基于改进 YOLOv5 的小目标检测论文代码复现

使用yolov5-6.0源码、yolov5x.yaml、yolov5x.pt

1、在主干网络中, 加入CBAM 注意力模块增强网络特征提取能力
参考：加入CBAM

# 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, CABlock, [128, 4]],
   [-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
  ]

2、在颈部网络部分, 使用 BiFPN 结构替换 PANet 结构, 强化底层特征利用; （将所有的Concat改为BiFPN_Concat2）
参考： BiFPN

# YOLOv5 head
head:
  [[-1, 1, Conv, [512, 1, 1]],  #20*20
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], #40*40
   [[-1, 6], 1, BiFPN_Concat2, [1]],  # cat backbone P4  40*40
   [-1, 3, BottleneckCSP, [512, False]],  # 13     40*40
 
   [-1, 1, Conv, [512, 1, 1]], #40*40
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, BiFPN_Concat2, [1]],  # cat backbone P3   80*80
   [-1, 3, BottleneckCSP, [512, False]],  # 17 (P3/8-small)  80*80
 
   [-1, 1, Conv, [256, 1, 1]], #18  80*80
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], #19  160*160
   [[-1, 2], 1, BiFPN_Concat2, [1]], #20 cat backbone p2  160*160
   [-1, 3, BottleneckCSP, [256, False]], #21 160*160
 
   [-1, 1, Conv, [256, 3, 2]],  #22   80*80
   [[-1, 18], 1, BiFPN_Concat2, [1]], #23 80*80
   [-1, 3, BottleneckCSP, [256, False]], #24 80*80
 
   [-1, 1, Conv, [256, 3, 2]], #25  40*40
   [[-1, 14], 1, BiFPN_Concat2, [1]],  # 26  cat head P4  40*40
   [-1, 3, BottleneckCSP, [512, False]],  # 27 (P4/16-medium) 40*40
 
   [-1, 1, Conv, [512, 3, 2]],  #28  20*20
   [[-1, 10], 1, BiFPN_Concat2, [1]],  #29 cat head P5  #20*20
   [-1, 3, BottleneckCSP, [1024, False]],  # 30 (P5/32-large)  20*20
 
   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(p2, P3, P4, P5)
  ]

3、在检测头部分, 增加高分辨率检测头, 改善对于微小目标的检测能力
参考：检测头

# Parameters
nc: 2  # number of classes
depth_multiple: 1.33  # model depth multiple
width_multiple: 1.25  # layer channel multiple
anchors:
  - [5,6, 8,14, 15,11]  #4
  - [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 head
head:
  [[-1, 1, Conv, [512, 1, 1]],  #20*20
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], #40*40
   [[-1, 6], 1, BiFPN_Concat2, [1]],  # cat backbone P4  40*40
   [-1, 3, BottleneckCSP, [512, False]],  # 13     40*40
 
   [-1, 1, Conv, [512, 1, 1]], #40*40
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, BiFPN_Concat2, [1]],  # cat backbone P3   80*80
   [-1, 3, BottleneckCSP, [512, False]],  # 17 (P3/8-small)  80*80
 
   [-1, 1, Conv, [256, 1, 1]], #18  80*80
   [-1, 1, nn.Upsample, [None, 2, 'nearest']], #19  160*160
   [[-1, 2], 1, BiFPN_Concat2, [1]], #20 cat backbone p2  160*160
   [-1, 3, BottleneckCSP, [256, False]], #21 160*160
 
   [-1, 1, Conv, [256, 3, 2]],  #22   80*80
   [[-1, 18], 1, BiFPN_Concat2, [1]], #23 80*80
   [-1, 3, BottleneckCSP, [256, False]], #24 80*80
 
   [-1, 1, Conv, [256, 3, 2]], #25  40*40
   [[-1, 14], 1, BiFPN_Concat2, [1]],  # 26  cat head P4  40*40
   [-1, 3, BottleneckCSP, [512, False]],  # 27 (P4/16-medium) 40*40
 
   [-1, 1, Conv, [512, 3, 2]],  #28  20*20
   [[-1, 10], 1, BiFPN_Concat2, [1]],  #29 cat head P5  #20*20
   [-1, 3, BottleneckCSP, [1024, False]],  # 30 (P5/32-large)  20*20
 
   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(p2, P3, P4, P5)
  ]