In case of layerGraphbased approach we use trainNetworkto train the network and this function takes the entire data for the training. In case imageInputLayerthe Normalization used is 'zerocenter' by default and Meanis '[ ]' by default i.e., the software calculates the mean at training time on the complete data within the trainNetworkfunction.
In case of dlnetworkbased approach we won't use the trainNetworkfunction and instead use custom training loops. In this case we pass minibatches (minibatchqueue) of the data during each iteration of custom training loop. Hence the mean is not automatically calculated here.