YOLOv11融合CVPR[2023]空间和通道重建卷积ScConv模块及相关改进思路|YOLO改进最简教程

---

YOLOv11v10v8使用教程：  YOLOv11入门到入土使用教程

YOLOv11改进汇总贴：YOLOv11及自研模型更新汇总 

---

《SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy》

一、 模块介绍

        论文链接：SCConv: Spatial and Channel Reconstruction Convolution...

        代码链接（大佬复现）：https://github.com/cheng-haha/ScConv

论文速览：卷积神经网络 （CNN） 在各种计算机视觉任务中取得了卓越的性能，但这是以消耗大量计算资源为代价的，部分原因是卷积层提取了冗余特征。最近的工作要么压缩训练有素的大型模型，要么探索设计良好的轻量级模型。在本文中，我们尝试利用特征之间的空间和通道冗余进行 CNN 压缩，并提出了一种高效的卷积模块，称为 SCConv（空间和通道重建卷积），以减少冗余计算并促进代表性特征学习。所提出的 SCConv 由两个单元组成：空间重建单元 （SRU） 和通道重建单元 （CRU）。SRU 采用 separate-and-reconstruct 方法来抑制空间冗余，而 CRU 使用 split-transform-andfuse 策略来减少通道冗余。此外，SCConv 是一个即插即用的架构单元，可用于直接替换各种卷积神经网络中的标准卷积。实验结果表明，SCConv 嵌入式模型能够通过减少冗余特征来实现更好的性能，从而显著降低复杂性和计算成本。

总结：轻量化模块，好用。​

---

二、 加入到YOLO中

2.1 创建脚本文件

        首先在ultralytics->nn路径下创建blocks.py脚本，用于存放模块代码。

2.2 复制代码        

        复制代码粘到刚刚创建的blocks.py脚本中，如下图所示：

import torch
import torch.nn as nn
import torch.nn.functional as Fclass GroupBatchnorm2d(nn.Module):def __init__(self, c_num: int,group_num: int = 16,eps: float = 1e-10):super(GroupBatchnorm2d, self).__init__()assert c_num >= group_numself.group_num = group_numself.weight = nn.Parameter(torch.randn(c_num, 1, 1))self.bias = nn.Parameter(torch.zeros(c_num, 1, 1))self.eps = epsdef forward(self, x):N, C, H, W = x.size()x = x.view(N, self.group_num, -1)mean = x.mean(dim=2, keepdim=True)std = x.std(dim=2, keepdim=True)x = (x - mean) / (std + self.eps)x = x.view(N, C, H, W)return x * self.weight + self.biasclass SRU(nn.Module):def __init__(self,oup_channels: int,group_num: int = 16,gate_treshold: float = 0.5,torch_gn: bool = True):super().__init__()self.gn = nn.GroupNorm(num_channels=oup_channels, num_groups=group_num) if torch_gn else GroupBatchnorm2d(c_num=oup_channels, group_num=group_num)self.gate_treshold = gate_tresholdself.sigomid = nn.Sigmoid()def forward(self, x):gn_x = self.gn(x)w_gamma = self.gn.weight / sum(self.gn.weight)w_gamma = w_gamma.view(1, -1, 1, 1)reweigts = self.sigomid(gn_x * w_gamma)# Gatew1 = torch.where(reweigts > self.gate_treshold, torch.ones_like(reweigts), reweigts)  # 大于门限值的设为1，否则保留原值w2 = torch.where(reweigts > self.gate_treshold, torch.zeros_like(reweigts), reweigts)  # 大于门限值的设为0，否则保留原值x_1 = w1 * xx_2 = w2 * xy = self.reconstruct(x_1, x_2)return ydef reconstruct(self, x_1, x_2):x_11, x_12 = torch.split(x_1, x_1.size(1) // 2, dim=1)x_21, x_22 = torch.split(x_2, x_2.size(1) // 2, dim=1)return torch.cat([x_11 + x_22, x_12 + x_21], dim=1)class CRU(nn.Module):'''alpha: 0<alpha<1'''def __init__(self,op_channel: int,alpha: float = 1 / 2,squeeze_radio: int = 2,group_size: int = 2,group_kernel_size: int = 3,):super().__init__()self.up_channel = up_channel = int(alpha * op_channel)self.low_channel = low_channel = op_channel - up_channelself.squeeze1 = nn.Conv2d(up_channel, up_channel // squeeze_radio, kernel_size=1, bias=False)self.squeeze2 = nn.Conv2d(low_channel, low_channel // squeeze_radio, kernel_size=1, bias=False)# upself.GWC = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=group_kernel_size, stride=1,padding=group_kernel_size // 2, groups=group_size)self.PWC1 = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=1, bias=False)# lowself.PWC2 = nn.Conv2d(low_channel // squeeze_radio, op_channel - low_channel // squeeze_radio, kernel_size=1,bias=False)self.advavg = nn.AdaptiveAvgPool2d(1)def forward(self, x):# Splitup, low = torch.split(x, [self.up_channel, self.low_channel], dim=1)up, low = self.squeeze1(up), self.squeeze2(low)# TransformY1 = self.GWC(up) + self.PWC1(up)Y2 = torch.cat([self.PWC2(low), low], dim=1)# Fuseout = torch.cat([Y1, Y2], dim=1)out = F.softmax(self.advavg(out), dim=1) * outout1, out2 = torch.split(out, out.size(1) // 2, dim=1)return out1 + out2class ScConv(nn.Module):def __init__(self,op_channel: int,group_num: int = 4,gate_treshold: float = 0.5,alpha: float = 1 / 2,squeeze_radio: int = 2,group_size: int = 2,group_kernel_size: int = 3,):super().__init__()self.SRU = SRU(op_channel,group_num=group_num,gate_treshold=gate_treshold)self.CRU = CRU(op_channel,alpha=alpha,squeeze_radio=squeeze_radio,group_size=group_size,group_kernel_size=group_kernel_size)def forward(self, x):x = self.SRU(x)x = self.CRU(x)return x

