# parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [116,90, 156,198, 373,326] # P5/32
- [30,61, 62,45, 59,119] # P4/16
- [10,13, 16,30, 33,23] # P3/8
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, BottleneckCSP, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
]
# YOLOv5 head
head:
[[-1, 3, BottleneckCSP, [1024, False]], # 9
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 18 (P3/8-small)
[-2, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 22 (P4/16-medium)
[-2, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 26 (P5/32-large)
[[], 1, Detect, [nc, anchors]], # Detect(P5, P4, P3)
]
