py-R-FCN
py-R-FCN copied to clipboard
can't reproduce the mAP reported in readme, only 28.0 mAP in coco minival
hi:
I have run the traning code without change anyting for three times, but get lower mAP than you report in the readme, here's the details:
VOC: 07+12 trainval ,07test, mine: 79.1 the reported: 79.4 COCO: COCO 2014 train, COCO 2014 minival, mine: 28.0 (with 1920000 iter) the reported: 29.0 (though I test on 2014 minival, I think it won't be much different from the 2014 val )
my test env: python 2.7 , TITAN X (Pascal) 12G, I also reset git 1a2be8e. so anything wrong? i wanna know what should i care to reproduce the results.
bests jemmy li
i also have the problem.... in addition,did you meet the problem that the loss is nan(loss_bbox is nan),from Iteration 45000??