feature dropout

[cxw-droid]

Hi, thank you for you code.

PyGCL/GCL/augmentors/functional.py

Line 100 in c2f4dc7

 return F.dropout(x, p=1. - drop_prob) 

May I know why you set the F.dropout probability to 1. - drop_prob instead of the original drop_prob? I.e., why the code here is not return F.dropout(x, p=drop_prob)? Thanks.