According to Francois Chollet, Keras was released two years ago, in March, 2015. It then proceeded to grow from one user to one hundred thousand. The following image, taken from the Keras blog, shows the growth of number of Keras users over time.
One important update with Keras 2.0 is that the API will now be a part of TensorFlow, starting with TensorFlow 1.2. Indeed, Keras is becoming more and more the lingua franca for deep learning, a spec used in an increasing number of deep learning contexts. For instance, Skymind is implementing Keras spec in Scala for ScalNet, and Keras.js is doing the same for JavaScript for running of deep learning directly in the browser. Efforts are also underway to provide a Keras API for MXNET and CNTK deep learning toolkits.
