Today (at the point of writing) TensorFlow 2.
0 Alpha preview package was officially released and the documentation was updated on the official website!I’m so pumped and excited about this and just can’t wait to share this with you!!To get to know some of the previous uses cases of TensorFlow and some of the changes in TensorFlow 2.
0, check out the short video below:What’s New in TensorFlow 2.
0 by Paige Bailey (Developer Advocate)Some New Features in TensorFlow 2.
0Even though the Tensorflow 2.
0 is still in the preview version, but we can start trying out some of the coolest features that have been long awaited after TensorFlow 1.
And trust me.
You will be blown away with the ease of use to learn and use TensorFlow 2.
0, especially for beginners.
0 focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs, and flexible model building on any platform.
There are multiple changes in TensorFlow 2.
0 to make TensorFlow users more productive.
In the section below, I’ll just give a brief overview of two of the major changes that make TensorFlow 2.
0 much more intuitive and productive to use.
To know what’s coming in TensorFlow 2.
0, you can check out the Medium article published by the TensorFlow team or the summary on the official TensorFlow website.
Alternatively, you can also watch this video (attached below) created by Aurélien Géron, the author of Hands-On Machine Learning with Scikit-Learn and TensorFlow.
What I like the most about the video is that he also compared the difference between Pytorch and TensorFlow 2.
0 besides mentioning some of the major changes in TensorFlow 2.
0 Changes by Aurélien Géron1.
Eager ExecutionWith eager execution enabled by default, TensorFlow operations are now immediately evaluated and return their values without building graphsSince there isn’t a computational graph to build and run later in a session, it’s easy to inspect results using print() or a debuggerEvaluating, printing, and checking tensor values does not break the flow for computing gradientsTensorFlow 2.
0 executes eagerly (like Python normally does) and in 2.
0, graphs and sessions should feel like implementation details.
Functions, not SessionsLet’s face it.
run() has always been our headache where we need to call the session before making any computations with our TensorFlow graphs.
And TensorFlow 2.
0 is here to solve this problem with that in mind.
Since a session.
run() call is almost like a function call: You specify the inputs and the function to be called, and you get back a set of outputs.
In TensorFlow 2.
0, you can use a decorator called tf.
function() so that you’re able to automatically define a TensorFlow function to run computation as a graph of TensorFlow operations, with named arguments and explicit return values.
In other words, you can write graph code using natural Python syntax, while being able to write Eager style code in a concise manner, and run it as a TensorFlow graph using tf.
Final ThoughtsWonderful Google office tour in SingaporeThank you for reading.
With so many exciting and user-friendly features, I really look forward to the final version of TensorFlow 2.
Meanwhile, if you’re interested in keeping up-to-date with the development of the of TensorFlow 2.
0, you can always subscribe to the mailing lists or join the communities here!As always, if you have any questions or comments feel free to leave your feedback below or you can always reach me on LinkedIn.
Till then, see you in the next post!.????About the AuthorAdmond Lee is a Big Data Engineer at work, Data Scientist in action.
He is known as one of the highly sought-after data scientists and consultants in helping start-up founders and various companies tackle their problems using data with deep data science and industry expertise.
You can connect with him on LinkedIn, Medium, Twitter, and Facebook.
Admond Lee Kin Lim – Big Data Engineer – Micron Technology | LinkedInView Admond Lee Kin Lim's profile on LinkedIn, the world's largest professional community.
Admond has 12 jobs listed on…www.
com.. More details