Learning Data Mining with Python - Second Edition

Deeper networks

These techniques will probably fool our current implementation, so improvements will need to be made to make the method better. Try some of the deeper networks we used. Larger networks need more data, though, so you will probably need to generate more than the few thousand samples we did here in order to get good performance. Generating these datasets is a good candidate for parallelization—lots of small tasks that can be performed independently.

A good idea for increasing your dataset size, which applies to other datasets as well, is to create variants of existing images. Flip images upside down, crop them weirdly, add noise, blur the image, make some random pixels black and so on.