models/cfg/esod/uavdt_yolov5m.yaml

# parameters
nc: 1  # number of classes
depth_multiple: 0.67  # model depth multiple
width_multiple: 0.75  # layer channel multiple

# anchors  1024
anchors:
 - [14,16,  22,26,  40,21]  # P3/8
 - [37,30,  24,46,  56,26]  # P4/16
 - [40,48,  85,59,  144,114]  # P5/32

# YOLOv5 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],  # 0-P1/2 ~ RF=(2-1)*1+3=4
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4 ~ RF=(4-1)*2+3=9
   [-1, 3, C3, [128]],  # RF=9+2*(3*0.33)=9+2=11  or  9+6=15
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8 ~ RF=(11-1)*2+3=23  or (15-1)*2+3=31
   [-1, 9, C3, [256]],  # RF=23+2*(9*0.33)=23+6=29  or 31+18=49

   [-1, 1, SPP, [256, [5, 9, 13]]],
#   [-1, 1, ASPP, [256, [1, 2, 4, 6]]],
   [[-1], 1, Segmenter, [1]],
   [[4, -1], 1, HeatMapParser, [256, 8, 0.3]],  # 7, from 4 or 5? : 4.

   [-1, 1, Conv, [512, 3, 2]],  # 8-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 10-P5/32
   [-1, 1, SPP, [1024, [3, 5, 7]]],  # 5,9,13
   [-1, 3, C3, [1024, False]],  # 12
  ]

# YOLOv5 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 9], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 16

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 20 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 17], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 23 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 26 (P5/32-large)

   [[20, 23, 26], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]