How to calculate num_per_class?

[AbdulNur71]

Dear QingyongHu, Congratulations and thanks for your interesting paper RandLA-Net. I am trying to perform it, it is going good. Could you please let me know, in helper_tool.py, page 4-5/6, you pre calculated the number of points in each of 8 categories, for example for Semantic3D data. i.e., num_per_class = np.array ([5181602, 5012952, 6830086, 1311528, 10476365, 946982, 334860, 269353], dtype = np.int32). I thought that the numbers are of the points exist in each class in the training data, and I tried different ways to find but do not match with yours. Could you please advise how you calculated the numbers? thanks in advance.

[TanKecheng]

Hello, Have you understood the problem, please? I am also very confused about this question.

[DayongRen]

Dear QingyongHu, Congratulations and thanks for your interesting paper RandLA-Net. I am trying to perform it, it is going good. Could you please let me know, in helper_tool.py, page 4-5/6, you pre calculated the number of points in each of 8 categories, for example for Semantic3D data. i.e., num_per_class = np.array ([5181602, 5012952, 6830086, 1311528, 10476365, 946982, 334860, 269353], dtype = np.int32). I thought that the numbers are of the points exist in each class in the training data, and I tried different ways to find but do not match with yours. Could you please advise how you calculated the numbers? thanks in advance.

Hello, Have you understood the problem, please? I am also very confused about this question.