Shane Zhao
Shane Zhao
> Hello, I have the same problem, is there any way to solve this problem?
491498408
> Have you ever increase the positive iou threshold for rcnn, and increase the nms threhold of retinanet for more proposals? > > ``` > Following Wang et al.(2019), we...
> @zhaoxin111 Hello, would you open source your reimplementation of retinanet+rcnn? The code will be open sourced after I finish it.
> Hey, > I am happy to see, that someone else is also trying to use CenterNet2 in mmdetection. > > As for now, I didn't manage to get a...
I reimplement Faster RCNN-Retinanet with mmdetection, the mAP is worse than origin faster rcnn. Looking forward to more details.
> I can't download from below: > http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat > any other alternative link available? 用迅雷
> will it be too big for baiduyun?下午5:22, 2018年9月18日, Matrix : I can't download from below: http://horatio.cs.nyu.edu/mit/silberman/nyu_depth_v2/nyu_depth_v2_labeled.mat any other alternative link available? 用迅雷 —You are receiving this because you commented.Reply...