Batch Normalization has different behavior in training phase and testing phase.
For example, when using tf.contrib.layers.batch_norm in tensorflow, we should set different value for is_training in different phase.
My qusetion is: what if I still set is_training=True when testing? That is to say what if I still use the training mode in testing phase?
The reason why I come up with this question is that, the released code of both Pix2Pix and DualGAN don't set is_training=False when testing. And it seems that if is_training=False is set when testing, the quality of generated images could be very bad.
Is there someone could please explain this? thanks.