Thursday, February 16, 2017

TensorFlow 1.0 Released!

TensorFlow 1.0 has been released!

Just a week back I posted about the announcement of TensorFlow 1.0 and the new features coming. Now, it's finally here. It was released at the first TensorFlow Dev Summit held yesterday (15th Feb) at Mountain View, California.


The official TensorFlow website is now updated for the 1.0 release, which also now has a section for TensorFlow Fold which allows to work with input data of different shapes and sizes, and which has now been made open-source. The installation instructions have also been updated for the latest version, and they have added a guide on how to upgrade your application to TensorFlow 1.0.

The release notes for 1.0 suggests that all the anticipated features are here: The XLA compiler, Debugger, The Java API, Mobile support improvements, and much more. There's also news reports coming in which states that more machine learning models, such as SVMs, will come to TensorFlow. Better support for Keras is also hinted. I'm eagerly waiting for Keras to upgrade to support new features in TensorFlow 1.0.

Related posts:

Related links:

No comments:

Post a Comment