TensorFlow 1.10 has just been released. Here’s what’s new.


Nordnet Baritof
Nordnet Baritof
  • Technical Writer
  • Entrepreneur
  • Founder and CEO
  • Developer
  • Blogger and IT Analyst
2018-08-14 09:33:36

| Share
| Share
| Share
TensorFlow 1.10 has just been released. Here’s what’s new.

Tensorflow, the popular Machine Learning framework, just released its version 1.10 on 09/08/2018. As any data scientist worthy of this name, ignoring the most recent patches is not an option: you want to use your libraries and frameworks to bring out their fullest potential so that your clients know they got their money’s worth through you! (Needless to say, but I am taking no chances here: version 1.10 is NOT the same as version 1.1. Remember that, it will save your reputation some day!)

And so, in an attempt to help my fellow data scientists and the data science community as a whole (After all, if you listened to the latest episode of the Superdatascience podcast, “We are a collaboration, not a competition!”), I will go through the three major features and improvements that version 1.10 has over its predecessor, version 1.9. Note that these are not the only changes that were made, but to explain the other improvements, I would probably need one article each because they are quite advanced. If you are still curious, feel free to have a look at this Github link.

  1. The tf.lite runtime now supports complex64

We all know how computationally intensive Machine Learning and Deep Learning algorithms can be. Now imagine deploying those on a mobile phone! It might be a good idea if you’re planning to heat up your lunch using your processor, but otherwise, RIP phone ☹

Luckily, Tensorflow Lite comes to the rescue! Tensorflow Lite is Tensorflow’s lightweight solution for mobile and embedded devices, and goes by tf.lite when used in code.

Alright, that’s cool, but what’s complex64? ‘complex64’ is a data type representing a complex number, with a float64 as real and a float64 as an imaginary component. Integrating this into tf.lite means the range of calculations you can perform has just been extended to cover operations involving complex numbers!

2. Initial Bigtable integration for tf.data

Click the next button 

Google following your every move here is how to limit it
Google following your every move here is how to limit it
.
An Interview Question on Spring
An Interview Question on Spring

Spring Singletons are not Java Singletons. Let's go over the important differences between them and how Spring singletons interact within containe


An Interview Question on Spring
TensorFlow 1.10 has just been released. Here’s what’s new.

Tensorflow, the popular Machine Learning framework, just released its version 1.10 on 09/08/2018. As any data scientist worthy of this name, ignoring


An Interview Question on Spring
7 best node js frameworks for developers

Node.JS is a platform built on V8, the Javascript engine which allows you to create fast and scalable web applications. Node.JS uses an event model an


An Interview Question on Spring
How to get from idea to prototype in 5 steps

The word 'prototype' has a long history. It derives ultimately from two ancient Greek words: photos (first) and typos (impression). It is impo


An Interview Question on Spring
6 differences between good designers and great designers

Great designers design in multiple mediums seamlessly They incorporate the whole user flow into the design - no matter where that takes them.


An Interview Question on Spring
8 tips for a happy development team

1. Start every meeting with good news No matter how good or bad your day, somebody somewhere is doing something great in your company. Take 30 seco



© 2013-2019 best of geeks. All rights reserved.