# Batch normalization vs batch size

I have noticed that my performance of VGG 16 network gets better if I increase the batch size from $$64$$ to $$256$$. I have also observed that, using batch size $$64$$, the with and without batch normalization results have lot of difference. With batch norm results being poorer. As I increase the batch size the performance of with and without batch normalization gets closer. Something funky going on here.

So I would like to ask is the increase in batch size have effect on batch normalization?

• Adding batchnorm right after the relu layers? – Aditya Nov 30 '18 at 6:57
• tried both after relu and before relu, both results are poorer than without BN. – Haramoz Nov 30 '18 at 15:39