microsoft/Semi-supervised-learning

[Question] Regarding the Unused m Parameter in the RandAugment Class.

SasaSho opened this issue · 2 comments

Hello,

I was reviewing the code for the RandAugment class and I noticed that the m parameter, which is set during initialization, does not seem to be utilized anywhere within the class. Additionally, I observed that it is marked as deprecated in the constructor (self.m = m # [0, 30] in fixmatch, deprecated.).

I am curious to know the rationale behind not utilizing the m parameter to potentially control the intensity of transformations within the class. It seems like it could be a significant parameter for adjusting the extent of augmentations applied to the images.

Furthermore, could you please shed some light on why it is marked as deprecated in the constructor? Does it indicate a shift in the approach towards image augmentation, or is there another reason?

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

This issue was closed because it has been stalled for 5 days with no activity.