Batch normalize regression objective in training and undo it in testing

In a regression network, I would like to use batch normalization on the objective y to obtain y_norm to fit. Because y_norm is well distributed.

In testing stage after training, I need to "undo" a batch normalization on the predicted y_norm. Is there any elegant way in tensorflow/keras in which I can construct an "undo" layer from the origin BN layer?