TensorFlow Model Optimization Toolkit — Weight Clustering API
Community · TensorFlow Core
TensorFlow Model Optimization Toolkit — Weight Clustering API

A guest post by Mohamed Nour Abouelseoud, and Anton Kachatkou at Arm

We are excited to introduce a weight clustering API, proposed and contributed by Arm, to the TensorFlow Model Optimization Toolkit.

Layerwise learning for Quantum Neural Networks
Community · TF Quantum
Layerwise learning for Quantum Neural Networks

Posted by Andrea Skolik, Volkswagen AG and Leiden University

In early March, Google released TensorFlow Quantum (TFQ) together with the University of Waterloo and Volkswagen AG. TensorFlow Quantum is a software framework for quantum machine learning (QML) which allows researchers to jointly use functionality from Cirq and TensorFlow. Both Cirq and TFQ are aimed at simulating noisy intermediate-sc…

 The Future of Machine Learning is Tiny and Bright
Community · TensorFlow Lite
The Future of Machine Learning is Tiny and Bright

Posted by Josh Gordon, Developer Advocate
A new HarvardX TinyML course on edX.orgProf. Vijay Janapa Reddi of Harvard, the TensorFlow Lite Micro team, and the edX online learning platform are sharing a series of short TinyML courses this fall that you can observe for free, or sign up to take and receive a certificate. In this article, I’ll share a bit about TinyML, what you can do with it, and the …

Train your TensorFlow model on Google Cloud using TensorFlow Cloud
TensorFlow Core
Train your TensorFlow model on Google Cloud using TensorFlow Cloud

Posted by Jonah Kohn and Pavithra Vijay, Software Engineers at Google

TensorFlow Cloud is a python package that provides APIs for a seamless transition from debugging and training your TensorFlow code in a local environment to distributed training in Google Cloud. It simplifies the process of training models on the cloud into a single, simple function call, requiring minimal setup and almost zero …

TensorFlow 2 MLPerf submissions demonstrate best-in-class performance on Google Cloud
TensorFlow Core
TensorFlow 2 MLPerf submissions demonstrate best-in-class performance on Google Cloud

Posted by Pankaj Kanwar, Peter Brandt, and Zongwei Zhou from the TensorFlow Team

MLPerf, the industry standard for measuring machine learning performance, has released the latest benchmark results from the MLPerf Training v0.7 round. We’re happy to share that Google’s submissions demonstrate leading top-line performance (fastest time to reach target quality), with the ability to scale up to 4,000+…

What's new in TensorFlow 2.3?
TensorFlow Core
What's new in TensorFlow 2.3?

Posted by Josh Gordon for the TensorFlow team

TensorFlow 2.3 has been released! The focus of this release is on new tools to make it easier for you to load and preprocess data, and to solve input-pipeline bottlenecks, whether you’re working on one machine, or many.

Accelerating TensorFlow Lite with XNNPACK Integration
TensorFlow Lite
Accelerating TensorFlow Lite with XNNPACK Integration

Posted by Marat Dukhan, Google Research

Leveraging the CPU for ML inference yields the widest reach across the space of edge devices. Consequently, improving neural network inference performance on CPUs has been among the top requests to the TensorFlow Lite team. We listened and are excited to bring you, on average, 2.3X faster floating-point inference through the integration of the XNNPACK libra…

500 developers spanning 53 countries have passed the TensorFlow Certificate Exam!
500 developers spanning 53 countries have passed the TensorFlow Certificate Exam!

Posted by Jocelyn Becker, Program Manager, TensorFlow Certificate

Using machine learning in the browser to lip sync to your favorite songs
TensorFlow.js
Using machine learning in the browser to lip sync to your favorite songs

Posted by Pohung Chen, Creative Technologist, Google Partner Innovation

Sharing Pixelopolis, a self-driving car demo from Google I/O built with TF-Lite
TensorFlow Lite
Sharing Pixelopolis, a self-driving car demo from Google I/O built with TF-Lite

Posted by Miguel de Andrés-Clavera, Product Manager, Google PI

In this post, I’d like to share with you a demo we built for (and had planned to show at) Google I/O this year with TensorFlow Lite. I wish we had the opportunity to meet in person, but I hope you find this article interesting nonetheless!
PixelopolisPixelopolis is an interactive installation that showcases self-driving miniature cars…

