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💡💡💡
本文给大家带来的教程是将YOLO11的卷积替换为一种轻量化的卷积结构来提取特征。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 将代码添加到YOLO11中
2.2 更改init.py文件
2.3 添加yaml文件
2.4 注册模块
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 lightweight-design for real-time detector architectures——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 将代码添加到YOLO11中
关键步骤一：在/ultralytics/ultralytics/nn/modules/下新建Slim-Neck.py，并粘贴下面代码
import torch
import torch.nn as nn
import math
def autopad(k, p=None, d=1):
"""
Pads kernel to 'same' output shape, adjusting for optional dilation; returns padding size.
`k`: kernel, `p`: padding, `d`: dilation.
"""
if d > 1:
k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
# Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
default_act = nn.SiLU() # default activation
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
"""Initializes a standard convolution layer with optional batch normalization and activation."""
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), 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):
"""Applies a convolution followed by batch normalization and an activation function to the input tensor `x`."""
return self.act(self.bn(self.conv(x)))
def forward_fuse(self, x):
"""Applies a fused convolution and activation function to the input tensor `x`."""
return self.act(self.conv(x))
class DWConv(Conv):
"""Depth-wise convolution."""
def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation
"""Initialize Depth-wise convolution with given parameters."""
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
class GSConv(nn.Module):
# GSConv https://github.com/AlanLi1997/slim-neck-by-gsconv
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
super().__init__()
c_ = c2 // 2
self.cv1 = Conv(c1, c_, k, s, p, g, d, Conv.default_act)
self.cv2 = Conv(c_, c_, 5, 1, p, c_, d, Conv.default_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.size()
b_n = b * n // 2
y = 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)
class GSConvns(GSConv):
# GSConv with a normative-shuffle https://github.com/AlanLi1997/slim-neck-by-gsconv
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
super().__init__(c1, c2, k, s, p, g, act=True)
c_ = c2 // 2
self.shuf = nn.Conv2d(c_ * 2, c2, 1, 1, 0, bias=False)
def forward(self, x):
x1 = self.cv1(x)
x2 = torch.cat((x1, self.cv2(x1)), 1)
# normative-shuffle, TRT supported
return nn.ReLU()(self.shuf(x2))
class GSBottleneck(nn.Module):
# GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv
def __init__(self, c1, c2, k=3, s=1, e=0.5):
super().__init__()
c_ = int(c2*e)
# for lighting
self.conv_lighting = nn.Sequential(
GSConv(c1, c_, 1, 1),
GSConv(c_, c2, 3, 1, act=False))
self.shortcut = Conv(c1, c2, 1, 1, act=False)
def forward(self, x):
return self.conv_lighting(x) + self.shortcut(x)
class GSBottleneckns(GSBottleneck):
# GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv
def __init__(self, c1, c2, k=3, s=1, e=0.5):
super().__init__(c1, c2, k, s, e)
c_ = int(c2*e)
# for lighting
self.conv_lighting = nn.Sequential(
GSConvns(c1, c_, 1, 1),
GSConvns(c_, c2, 3, 1, act=False))
class GSBottleneckC(GSBottleneck):
# cheap GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv
def __init__(self, c1, c2, k=3, s=1):
super().__init__(c1, c2, k, s)
self.shortcut = DWConv(c1, c2, k, s, act=False)
class VoVGSCSP(nn.Module):
# VoVGSCSP module with GSBottleneck
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.gsb = nn.Sequential(*(GSBottleneck(c_, c_, e=1.0) for _ in range(n)))
self.res = Conv(c_, c_, 3, 1, act=False)
self.cv3 = Conv(2 * c_, c2, 1)
def forward(self, x):
x1 = self.gsb(self.cv1(x))
y = self.cv2(x)
return self.cv3(torch.cat((y, x1), dim=1))
class VoVGSCSPns(VoVGSCSP):
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
self.gsb = nn.Sequential(*(GSBottleneckns(c_, c_, e=1.0) for _ in range(n)))
class VoVGSCSPC(VoVGSCSP):
# cheap VoVGSCSP module with GSBottleneck
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2)
c_ = int(c2 * 0.5) # hidden channels
self.gsb = GSBottleneckC(c_, c_, 1, 1)
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_slim-neck.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, 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, VoVGSCSP, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, VoVGSCSP, [256, False]] # 16 (P3/8-small)
- [-1, 1, GSConv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, VoVGSCSP, [512, False]] # 19 (P4/16-medium)
- [-1, 1, GSConv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, VoVGSCSP, [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 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, 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, VoVGSCSP, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, VoVGSCSP, [256, False]] # 16 (P3/8-small)
- [-1, 1, GSConv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, VoVGSCSP, [512, False]] # 19 (P4/16-medium)
- [-1, 1, GSConv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, VoVGSCSP, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 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, 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, VoVGSCSP, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, VoVGSCSP, [256, False]] # 16 (P3/8-small)
- [-1, 1, GSConv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, VoVGSCSP, [512, False]] # 19 (P4/16-medium)
- [-1, 1, GSConv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, VoVGSCSP, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, OBB, [nc, 1]] # OBB(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：5122.4 注册模块
关键步骤四：在task.py的parse_model函数添加 GSConv, VoVGSCSP, VoVGSCSPC,
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, VoVGSCSP, VoVGSCSPC,
还是这个函数，靠下面几行 添加
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_slim-neck.yaml的路径即可 【注意是在外边的Ultralytics下新建train.py】
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 1 448 ultralytics.nn.modules.models.slim_neck.GSConv [3, 16, 3, 2]
1 -1 1 2768 ultralytics.nn.modules.models.slim_neck.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.models.slim_neck.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.models.slim_neck.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.models.slim_neck.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 129600 ultralytics.nn.modules.models.slim_neck.VoVGSCSP [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 37152 ultralytics.nn.modules.models.slim_neck.VoVGSCSP [256, 64, 1, False]
17 -1 1 19360 ultralytics.nn.modules.models.slim_neck.GSConv [64, 64, 3, 2]
18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1]
19 -1 1 105024 ultralytics.nn.modules.models.slim_neck.VoVGSCSP [192, 128, 1, False]
20 -1 1 75584 ultralytics.nn.modules.models.slim_neck.GSConv [128, 128, 3, 2]
21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
22 -1 1 414848 ultralytics.nn.modules.models.slim_neck.VoVGSCSP [384, 256, 1, True]
23 [16, 19, 22] 1 464912 ultralytics.nn.modules.head.Detect [80, [64, 128, 256]]
YOLO11_slim_neck summary: 410 layers, 2,376,016 parameters, 2,376,000 gradients, 5.6 GFLOPs3.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——<专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅>。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？ ——专栏地址：YOLO11入门 + 改进涨点——点击即可跳转 欢迎订阅
-
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。
-
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。
-
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。
-
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
