jiangtianyuan
jiangtianyuan
> Hello @traveller59 and @repa1022 , I have the same problem, The evaluation result in [email protected],0.7,0.7 and [email protected],0.5,0.5 are totally different, i understand that for 0.5 is different from 0.7,...
Have you solved this question? I get the same questions
> Got the same > I changed backend port to 16666 and it works Thank you for your reply. But my problem still exists. I think this may be a...
> The GT masks are represented as polygons(a set of points) in the json file, but the number of the points is different for different objects, you need to sample...
> @LittleYuanzi @skyhehe123 hello,can you get the same mAP as authors?,I clone this project,and download the pretrained model ,but the result mAP is lower about 6％．and I trained the model...
> Those are the ignored values which are set in `DataLoader` for nearby points of the enlarged cuboid as here https://github.com/sshaoshuai/Pointnet2.PyTorch/blob/master/tools/dataset.py#L165 thank you very much