YOLOv9独家原创改进|加入空间和通道重建卷积SCConv模块！

news2024/11/25 2:44:13

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、本文介绍

本文将一步步演示如何在YOLOv9中添加 / 替换新模块，寻找模型上的创新！

适用检测目标： YOLOv9模块通用改进

二、改进步骤

《YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information》

论文地址： https://ieeexplore.ieee.org/abstract/document/10204928

代码地址： https://github.com/MCG-NKU/SCNet/blob/master/scnet.py

2.1 创建一个脚本存放新模块

为方便调用，这里我将脚本放在models包下，命名为extra.py。

2.2 将模块复制到脚本中，并导入需要的包（以SCConv为例）

我们将SCConv的代码复制到刚刚创建的extra.py脚本中。

import torch
import torch.nn as nn
import torch.nn.functional as F

from models.common import Conv


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

        self.k4 = Conv(inplanes, planes, k=3, s=1, p=padding, d=dilation, g=groups, 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

2.3 对yolo.py操作

打开models包下的yolo.py文件夹，将刚才创建的脚本导入。并在下方第700行的位置(位置可能因v9版本更新变动)加入下方代码。

2.4 运行配置文件

创建模型配置文件（yaml文件），将我们所作改进加入到配置文件中（这一步的配置文件可以复制models - > detect 下的yaml修改。）。对YOLO系列yaml文件不熟悉的同学可以看我往期的yaml详解教学！

YOLO系列 “.yaml“文件解读-CSDN博客

# YOLOv9

# parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.25  # 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, RepNCSPELAN4, [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
   [-1, 1, SCConv, []],  # 38

   
   
   # detection head

   # detect
   [[31, 34, 38, 16, 19, 22], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]