TensorFlow Furthers the Development of Machine Learning

Table Of Contents

In preparation for his talk at the upcoming Codemotion Deep Learning virtual conference next week, I spoke to Luiz Gustavo Martins, TensorFlow Developer Advocate, at Google.

He explained that his main role is to help developers use tensor flow the best way possible. “I also help them achieve their goals and bring feedback to the team to TensorFlow team to keep improving the product in keeping addressing developer needs. As I’m also a developer advocate, I end up being a TensorFlow developer myself because I have to understand the developer’s needs. I have to try to understand why there’s a problem. I have to understand how and what they’re trying to do. This is very cool because I have the opportunity to learn a lot of new things. Sometimes it’ll be too hard for me, but you just keep studying. And you’ll get there.”

TensorFlow is an end-to-end open-source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, and community resources that lets researchers push the state-of-the-art in ML, and developers easily build and deploy ML-powered applications.

The Genesis of Tensor Flow

Google, as a company, is forever focused on product improvement. They started using machine learning internally, and as Luiz explained that “the Google Brain team started writing frameworks to help us with our own problems. We developed multiple solutions, and TensorFlow developed in 2015 was the best of these. We open-sourced it, of course, to help the community and to help improve because, of course, Google cannot do everything in machine learning, there’s a lot of people in the world that can help. — That’s why we open source, so we get more people contributing to the technology or people contributing to the field.”

Last week TensorFlow surpassed 100 million installs — remarkable for a product that’s only existed for five years! Especially as Luiz notes that the product is fairly niche, and designed originally for those specifically working in machine learning, not generalist devs.

Luiz notes that “As people start to find out more about machine learning, they start to think, ‘oh, maybe I should use this on my field, maybe it can solve my problems.’ “ This one of the developments due to interest was the evolution of frameworks for mobile phone deployment. “That’s something that people hadn’t even thought about, machine learning on the phone because of all the hardware restrictions, right? Then we thought, maybe we can deploy this on an Android app. And that’s when that’s where TensorLight came to life. Because we needed a better version of TensorFlow that would run given all the memory and hardware restrictions of Android.”

Codemotion Online Tech Conference
Shaping the Future with Deep Learning

The impact of AI on our lives is already tangible and it is destined to grow exponentially. From Healthcare to Finance, from Marketing to Manufacturing, and many more fields are going through a fast-paced revolution.

On May 27, join our free online event to learn how you too can be a part of it from some of the most prominent DL experts in the world.


Always Evolving

Since then, TensorFlow is always evolving. Luiz details: “We developed TensorFlow Lite to work with microcontrollers and all kinds of embedded devices. TensorFlow.js. was introduced to give JavaScript developers better tools to use TensorFlow.”

Google also created TensorFlow Extended (TFX), an end-to-end platform for deploying production ML pipelines in response to the particular needs of enterprise:

“There are different challenges that you have to address compared to if you’re just playing during the weekend. TFX was also able to meet some of the needs that we had internally.”

A healthy mix of TensorFlow users

TensorFlow users are a healthy mix of academics, researchers, enterprises, startups, and hobbyists. As Luiz notes, “We have users doing all kinds of things. So we talk to universities, as well as people just starting to learn machine learning. You start to talk to people that were like, I myself. I was an Android developer for some years. And so I start using machine learning on Android. And then I really liked it. And of course, we have researchers who need TensorFlow to write their papers. So we have tools for them specifically, to help them share their results, their training, and data. We also have, of course, big enterprises in all kinds of sectors using TensorFlow. And then there’s hobbyists who we love because they always come up with great ideas, and they build things super fast.” Luiz gave the example of a self-driving car using Python.

How can a newbie get started?

I was interested to know about the ease of entry for people new to Machine Learning. Luiz explained, “We are making our tools easier and easier to use. There’s this teachable machine where you can just go to a web page and train a model. It’s super easy, you don’t need to know anything about machine learning. You get your module and you can play around with it. Really, there’s all these cool things and demos that you can see that look like magic, sometimes just, it’s unbelievable. And that’s great. I like to work with these people to help them and to also learn from them.”

The benefits of Colab

Luiz notes that while we’re all spending our tie at home, it’s an opportunity to start learning something new. “There’s a lot of resources available in TensorFlow to make your life way easier to learn, and to try out things.

One great resource is Colaboratory, or “Colab” for short, which allows you to write and execute Python in your browser, with zero configuration required, free access to GPUs, and easy sharing. With Colab you can import an image dataset, train an image classifier on it, and evaluate the model, all in just a few lines of code. Colab notebooks execute code on Google’s cloud servers, meaning you can leverage the power of Google hardware, including GPUs and TPUs, regardless of the power of your machine. All you need is a browser.

Luiz shared: “I was talking to someone this week in a region where the internet is not great. However, machine learning requires a lot of data, a lot of downloads. So I was talking to them, and they were happy that we have Colab. Because they can use all their resources on the browser. They didn’t download to their machines, and they could keep trying in learning new things. So this is something that was great. And yeah, so I guess it’s a good time to learn new things.”

If you’d like to learn more about Machine Learning and TensorFlow, join us next week on May 27th for our virtual Deep Learning Conference where a fantastic cohort of speakers including Luiz will be speaking about advances in technological research and real-world applications.

You can read the orginal version of this article at Codemotion.com, where you will find more related contents. https://www.codemotion.com/magazine/dev-hub/machine-learning-dev/tensorflow-furthers-the-development-of-machine-learning/




We help tech communities to grow worldwide, providing top-notch tools and unparalleled networking opportunities.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

CNN Architectures, a Deep-dive

The Video Search Engine — My Journey Into Computer Vision

Artificialis Machine Learning Contest

Tokenization Techniques in Natural Language Processing in Python

Day 3 — K-Nearest Neighbors and Bias–Variance Tradeoff

Hello, new neighbors :-)

Different types of Machine learning and their types.

Logistic Regression from Scratch: Multi classification with OneVsAll

Train a Face-Mask Detection Model in Under 5 Minutes using Lobe.ai

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store


We help tech communities to grow worldwide, providing top-notch tools and unparalleled networking opportunities.

More from Medium

The Middle East conflict is a perpetual site of violence, political conflict and despair Gustavo de…


Goodbye SW150

University Is Not The Only Career Path

Two roads and a lot of yellow trees.