yolov5 C3改进|深度可分离卷积轻量化主干

一、深度可分离卷积代码

import torch
import torch.nn as nn


class DP_Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(DP_Conv, self).__init__()
        self.conv = nn.Conv2d(c1, c1, kernel_size=3, stride=1, padding=1, groups=c1)
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=s)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
        #self.act = h_swish()
 
    def forward(self, x):
        return self.act(self.bn(self.conv(x)))
 
    def fuseforward(self, x):
        return self.act(self.conv(x))
 
class DP_Bottleneck(nn.Module):
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(DP_Bottleneck, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = DP_Conv(c1, c_, 1)
        self.cv2 = DP_Conv(c_, c2, 1)
        self.add = shortcut and c1 == c2
        
    def forward(self, x): 
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
 
class DP_C3(nn.Module):
    # 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(DP_C3, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = DP_Conv(c1, c_, 1)
        self.cv2 = DP_Conv(c1, c_, 1)
        self.cv3 = DP_Conv(2 * c_, c2, 1)  # act=FReLU(c2)
        self.m = nn.Sequential(*[DP_Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])  
        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
 
    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

二、yaml文件

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]