label smoothing one-sided?

[makeyourownalgorithmicart]

a previous issue was closed but I don't think it should be.

I'm opening this as I don't know how to request re-opening that one: https://github.com/soumith/ganhacks/issues/10

there are two opinions:

• only smooth D (0s and 1s)
• only smooth 1s for data sources coming from the training data and G

which one is not clear yet