This article felt a bit unfair to TensorFlow, which now includes Keras.
Rafael Espericueta

Keras does not address the issues of TensorFlow. In fact Keras makes it harder to build new architectures for research. Keras is meant to make classic algorithms easy to run and be conveniently used as black boxes. You don’t need keras for pytorch since it’s easy to build the “fit” and “predict” functions with it.

Like what you read? Give Issam Laradji a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.