TensorFlow 2 meets the Object Detection API
TensorFlow Core
TensorFlow 2 meets the Object Detection API

Posted by Vivek Rathod and Jonathan Huang, Google Research

TensorFlow operation fusion in the TensorFlow Lite converter
TensorFlow Core · TensorFlow Lite
TensorFlow operation fusion in the TensorFlow Lite converter

Posted by Ashwin Murthy, Software Engineer, TensorFlow team @ Google
OverviewEfficiency and performance are critical for edge deployments. TensorFlow Lite achieves this by means of fusing and optimizing a series of more granular TensorFlow operations (which themselves are composed of composite operations, like LSTM) into a single executable TensorFlow Lite unit.

Many users have asked us for more g…

Responsible AI with TensorFlow
Responsible AI · TensorFlow Core
Responsible AI with TensorFlow

Posted byTulsee Doshi, Andrew Zaldivar

As billions of people around the world continue to use products or services with AI at their core, it becomes more important than ever that AI is deployed responsibly: preserving trust and putting each individual user’s well-being first. It has always been our highest priority to build products that are inclusive, ethical, and accountable to our communities,…

 Enhance your TensorFlow Lite deployment with Firebase
TensorFlow Lite
Enhance your TensorFlow Lite deployment with Firebase

Posted by Khanh LeViet, TensorFlow Developer Advocate

Introducing a New Privacy Testing Library in TensorFlow
TensorFlow Core
Introducing a New Privacy Testing Library in TensorFlow

Posted by Shuang Song and David Marn

Accelerating AI performance on 3rd Gen Intel® Xeon® Scalable processors with TensorFlow and Bfloat16
Community
Accelerating AI performance on 3rd Gen Intel® Xeon® Scalable processors with TensorFlow and Bfloat16

A guest post by Niranjan Hasabnis, Mohammad Ashraf Bhuiyan, Wei Wang, AG Ramesh at Intel

From singing to musical scores: Estimating pitch with SPICE and Tensorflow Hub
TensorFlow Core · TensorFlow Hub
From singing to musical scores: Estimating pitch with SPICE and Tensorflow Hub

Posted by Luiz Gustavo Martins, Beat Gfeller and Christian Frank

Pitch is an attribute of musical tones (along with duration, intensity and timbre) that allows you to describe a note as “high” or “low”. Pitch is quantified by frequency, measured in Hertz (Hz), where one Hz corresponds to one cycle per second. The higher the frequency, the higher the note.

Running and Testing TF Lite on Microcontrollers without hardware in Renode
Community · TensorFlow Lite
Running and Testing TF Lite on Microcontrollers without hardware in Renode

A guest post by Michael Gielda of Antmicro

Every day more and more software developers are exploring the worlds of machine learning, embedded systems, and the Internet of Things. Perhaps one of the most exciting advances to come out of the most recent innovations in these fields is the incorporation of ML at the edge and into smaller and smaller devices - often referred to as TinyML.

Part 2: Fast, scalable and accurate NLP: Why TFX is a perfect match for deploying BERT
Community · TFX
Part 2: Fast, scalable and accurate NLP: Why TFX is a perfect match for deploying BERT

Guest author Hannes Hapke, Senior Data Scientist, SAP Concur Labs. Edited by Robert Crowe on behalf of the TFX team

Transformer models and the concepts of transfer learning in Natural Language Processing have opened up new opportunities around tasks like sentiment analysis, entity extractions, and question-answer problems.

BERT models allow data scientists to stand on the shoulders of giants. Pr…

TensorFlow User Groups: Updates from Around the World
Community
TensorFlow User Groups: Updates from Around the World

Posted by Soonson Kwon, Biswajeet Mallik, and Siddhant Agarwal, Program Managers

TensorFlow User Groups (or TFUGs, for short) are a community of curious, passionate machine learning developers and researchers around the world. TFUGs play an important role in helping developers share their knowledge and experience in machine learning, and the latest TensorFlow updates. Google and the TensorFlow tea…