Better generator integration/example

[drewbo]

Creating a data.npz file may result in too large a file for some projects. At that point it may be better to read the training data in with a generator (example: Keras flow_from_directory). The easiest way to do this now would be to skip the final step (label-maker package) and read directly from the labels.npz and the tiles directory. We should create either (1) an example showing how to do this or (2) additional scripts which perform this for the user depending upon configuration (or a combination of the two).

[wronk]

I vote for starting with (1) since it's the simplest and we avoid rewriting Keras's ImageDataGenerator functionality. If we want to show examples for other platforms (like MXNet or straight tensorflow) we can do (2), but then it might be worth separating that work into 2 issues.