models/detect/gelan-e.yaml

# YOLOv9

# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()

# anchors
anchors: 3

# gelan backbone
backbone:
  [
   [-1, 1, Silence, []],
  
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2

   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4

   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]],  # 3

   # avg-conv down
   [-1, 1, ADown, [256]],  # 4-P3/8

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]],  # 5

   # avg-conv down
   [-1, 1, ADown, [512]],  # 6-P4/16

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]],  # 7

   # avg-conv down
   [-1, 1, ADown, [1024]],  # 8-P5/32

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]],  # 9
   
   # routing
   [1, 1, CBLinear, [[64]]], # 10
   [3, 1, CBLinear, [[64, 128]]], # 11
   [5, 1, CBLinear, [[64, 128, 256]]], # 12
   [7, 1, CBLinear, [[64, 128, 256, 512]]], # 13
   [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]], # 14
  
   # conv down fuse
   [0, 1, Conv, [64, 3, 2]],  # 15-P1/2
   [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]], # 16

   # conv down fuse
   [-1, 1, Conv, [128, 3, 2]],  # 17-P2/4
   [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]], # 18  

   # elan-1 block
   [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]],  # 19

   # avg-conv down fuse
   [-1, 1, ADown, [256]],  # 20-P3/8
   [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]], # 21  

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]],  # 22

   # avg-conv down fuse
   [-1, 1, ADown, [512]],  # 23-P4/16
   [[13, 14, -1], 1, CBFuse, [[3, 3]]], # 24 

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]],  # 25

   # avg-conv down fuse
   [-1, 1, ADown, [1024]],  # 26-P5/32
   [[14, -1], 1, CBFuse, [[4]]], # 27

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]],  # 28
  ]

# gelan head
head:
  [
   # elan-spp block
   [28, 1, SPPELAN, [512, 256]],  # 29

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 25], 1, Concat, [1]],  # cat backbone P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]],  # 32

   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 22], 1, Concat, [1]],  # cat backbone P3

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]],  # 35 (P3/8-small)

   # avg-conv-down merge
   [-1, 1, ADown, [256]],
   [[-1, 32], 1, Concat, [1]],  # cat head P4

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]],  # 38 (P4/16-medium)

   # avg-conv-down merge
   [-1, 1, ADown, [512]],
   [[-1, 29], 1, Concat, [1]],  # cat head P5

   # elan-2 block
   [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]],  # 41 (P5/32-large)

   # detect
   [[35, 38, 41], 1, DDetect, [nc]],  # Detect(P3, P4, P5)
  ]