In step 1, we used NormalizerStandardize to normalize the dataset. NormalizerStandardize normalizes the data (features) so they have a mean of 0 and a standard deviation of 1. In other words, all the values in the dataset will be normalized within the range of (0, 1):

DataNormalization normalization = new NormalizerStandardize();
 normalization.fit(trainIterator);

This is a standard normalizer in DL4J, although there are other normalizer implementations available in DL4J. Also, note that we don't need to call fit() on test data because we use the scaling parameters learned during training to scale the test data.

We need to call the setPreprocessor() method as we demonstrated in step 2 for both train/test iterators. Once we have set the normalizer using setPreprocessor(), the data returned by the iterator will be auto-normalized using the specified normalizer. Hence it is important to call setPreprocessor() along with the fit() method.