Deep Learning with Keras

API changes

The Keras 2.0 changes implied the need to rethink some APIs. For full details, please refer to the release notes (https://github.com/fchollet/keras/wiki/Keras-2.0-release-notes). This module legacy.py summarizes the most impactful changes and prevents warnings when using Keras 1.x calls:

""Utility functions to avoid warnings while testing both Keras 1 and 2."""import keraskeras_2 = int(keras.__version__.split(".")[0]) > 1 # Keras > 1def fit_generator(model, generator, epochs, steps_per_epoch):    if keras_2:        model.fit_generator(generator, epochs=epochs, steps_per_epoch=steps_per_epoch)    else:        model.fit_generator(generator, nb_epoch=epochs, samples_per_epoch=steps_per_epoch)def fit(model, x, y, nb_epoch=10, *args, **kwargs): if keras_2: ...