2.3 更改task.py文件 

       打开ultralytics->nn->modules->task.py，在脚本空白处导入函数。

from ultralytics.nn.blocks import *

        之后找到模型解析函数parse_model（约在tasks.py脚本中940行左右位置，可能因代码版本不同变动），在该函数的最后一个else分支上面增加相关解析代码。

        elif m is ScConv:c2 = ch[f]args = [ch[f], ]

2.4 更改yaml文件 

yam文件解读：YOLO系列 “.yaml“文件解读_yolo yaml文件-CSDN博客

       打开更改ultralytics/cfg/models/11路径下的YOLOv11.yaml文件，替换原有模块。（放在该位置仅能插入该模块，具体效果未知。博主精力有限，仅完成与其他模块二次创新融合的测试，结构图见文末，代码见群文件更新。）

# 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, 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, ScConv, []]- [-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)

---

 2.5 修改train.py文件

       创建Train脚本用于训练。

from ultralytics.models import YOLO
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'if __name__ == '__main__':model = YOLO(model='ultralytics/cfg/models/11/yolo11.yaml')# model.load('yolov8n.pt')model.train(data='./data.yaml', epochs=2, batch=1, device='0', imgsz=640, workers=2, cache=False,amp=True, mosaic=False, project='runs/train', name='exp')

         在train.py脚本中填入修改好的yaml路径，运行即可训练，数据集创建教程见下方链接。

YOLOv11入门到入土使用教程(含结构图)_yolov11使用教程-CSDN博客

三、相关改进思路（2024/11/16日群文件）

根据ScConv模块特性，可替换C2f、C3模块中的BottleNeck部分，代码见群文件，结构如图。

 ⭐另外，融合上百种深度学习改进模块的YOLO项目仅79.9（含百种改进的v9），RTDETR79.9,含高性能自研模型，更易发论文，代码每周更新，欢迎点击下方小卡片加我了解。⭐

---