About batch_normalization

[mrgloom]

affinelayer/pix2pix-tensorflow#126

face2face-demo/reduce_model.py

Line 42 in 19d916a

def batchnorm(inputs):

Also about your comment

face2face-demo/reduce_model.py

Line 45 in 19d916a

# # this block looks like it has 3 inputs on the graph unless we do this

Isn't use unique name for each tf.layers.batch_normalization is sufficient? (by default its name=None)
affinelayer/pix2pix-tensorflow#126 (comment)