Why there is no difference in using batch_norm function when training and testing?

[JianqiangRen]

batch_norm( inputs, decay=0.999, center=True, scale=False, epsilon=0.001, activation_fn=None, param_initializers=None, param_regularizers=None, updates_collections=tf.GraphKeys.UPDATE_OPS, is_training=True, reuse=None, variables_collections=None, outputs_collections=None, trainable=True, batch_weights=None, fused=None, data_format=DATA_FORMAT_NHWC, zero_debias_moving_mean=False, scope=None, renorm=False, renorm_clipping=None, renorm_decay=0.99 )

parameters are listed above, and is_training should be true when model is under traing ,false when testing, but why there is no such difference in these codes?

[ppwwyyxx]

Answer is in the paper.