Keras proper, a high-level front end for building neural network models, ships with support for three back-end deep learning frameworks: TensorFlow, CNTK, and Theano. Amazon is currently working ...

Scikit-learn, PyTorch, and TensorFlow remain core tools for structured data and deep learning tasks.New libraries like JAX, ...

Keras ships with support for three back-end deep learning frameworks: TensorFlow, CNTK, and Theano. Amazon is currently working on developing a MXNet back-end for Keras.

Google announced TensorFlow 2.0 is now available for public use. ... Initial integration with the Keras deep learning library began with the release of TensorFlow 1.0 in February 2017.

Currently, Keras is a separate package that's easy to install using pip or your favorite package manager, but Google plans to have it built-in to the 1.2 release of TensorFlow.