QingWindIsStillTheWind

I would like to ask the next author, if the size of the image used for network training is 960x540, then when I want to use this network test, the...

I would like to ask the author, if the size of the image used for network training is 960x540, then when I want to use this network test, the resolution...

请问按照论文所讲，作者您是使用了Scannet数据集中的18个类别进行测试，请问在训练的时候，是否将18个类之外的其余类别当作背景一起进行训练呢？还是说只选取了18个类的点云进行训练？

问题一：请问这个.h5文件里的coords是什么呢？ 问题二：coords和point有何区别，point里面的0-9的顺序分别是什么xyzrgbx’y‘z或者x’y'z'xyzrgb？ 问题三：不知道自己理解的对不对，我看.h5里面的数据不是已经归一化到0-1了吗，为什么在load_fixed_points函数中再次归一化呢？ 感谢您的解答

Test image size problem

1

I would like to ask the author, if the size of the image used for network training is 960x540, then when I want to use this network test, the resolution...

What are the evaluation indicators in the paper [email protected] It is np.mean(p) listed in the code ? If not, how should we calculate to get the information in the paper...

Test image size problem

1

I would like to ask the author, if the size of the image used for network training is 960x540, then when I want to use this network test, the resolution...

请问这个耗时多少秒