Talk given at ODSC East, Boston, May 1, 2019.
Tensorflow 2.0 makes Keras the default API for model definition. This is a big change. It makes Tensorflow more accessible to beginners and newcomers and it also disrupts consolidated patterns and habits for experienced Tensorflow programmers. This workshop is aimed to both audiences and it covers how to define models in Tensorflow 2.0 using the tf.keras API. It also covers the commonalities and differences between the open source Keras package and tf.keras, explaining pros and cons of each of the two. If you are getting started with Tensorflow or you're puzzled by the changes in Tensorflow 2.0, come and learn how easy it is to design models using Keras.
20. Catalit LLC
LEGACY REASONSTO USE KERAS
• 2 reasons to use Keras until now:
• Simple API ==> Adopted byTF 2.0
• Multiple backends ==> No more true/relevant
29. Catalit LLC
PUBLIC 2.0 DESIGN PROCESS
https://groups.google.com/a/tensorflow.org/forum/#!forum/discuss
https://github.com/tensorflow/community/blob/master/governance/TF-RFCs.md
https://github.com/tensorflow/community/tree/master/rfcs
30. Catalit LLC
SOME ACCEPTED RFC
• TensorForest Estimator
• Attention for Dense networks on Keras
• TensorFlow 2.0: Optimizer unification
• Unify RNN Inteface
• Check https://github.com/tensorflow/community/tree/master/rfcs
54. Catalit LLC
IMPROVED DOC
• Historically:
• Keras Documentation => Awesome
• Tensorflow Documentation => Pretty bad
55. Catalit LLC
IMPROVED DOC
• As of May 2019
• Keras Documentation => Stale, no new releases
since October 2018
• Tensorflow 2.0 Alpha Documentation => Pretty
good, full of examples and tutorials
89. Catalit LLC
CONCLUSIONS
• Tensorflow 2.0 is coming
• It will replace Keras sooner thanTensorflow 1.x
• Migration from Keras andTensorflow 1.x quite easy
• New opportunities
• Vendor lock-in