Hacker News Reader

Keras still has CNTK and Theano backends in addition to Tensorflow. Given that both frameworks are not being developed anymore, is there any point in maintaining those backends in the future?

View on HN

From the release announcement:

> Development will focus on tf.keras going forward. We will keep maintaining multi-backend Keras over the next 6 months, but we will only be merging bug fixes.

So it's the end of Keras

and I thought there was discussion about including mx.net. Looks like if you want to build, train and reuse NNs (in an established framework) you finally have to choose between Google, Facebook or Amazon/Microsoft in every case.

There is support for Keras with MXNet[1], however you need to install a forked version of keras, `pip install keras-mxnet`.

[1] https://github.com/awslabs/keras-apache-mxnet

I guess it's going to be just TensorFlow in the near future. From the release notes:

> This is also the last major release of multi-backend Keras. Going forward, we recommend that users consider switching their Keras code to tf.keras in TensorFlow 2.0.

Reply on news.ycombinator.com