YOLOv9独家改进|使用HWD(小波下采样)模块改进ADown

---

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

        HWD是一种下采样模型，应用了小波变换的方法。

        ADown是YOLOv9中的下采样模块，对不同的数据场景具有一定的可学习能力。

---

二、HWD-ADown模块详解

 2.1 模块简介

       HWD-ADown的主要思想：  使用HWD替换ADown中的Conv模块。

---

三、 HWD-ADown模块使用教程

3.1 HWD-ADown模块的代码

try:
    from mmcv.cnn import build_activation_layer, build_norm_layer
    from mmcv.ops.modulated_deform_conv import ModulatedDeformConv2d
    from mmengine.model import constant_init, normal_init
except ImportError as e:
    pass

"""
论文地址：https://arxiv.org/pdf/2208.03641v1.pdf
"""


class HWD_ADown(nn.Module):
    def __init__(self, c1, c2):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
        self.c = c2 // 2
        # self.cv1 = Conv(c1 // 2, self.c, 3, 2, 1)
        self.cv1 = HWD(c1 // 2, self.c, 3, 1, 1)
        self.cv2 = Conv(c1 // 2, self.c, 1, 1, 0)

    def forward(self, x):
        x = nn.functional.avg_pool2d(x, 2, 1, 0, False, True)
        x1, x2 = x.chunk(2, 1)
        x1 = self.cv1(x1)
        x2 = torch.nn.functional.max_pool2d(x2, 3, 2, 1)
        x2 = self.cv2(x2)
        return torch.cat((x1, x2), 1)


class HWD(nn.Module):
    def __init__(self, in_ch, out_ch, k, s, p):
        super(HWD, self).__init__()
        from pytorch_wavelets import DWTForward
        self.wt = DWTForward(J=1, mode='zero', wave='haar')
        self.conv = Conv(in_ch * 4, out_ch, k, s, p)

    def forward(self, x):
        yL, yH = self.wt(x)
        y_HL = yH[0][:, :, 0, ::]
        y_LH = yH[0][:, :, 1, ::]
        y_HH = yH[0][:, :, 2, ::]
        x = torch.cat([yL, y_HL, y_LH, y_HH], dim=1)
        x = self.conv(x)
        return x

---

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, HWD_ADown}:

---

3.3 运行配置文件

# YOLOv9
# ⭐⭐Powered by https://blog.csdn.net/StopAndGoyyy,  技术指导QQ:2668825911⭐⭐

# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3
# ⭐⭐Powered by https://blog.csdn.net/StopAndGoyyy,  技术指导QQ:2668825911⭐⭐
# 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, HWD_ADown, [256]],  # 4-P3/8

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

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

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

   # avg-conv down
   [-1, 1, HWD_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, HWD_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, HWD_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!

---