MenghaoGuo/PCT

Question about training

xinze98 opened this issue · 1 comments

Hello Guo! I found that much more epochs were needed in part_seg task when I replaced the model in Pointnet++ with PCT. (Pointnet++ code from https://github.com/yanx27/Pointnet_Pointnet2_pytorch)

Pointnet++ needs less than 50 epochs while PCT needs more than 500 epochs. Is this caused by model complexity? Have you found same question when training?

We don't observe this in the experiments. I suggest you can adjust this initial learning rate.