-neck-by-gsconvdef __init__(self, c1, c2, k=1, s=1, g=1, act=True):super().__init__()c_ = c2 // 2self.cv1 = Conv(c1, c_, k, s, None, g, act)self.cv2 = Conv(c_, c_, 5, 1, None, c_ , act)def forward(self, x):x1 = self.cv1(x)x2 = torch.cat((x1, self.cv2(x1)), 1)# shuffle# y = x2.reshape(x2.shape[0], 2, x2.shape[1] // 2, x2.shape[2], x2.shape[3])# y = y.permute(0, 2, 1, 3, 4)# return y.reshape(y.shape[0], -1, y.shape[3], y.shape[4])b, n, h, w = x2.data.size()b_n = b * n // 2y = x2.reshape(b_n, 2, h * w)y = y.permute(1, 0, 2)y = y.reshape(2, -1, n // 2, h, w)return torch.cat((y[0], y[1]), 1)

2.2 更改init.py文件

关键步骤二：修改/ultralytics/ultralytics/nn/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_GS.yaml并将下面代码复制进去

  •  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 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, GSConv, [64, 3, 2]] # 0-P1/2- [-1, 1, GSConv, [128, 3, 2]] # 1-P2/4- [-1, 2, C3k2, [256, False, 0.25]]- [-1, 1, GSConv, [256, 3, 2]] # 3-P3/8- [-1, 2, C3k2, [512, False, 0.25]]- [-1, 1, GSConv, [512, 3, 2]] # 5-P4/16- [-1, 2, C3k2, [512, True]]- [-1, 1, GSConv, [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, GSConv, [256, 3, 2]]- [[-1, 13], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, GSConv, [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
# 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, GSConv, [64, 3, 2]] # 0-P1/2- [-1, 1, GSConv, [128, 3, 2]] # 1-P2/4- [-1, 2, C3k2, [256, False, 0.25]]- [-1, 1, GSConv, [256, 3, 2]] # 3-P3/8- [-1, 2, C3k2, [512, False, 0.25]]- [-1, 1, GSConv, [512, 3, 2]] # 5-P4/16- [-1, 2, C3k2, [512, True]]- [-1, 1, GSConv, [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, GSConv, [256, 3, 2]]- [[-1, 13], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, GSConv, [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)
  • 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 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, GSConv, [64, 3, 2]] # 0-P1/2- [-1, 1, GSConv, [128, 3, 2]] # 1-P2/4- [-1, 2, C3k2, [256, False, 0.25]]- [-1, 1, GSConv, [256, 3, 2]] # 3-P3/8- [-1, 2, C3k2, [512, False, 0.25]]- [-1, 1, GSConv, [512, 3, 2]] # 5-P4/16- [-1, 2, C3k2, [512, True]]- [-1, 1, GSConv, [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, GSConv, [256, 3, 2]]- [[-1, 13], 1, Concat, [1]] # cat head P4- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)- [-1, 1, GSConv, [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。

# 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GSconv

2.5 执行程序

在train.py中，将model的参数路径设置为yolo11_GSConv.yaml的路径

建议大家写绝对路径，确保一定能找到

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

报错解决：

若报错内容如下

    self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
TypeError: autopad() takes from 1 to 2 positional arguments but 3 were given

则在Conv.py中找打Conv这个类换成下面的代码

class Conv(nn.Module):"""Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""default_act = nn.SiLU()  # default activationdef __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):"""Initialize Conv layer with given arguments including activation."""super().__init__()self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, dilation=d, bias=False)self.bn = nn.BatchNorm2d(c2)self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()def forward(self, x):"""Apply convolution, batch normalization and activation to input tensor."""return self.act(self.bn(self.conv(x)))def forward_fuse(self, x):"""Perform transposed convolution of 2D data."""return self.act(self.conv(x))

 🚀运行程序，如果出现下面的内容则说明添加成功🚀  

                   from  n    params  module                                       arguments0                  -1  1       448  ultralytics.nn.modules.conv.GSConv           [3, 16, 3, 2]1                  -1  1      2768  ultralytics.nn.modules.conv.GSConv           [16, 32, 3, 2]2                  -1  1      6640  ultralytics.nn.modules.block.C3k2            [32, 64, 1, False, 0.25]3                  -1  1     19360  ultralytics.nn.modules.conv.GSConv           [64, 64, 3, 2]4                  -1  1     26080  ultralytics.nn.modules.block.C3k2            [64, 128, 1, False, 0.25]5                  -1  1     75584  ultralytics.nn.modules.conv.GSConv           [128, 128, 3, 2]6                  -1  1     87040  ultralytics.nn.modules.block.C3k2            [128, 128, 1, True]7                  -1  1    151168  ultralytics.nn.modules.conv.GSConv           [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     19360  ultralytics.nn.modules.conv.GSConv           [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     75584  ultralytics.nn.modules.conv.GSConv           [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_GSConv summary: 425 layers, 2,298,384 parameters, 2,298,368 gradients, 5.8 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？

  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.mrgr.cn/news/43237.html

相关文章：

  • MySQL基础之DML
  • Python | 使用Seaborn绘制KDE核密度估计曲线
  • java基础进阶知识点汇总（1）
  • NVIDIA网卡系列之ConnectX-6 DX规格信息(200G-PCIe 4.0x16-8PF1000VF-2019年发布)
  • JavaWeb程序设计（第四版）习题参考答案
  • 【Hadoop】改一下core-site.xml和hdfs-site.xml配置就可以访问Web UI
  • CSP-S 2021 T1廊桥分配
  • 面试手撕代码-手写线程池（优雅打断版本）
  • 【论文速看】DL最新进展20241005-Transformer、目标跟踪、Diffusion Transformer
  • [python]Flask_Login
  • 一、走进新语言
  • DatePicker 日期控件
  • Python 工具库每日推荐 【Pandas】
  • 【智能算法应用】蒲公英优化算法求解二维路径规划问题
  • etcd 集群搭建【docker-compose】
  • TMGM：黄金价格持稳，而WTI原油价格和天然气价格飙升
  • 【C#生态园】提高开发效率：6种必备C#开发库全面解析
  • 【操作系统】引导（Boot）电脑的奇妙开机过程
  • django华业社区电子政务管理系统-计算机毕业设计源码33448
  • 69. x 的平方根