yolob8改进-使用CVPR 2023 | SCConv替换SPPF

1.新建一个block.py（放SCConV源码）

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

__all__ =["ScConv"]

class 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_num
        self.group_num  = group_num
        self.weight     = nn.Parameter( torch.randn(c_num, 1, 1)    )
        self.bias       = nn.Parameter( torch.zeros(c_num, 1, 1)    )
        self.eps        = eps
    def 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.bias


class 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_treshold
        self.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 )
        # Gate
        w1          = 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 * x
        x_2         = w2 * x
        y           = self.reconstruct(x_1,x_2)
        return y
    
    def 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_channel
        self.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)
        #up
        self.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)
        #low
        self.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):
        # Split
        up,low  = torch.split(x,[self.up_channel,self.low_channel],dim=1)
        up,low  = self.squeeze1(up),self.squeeze2(low)
        # Transform
        Y1      = self.GWC(up) + self.PWC1(up)
        Y2      = torch.cat( [self.PWC2(low), low], dim= 1 )
        # Fuse
        out     = torch.cat( [Y1,Y2], dim= 1 )
        out     = F.softmax( self.advavg(out), dim=1 ) * out
        out1,out2 = torch.split(out,out.size(1)//2,dim=1)
        return out1+out2


class 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


if __name__ == '__main__':
    x       = torch.randn(1,32,16,16)
    model   = ScConv(32)
    print(model(x).shape)

2.修改task.py（源码太长了不放了）

修改思路：导入-> 修改parse_model（）函数

添加

elif m in {ScConv}:

            c2=ch[f]

            args=[c2,*args]

必须使用大括号，不然会报错

3.修改yolov8.yaml

 使用ScConv替换普通卷积会增大很多GFLOPs，我也不太理解，替换SPPF基本不会增加

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 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=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n 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, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, ScConv, []] # 9

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 3, C2f, [512]] # 12

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 3, C2f, [256]] # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]] # cat head P4
  - [-1, 3, C2f, [512]] # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]] # cat head P5
  - [-1, 3, C2f, [1024]] # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

最后实验结果发现map没有涨.......就学学