Useful Keras features

Manish Chablani
Towards Data Science
10 min readJun 3, 2017

--

Here is the summary of interesting features that I feel I will find useful to reference when I am building a deep learning pipeline a.k.a things I usually don’t remember. From Keras documentation at https://keras.io and other online posts.

How can I interrupt training when the validation loss isn’t decreasing anymore?

You can use an EarlyStopping callback:

from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(monitor='val_loss', patience=2)
model.fit(X, y

--

--

Head of AI @EightSleep , Marathoner. (Past: AI in healthcare @curaiHQ , DL for self driving cars @cruise , ML @Uber , Early engineer @MicrosoftAzure cloud