Attention with Keras

This story introduces you to a Github repository which contains an atomic up-to-date Attention layer implemented using Keras backend operations. With the unveiling of TensorFlow 2.0 it is hard to ignore the conspicuous attention (no pun intended!) There was greater focus on advocating Keras for implementing deep networks. Keras in TensorFlow 2.0 will come with three powerful APIs for implementing deep networks. For more information, get first hand information from TensorFlow team. However remember that while choosing advance APIs give more "wiggle room" for implementing complex models, they also increase the chances of blunders and various rabbit holes.