前言:
不知道原理的尝试,直接训练看结果如何。
一、新建yolov8-BiFPN-P2.yaml文件
文件内容如下:
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [4, 1, Conv, [256]] # 10
- [6, 1, Conv, [256]] # 11
- [9, 1, Conv, [256]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 11], 1, Concat, [1]]
- [-1, 3, C2f, [256]] # 15
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 10], 1, Concat, [1]]
- [-1, 3, C2f, [256]]
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] #19
- [2, 1, Conv, [256]]
- [[-1, 19], 1, Concat, [1]]
- [-1, 3, C2f, [256]] #22
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 10, 18], 1, Concat, [1]]
- [-1, 3, C2f, [256]] # 25
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11, 15], 1, Concat, [1]]
- [-1, 3, C2f, [256]] # 28
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]]
- [-1, 3, C2f, [256]] # 31
- [[22, 25, 28,31], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)
二、总结
亲测结果:模型量减少,但其他指标均有所降低(精度、召回率等)。总之,整体效果变差,针对本目标不可行。