ultralytics/models/v3/yolov3-spp.yaml

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv3-SPP object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/yolov3

# Parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# darknet53 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   [-1, 1, Bottleneck, [64]],
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
   [-1, 2, Bottleneck, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
   [-1, 8, Bottleneck, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
   [-1, 8, Bottleneck, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
   [-1, 4, Bottleneck, [1024]],  # 10
  ]

# YOLOv3-SPP head
head:
  [[-1, 1, Bottleneck, [1024, False]],
   [-1, 1, SPP, [512, [5, 9, 13]]],
   [-1, 1, Conv, [1024, 3, 1]],
   [-1, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)

   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
   [-1, 1, Bottleneck, [512, False]],
   [-1, 1, Bottleneck, [512, False]],
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)

   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
   [-1, 1, Bottleneck, [256, False]],
   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)

   [[27, 22, 15], 1, Detect, [nc]],   # Detect(P3, P4, P5)
  ]