batch_normalization should be involved in Test mode

[liurida]

When is_train, the bn is added. But test, it's ignored. based on the doc in the page, https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/layers/python/layers/layers.py logic should be like the desc below: is_training: Whether or not the layer is in training mode. In training mode it would accumulate the statistics of the moments into moving_mean and moving_variance using an exponential moving average with the given decay. When it is not in training mode then it would use the values of the moving_mean and the moving_variance.