models/cfg/vanilla/visdrone_rtmdetm.yaml

# parameters
nc: 10  # 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, [32, 3, 2]],  
   [-1, 1, Conv, [32, 3, 1]],  
   [-1, 1, Conv, [64, 3, 1]],  # 2-P1/2 
   [-1, 1, Conv, [128, 3, 2]],  
   [-1, 3, RTMDetCSPLayer, [128, True, True]],  # 4-P2/4
   [-1, 1, Conv, [256, 3, 2]],  
   [-1, 6, RTMDetCSPLayer, [256, True, True]],  # 6-P3/8

   ###
   
   [-1, 1, Conv, [512, 3, 2]],  
   [-1, 6, RTMDetCSPLayer, [512, True, True]],  # 8-P4/16
   [-1, 1, Conv, [1024, 3, 2]],  
   [-1, 1, SPP, [1024, [5, 9, 13]]],
   [-1, 3, RTMDetCSPLayer, [1024, False, True]],  # 11-P5/32
  ]

# YOLOv5 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, RTMDetCSPLayer, [512, False, False]],  # 15

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, RTMDetCSPLayer, [256, False, False]],  # 19 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 16], 1, Concat, [1]],  # cat head P4
   [-1, 3, RTMDetCSPLayer, [512, False, False]],  # 22 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 12], 1, Concat, [1]],  # cat head P5
   [-1, 3, RTMDetCSPLayer, [1024, False, False]],  # 25 (P5/32-large)

   [[19, 22, 25], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]