anachor计算

[hyz001]

我使用gen_anchors.py,生成anchors，数据集是自己标注的商品数据，box大小差不多，18个class，结果是：
0.66,1.33, 0.78,2.37, 0.96,1.60, 1.08,1.08, 1.10,2.88, 1.23,1.89, 1.47,1.32, 1.60,2.63, 1.82,1.70
0.824868
数值这么小，正确吗？

[AlexeyAB]

gen_anchors.py is for Yolo v2 (not for Yolo v3)

Yes, in the yolo v2 the anchors have small values:

darknet/cfg/yolov2-voc.cfg

Line 242 in 552207d

anchors = 1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071

[hyz001]

recalculate anchors for your dataset for width and height from cfg-file: darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 416 -height 416 then set the same 9 anchors in each of 3 [yolo]-layers in your cfg-file
这个指令在我电脑运行不出来，请问yolov3如何计算anachor？