当前位置： 首页 > news >正文

YOLO11改进 | 卷积模块 | 用Ghost卷积轻量化网络【详细步骤】

news 2025/4/30 15:11:40

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💡💡💡

Ghost 模块可以作为即插即用组件来升级现有的卷积神经网络。 Ghostbottleneck旨在堆叠Ghost模块，然后可以轻松建立轻量级的GhostNet。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GhostConv添加到YOLO11代码

2.1 GhostConv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：GhostNet: More Features from Cheap Operations 

官方代码：官方代码地址——点击即可跳转

2. 将GhostConv添加到YOLO11代码

2.1 GhostConv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

class GhostConv(nn.Module):# Ghost Convolution https://github.com/huawei-noah/ghostnetdef __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groupssuper().__init__()c_ = c2 // 2  # hidden channelsself.cv1 = Conv(c1, c_, k, s, None, g, act)self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)def forward(self, x):y = self.cv1(x)return torch.cat((y, self.cv2(y)), 1)class Ghost(nn.Module):# Ghost Bottleneck https://github.com/huawei-noah/ghostnetdef __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stridesuper(Ghost, self).__init__()c_ = c2 // 2self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pwDWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dwGhostConv(c_, c2, 1, 1, act=False))  # pw-linearself.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()def forward(self, x):return self.conv(x) + self.shortcut(x)

2.2 更改init.py文件 

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

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

2.5 执行程序

在train.py中，将model的参数路径设置为yolo11_GhostConv.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

🚀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.GhostConv        [3, 16, 3, 2]1                  -1  1      2768  ultralytics.nn.modules.conv.GhostConv        [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.GhostConv        [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.GhostConv        [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.GhostConv        [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.GhostConv        [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.GhostConv        [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_GhostConv summary: 347 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.mrgr.cn/news/43865.html

相关文章：

  • 蓝桥杯省赛真题打卡day4
  • 常用的英文论文查重网站
  • LeetCode hot100---贪心算法专题(C++语言)
  • late-chunk，尝试拯救硬切分的缺点。有序chunk，产生条理性response。
  • Buck电路-电感电容轻松计算
  • AI生成文章标题指定路径保存：创新工具助力内容创作高效启航
  • 面试算法题
  • Acwing 线性DP
  • 基于auth2的单点登录原理理解
  • react-问卷星项目（7）
  • 老系统处理策略
  • Javascript客户端时间与服务器时间
  • aws(学习笔记第二课) AWS SDK（node js）
  • DMA直接存储器存取
  • 工具 | 红队大佬亲测5款推荐的Burpsuite插件
  • 模型 SECI(知识的创造)
  • 一些硬件知识（二十七）
  • Vivado - JTAG to AXI Master (DDR4)
  • C++面试速通宝典——11
  • 类和对象的学习1