Oswald Campesato, "An introduction to TensorFlow 2"

A fast-paced introduction to TensorFlow 2 about some important new features (such as generators and the @tf.function decorator) and TF 1.x functionality that's been removed from TF 2 (yes, tf.Session() has retired).
Some concise code samples are presented to illustrate how to use new features of TensorFlow 2.

You'll also get a quick introduction to lazy operators (if you know FRP this will be super easy), along with a code comparison between TF 1.x/iterators with tf.data.Dataset and TF 2/generators with tf.data.Dataset.

Finally, we'll see how to define tf.keras models in TF 2 for CNNs and LSTMs, and briefly discuss BiDirectional LSTMs and VAEs.

Although familiarity with TF 1.x is helpful, newcomers with an avid interest in learning about TensorFlow 2 can benefit from this session.

Please note that TF 2 is currently in early release, and that this presentation does not contain Scala-related code samples.

Schedule

• 6:30-7:00 - networking (pizza, soft drinks)
• 7:00-7:10 - announcements etc.
• 7:10-8:00 - talk
• 8:00-8:30 - more networking