YOLOv9有效改进|使用空间和通道重建卷积SCConv改进RepNCSPELAN4

---

专栏介绍：YOLOv9改进系列 | 包含深度学习最新创新，主力高效涨点！！！

---

一、改进点介绍

        SCConv是一种即插即用的空间和通道重建卷积。

        RepNCSPELAN4是YOLOv9中的特征提取模块，类似YOLOv5和v8中的C2f与C3模块。

---

二、RepNCSPELAN4_SCConv模块详解

 2.1 模块简介

       RepNCSPELAN4_SCConv的主要思想：  使用SCConv替换RepNCSPELAN4中的Conv模块。

---

三、 RepNCSPELAN4_SCConv模块使用教程

3.1 RepNCSPELAN4_SCConv模块的代码

class RepNBottleneck_SC(RepNBottleneck):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__( c1, c2, shortcut, g, k, e)
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = RepConvN(c1, c_, k[0], 1)
        self.cv2 = SCConv(c_, c2, s=1, g=g)
        self.add = shortcut and c1 == c2


class RepNCSP_SCConv(RepNCSP):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_)
        self.cv2 = SCConv(c1, c_)
        self.cv3 = Conv(2 * c_, c2)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(RepNBottleneck_SC(c_, c_, shortcut, g, e=1.0) for _ in range(n)))


class RepNCSPELAN4SCConv(RepNCSPELAN4):
    # csp-elan
    def __init__(self, c1, c2, c3, c4, c5=1):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__(c1, c2, c3, c4, c5)
        self.cv1 = Conv(c1, c3, k=1, s=1)
        self.cv2 = nn.Sequential(RepNCSP_SCConv(c3 // 2, c4, c5), SCConv(c4, c4))
        self.cv3 = nn.Sequential(RepNCSP_SCConv(c4, c4, c5), SCConv(c4, c4))
        self.cv4 = Conv(c3 + (2 * c4), c2, 1, 1)

class SCConv(nn.Module):
    """https://github.com/MCG-NKU/SCNet/blob/master/scnet.py"""
    def __init__(self, inplanes, planes,k=3, s=1, p=1, dilation=1, g=1, pooling_r=4):
        super(SCConv, self).__init__()
        self.k2 = nn.Sequential(
                    nn.AvgPool2d(kernel_size=pooling_r, stride=pooling_r),
                    Conv(inplanes, planes, k=k, s=s, p=p, d=dilation, g=g, act=False))
        self.k3 = Conv(inplanes, planes, k=k, s=s, p=p, d=dilation, g=g, act=False)

        self.k4 = Conv(inplanes, planes, k=k, s=s, p=p, d=dilation, g=g, act=False)

    def forward(self, x):
        identity = x

        out = torch.sigmoid(torch.add(identity, F.interpolate(self.k2(x), identity.size()[2:]))) # sigmoid(identity + k2)
        out = torch.mul(self.k3(x), out)    # k3 * sigmoid(identity + k2)
        out = self.k4(out)  # k4

        return out

---

3.2 在YOlO v9中的添加教程

阅读YOLOv9添加模块教程或使用下文操作

        1. 将YOLOv9工程中models下common.py文件中的最下行（否则可能因类继承报错）增加模块的代码。

​

         2. 将YOLOv9工程中models下yolo.py文件中的第681行（可能因版本变化而变化）增加以下代码。

          RepNCSPELAN4, SPPELAN, RepNCSPELAN4SCConv1}:

---

3.3 运行配置文件

# YOLOv9
# Powered bu https://blog.csdn.net/StopAndGoyyy

# parameters
nc: 80  # number of classes
#depth_multiple: 0.33  # model depth multiple
depth_multiple: 1  # model depth multiple
#width_multiple: 0.25  # layer channel multiple
width_multiple: 1  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3

# YOLOv9 backbone
backbone:
  [
   [-1, 1, Silence, []],  
   
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4SCConv1, [256, 128, 64, 1]],  # 3

   # avg-conv down
   [-1, 1, ADown, [256]],  # 4-P3/8

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 5

   # avg-conv down
   [-1, 1, ADown, [512]],  # 6-P4/16

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 7

   # avg-conv down
   [-1, 1, ADown, [512]],  # 8-P5/32

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 9
  ]

# YOLOv9 head
head:
  [
   # elan-spp block
   [-1, 1, SPPELAN, [512, 256]],  # 10

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 13

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P3

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]],  # 16 (P3/8-small)

   # avg-conv-down merge
   [-1, 1, ADown, [256]],
   [[-1, 13], 1, Concat, [1]],  # cat head P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 19 (P4/16-medium)

   # avg-conv-down merge
   [-1, 1, ADown, [512]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 22 (P5/32-large)
   
   
   # multi-level reversible auxiliary branch
   
   # routing
   [5, 1, CBLinear, [[256]]], # 23
   [7, 1, CBLinear, [[256, 512]]], # 24
   [9, 1, CBLinear, [[256, 512, 512]]], # 25
   
   # conv down
   [0, 1, Conv, [64, 3, 2]],  # 26-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 27-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]],  # 28

   # avg-conv down fuse
   [-1, 1, ADown, [256]],  # 29-P3/8
   [[23, 24, 25, -1], 1, CBFuse, [[0, 0, 0]]], # 30  

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]],  # 31

   # avg-conv down fuse
   [-1, 1, ADown, [512]],  # 32-P4/16
   [[24, 25, -1], 1, CBFuse, [[1, 1]]], # 33 

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 34

   # avg-conv down fuse
   [-1, 1, ADown, [512]],  # 35-P5/32
   [[25, -1], 1, CBFuse, [[2]]], # 36

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]],  # 37
   
   
   
   # detection head

   # detect
   [[31, 34, 37, 16, 19, 22], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]

3.4 训练过程

​

---

欢迎关注!

---