File size: 1,699 Bytes
1e84a23 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # expand model depth
width_multiple: 1.0 # expand layer channels
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# 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, BottleneckCSP, [64]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 2, BottleneckCSP, [128]],
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
[-1, 8, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
[-1, 8, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
[-1, 4, BottleneckCSP, [1024]], # 10
]
# yolov3-spp head
# na = len(anchors[0])
head:
[[-1, 1, Bottleneck, [1024, False]], # 11
[-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]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 16 (P5/32-large)
[-3, 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]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 24 (P4/16-medium)
[-3, 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]],
[-1, 1, nn.Conv2d, [na * (nc + 5), 1, 1]], # 30 (P3/8-small)
[[], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
|