发现有小伙伴在使用yolo8训练自己模型时,不知道如何选择模型规模。
如果是yolov8原模型,在训练的时候大家都知道用yolov8s,yolov8n这样子选择
用其他自定义模型时,如果模型yaml有如下内容
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8s.yaml' will call yolov8.yaml with scale 's'
# [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
那么也可以通过在yolov8后加标识指定模型大小,如yolov8s-repvgg.yaml,yolov8n-repvgg.yaml
如果是下面这样
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # scales module repeats
width_multiple: 0.50 # scales convolution channels
则需要将下面两个变量改成自己需要的大小就可以了