of course it fit and fit_generator will rarely be equivalent on large datasets. this will happen with any DL framework, not just keras.

the bug is in the fact that deep learning will behave as expected if training and testing data come from similar distributions. while this is almost always the case for small datasets, it might diverge quite dramatically in large ones.

Written by

Managing Director @ amethix.com Chief Software Engineer & Host @datascienceathome.com

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store