Creator of Keras confirmed that the new version comes out in a few days. Keras becomes multi-backend again with support for PyTorch, TensorFlow and JAX. Personally, I’m excited to be able to try JAX without having to deep dive into documentation and entire ecosystem. What about you?
Will it be backward compatible with keras 2.0 largely?
Yes, completely. In fact, tf.keras will just be changed internally (as in source code) as keras_core, but you won’t notice any difference in tf.keras (except for some removal of currently depracated legacy code and a visual update in .fit()).