darknet yolo 层设置

[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear


[yolo]
mask = 3,4,5
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

COCO数据集的类别数(cfg中的classes)为80,anchor数(cfg中的anchors)设置为9个,则filter个数(cfg中的filters)设置如上,规则如下公式:

image.png

你可能感兴趣的:(darknet yolo 层设置)