models/cfg/vanilla/visdrone_yolov8m.yaml

# parameters
nc: 80  # number of classes

# depth_multiple: 1.33  # model depth multiple
# width_multiple: 1.25  # layer channel multiple
# # anchors  1920
# anchors:
#   - [8,10,  10,22, 20,18]  # P3/8
#   - [23,40,  49,28,  41,59]  # P4/16
#   - [93,48,  81,93,  170,140]  # P5/32

depth_multiple: 0.67  # model depth multiple
width_multiple: 0.75  # layer channel multiple
# anchors  1536
anchors:
  - [6,8,    10,22,  19,15]  # P3/8
  - [19,32,  39,22,  32,47]  # P4/16
  - [74,38,  65,74,  136,112]  # P5/32

# YOLOv5 backbone
backbone:
  # [from, number, 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, SPPF, [1024, 5]],    # 9
  ]

# YOLOv5 head
head:
  [[-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C2f, [512, False]],  # 12

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

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

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

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