sunxia233

I re-executed the experiment, iou can reach 0.83

I ran the experiment on veri-776 according to your settings, Accuracy obtained for the first time mAP: 77.4% [I 210121 15:20:54 main:473] CMC curve, Rank-1 :95.89% [I 210121 15:20:54 main:473]...

我重新看了一下intervention和do运算，为了消除M对X的影响，这里是考虑头部类别和尾部类别数量不均衡的情况，因此是以控制变量的思想使用ClassAwaresampler的让尾部数据和头部数据采样一样多的次数是这样把。。