charlesq34/pointnet

ZeroDivisionError: float division by zero

noridayu1998 opened this issue · 3 comments

noridayu1998 commented

File "D:\1. PSM 2020\pointnet\pointnet-master\sem_seg\train.py", line 228, in train_one_epoch
log_string('mean loss: %f' % (loss_sum / float(num_batches)))

ZeroDivisionError: float division by zero

I have an error when running the sem_seg train.py.

Nhunguts commented

Hi @noridayu1998 , did you train with the original data ore your own data? I met this error when batch_size is greater than the number of point cloud.

  • 👍1
yuhan1010 commented

@noridayu1998 hi there, although we use different pointnet++ codes, there is a same problem when I run train_semseg.py. (BTW, I referred the code programming by yanx27)

songqiming97 commented

@noridayu1998 hi there, although we use different pointnet++ codes, there is a same problem when I run train_semseg.py. (BTW, I referred the code programming by yanx27)
I had the same problem. Have you solved it？