RFBNet Running test_RFB.py with your provided model, RFBNet300_VOC_80_7.pth, get a mAP of 0.8056 not 80.7% posted in your github.

Running test_RFB.py with your provided model, RFBNet300_VOC_80_7.pth, get a mAP of 0.8056 not 80.7% posted in your github.

Open ZhiqiJiang opened this issue 5 years ago • 6 comments

The command is python3 test_RFB.py --trained_model RFBNet300_VOC_80_7.pth. And the result is showed as below: Screenshot from 2019-04-12 10-55-46

Apr 12 '19 03:04 ZhiqiJiang

hellow,I run the command same with yours, but my APs of 20 classes and mAP are 0. Did you meet the same problem before the current results.

May 18 '19 12:05 love1314pds

@ love1314pds No I didn't. Maybe I modified something correspondingly.

Jun 11 '19 08:06 ZhiqiJiang

@love1314pds 我已经不止一次遇到跨框架引起精度损失这个问题了,就算是利用作者提供的pretrained model.我一直还没有耐下性子去定位分析乃至解决这个问题.

Jun 11 '19 08:06 ZhiqiJiang

嗯，好的，谢谢

Jun 12 '19 06:06 love1314pds

302f50c86b0ff30e845e6ca641bfe08 I use the same commad but ge't a map=0.459 But I didnot change anything~

Mar 13 '20 16:03 Feobi1999

Ps o

I have the same problem. Did you solve it?

Aug 28 '20 07:08 KrystalCWT