声明：不讲原理、只说改进、只看效果

一、HWD_Down代码

class HWD_ADown(nn.Module):
    def __init__(self, c1, c2):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
       # c1 = c1.float()
       # c2 = c2.floats()
        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 = x.float()  # 将输入数据转换为float类型
        
        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)
       # self.conv = Conv(in_ch * 4, out_ch, k, s, p, bias=False, dtype=torch.half)  # 假设Conv类支持dtype参数
 
    def forward(self, x):
       # x = x.float()  # 将输入数据转换为float类型
        yL, yH = self.wt(x.float())
        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复制

二、插入位置

直接替换原有ADown位置即可，在yolo.py文件中替换为见下图：

看上下文代码直接换。

三、yaml文件示例

# YOLOv9

# 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

# 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, HWD_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, HWD_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, HWD_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)
  ]
复制

四、运行成功截图

重新跑太麻烦，直接粘贴中间；在运行之前需关闭混合精度训练；不多做赘述。

推荐内容