about the parameter innitialization of BatchNorm

[zcc1019]

I am a new learner of Deeplearning.I Confused by some code.

in your acnet.abc.py. what the meaning of reduce_gama and gamma_int. they seem to be two defferent innitialization method. when is the proper time or occation to do innitialization for each
innitialization method? and why the choice of the use_last_bn must be different from the choice of reduce_gama, what the accosiation between two viarables.
I am trying to understand the code and applying in my own code. Thank your for your sharing and attention

[DingXiaoH]

They are just variants I once tried in my experiments. Maybe they would work better in some cases.
The default arguments are the configurations reported in the paper (not use_last_bn and gamma_init = 1).