Shathe
some of the prediction label's total num doesn't match points num
when i use visualize to watch the infer result it simply raise valueError and tells me that the num of the two doesn't match,some are equal but many are still not equal.how to solve this.
later i found that infer.py is calling loaders that self.training is True,which will allow the augmentation to delete some points randomly,change the self.training to False in user.py can solve the problem.
hello, i got the same problem and cannot find where to change self.training. Can you tell me where to change it? @hungkyun
hello, i got the same problem and cannot find where to change self.training. Can you tell me where to change it? @hungkyun
In parser.py, line 316, ''gt=self.gt, training=True)'', set training=False, and it works. Because when on inferring stage, the training is still True so it results in the augmentation to delete some points as @hungkyun said or you could set a flag to control that parameter.
