Layer Normalization, with average power constraints

Question

I'm studying the paper "An Introduction to Deep Learning for the Physical Layer". While implementing the proposed network with python Keras, I should normalize some values, output of former layer.
One way is simple L2 Normalization, ||X||^2 = 1, where X is a tensor of former layer output.
as a code

from keras import backend as K
Lambda(lambda x: K.l2_normalize(x,axis=1))

The other way, what I want to know, is ||X||^2 ≤ 1.
Is there any way that constrains the value of layer outputs?

Answer 1

I solved it!
That normalization can be easily implemented by using 'Batch Normalization'.