Does the periodic rate require a periodic batch size?

Batch Normalization uses the average mini-batch and variance to normalize the output level. If I train a network with a batch size of, say 100, but then you want to use the trained network for one-shot predictions (batch size 1), should you expect problems? Do I have to punish the level of party norms in order to converge to the transformation of identity during training in order to avoid this?

+4
source share
1 answer

No, there are no problems in doing this, during testing, the level of normalization of the party only scales and shifts inputs, taking into account factors obtained during training.

+3

All Articles