举例
比如某一次的输出结果如下
训练log中各参数的意义
5: 10.222071, 10.294983 avg loss, 0.000000 rate, 395.829699 seconds, 320 images
Loaded: 0.000000 seconds
Region Avg IOU: 0.227881, Class: 1.000000, Obj: 0.381839, No Obj: 0.465026, Avg Recall: 0.000000, count: 16
Region Avg IOU: 0.203516, Class: 1.000000, Obj: 0.494320, No Obj: 0.466775, Avg Recall: 0.000000, count: 8
Region Avg IOU: 0.313356, Class: 1.000000, Obj: 0.474162, No Obj: 0.466196, Avg Recall: 0.307692, count: 13
Region Avg IOU: 0.267079, Class: 1.000000, Obj: 0.500940, No Obj: 0.466384, Avg Recall: 0.250000, count: 8
Region Avg IOU: 0.419788, Class: 1.000000, Obj: 0.423686, No Obj: 0.466252, Avg Recall: 0.428571, count: 7
Region Avg IOU: 0.361871, Class: 1.000000, Obj: 0.427209, No Obj: 0.466280, Avg Recall: 0.200000, count: 10
Region Avg IOU: 0.365572, Class: 1.000000, Obj: 0.430385, No Obj: 0.466651, Avg Recall: 0.125000, count: 8
Region Avg IOU: 0.342102, Class: 1.000000, Obj: 0.417325, No Obj: 0.466240, Avg Recall: 0.222222, count: 9
参考源码
region_layer.c ==> forward_region_layer()函数最后一行：
printf("Region Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, Avg Recall: %f, count: %d\n",
avg_iou/count, avg_cat/class_count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, count);
解释
5 -- batch iteration, 表次训练了多少个batch次，或者说batch -> batch -> batch ....这样共训练了多少个轮回
10.222071 －total loss
10.294983 - average loss, 平均损失率，最终结构的评估参数，越小越好，官网给出例子是
- 9002 - iteration number (number of batch)
- 0.060730 avg - average loss (error) - the lower, the better（差不达到这个点，或不再下降，就可以停下来了）
Region Avg IOU - 平均的IOU，是预测的bounding box和ground truth的交集与并集之比，期望该值趋近于1。
Class: 标注物体的概率（找到了多少个类/共有多少个类），期望该值趋近于1（俺这只有一个类，是1）
Obj -- 表示把正本判断为正本得到的平均confidence，该期望该值趋近于1.
No Obj -- 表示总confidence/总box数，期望该值越来越小但不为零.
Avg Recall：找出来的正本数 与 总的正本数之比值，期望该值趋近于1
count: 总共找到的正本数
