VisionAir: Using Federated Learning to estimate Air Quality using the Tensorflow API for Java
Developer Stories
VisionAir: Using Federated Learning to estimate Air Quality using the Tensorflow API for Java

A guest article by Harshita Diddee, Divyanshu Sharma, Shivani Jindal and Shivam Grover

Matrix Compression Operator
Developer Stories
Matrix Compression Operator

Posted by Rina Panigrahy

Speeding up neural networks using TensorNetwork in Keras
Developer Stories
Speeding up neural networks using TensorNetwork in Keras

Posted by Marina Munkhoeva, PhD student at Skolkovo Institute of Science and Technology and AI Resident at Alphabet's X, Chase Roberts, Research Engineer at Alphabet's X, and Stefan Leichenauer, Research Scientist at Alphabet's X

 TensorFlow Lattice: Flexible, controlled and interpretable ML
TensorFlow Core
TensorFlow Lattice: Flexible, controlled and interpretable ML

Posted by Mahdi Milani Fard, Software Engineer, Google Research

Most ML practitioners have encountered the typical scenario where the training data looks very different from the run-time queries on which the model is evaluated. As a result, flexible ML solutions such as DNNs or forests that rely solely on the training dataset often act unexpectedly and even wildly in parts of the input space not …

Request for Proposals: Faculty Awards to Support Machine Learning Courses, Diversity, and Inclusion
Developer Stories
Request for Proposals: Faculty Awards to Support Machine Learning Courses, Diversity, and Inclusion

Posted by Josh Gordon for the TensorFlow team

TensorFlow.js for React Native is here!
TensorFlow.js
TensorFlow.js for React Native is here!

Posted by Yannick Assogba, Software Engineer, Google Research, Brain team

We are pleased to announce that TensorFlow.js for React Native is now available for general use. We would like to thank everyone who gave us feedback, bug reports, and contributions during the alpha release and invite the broader community of React Native developers to try it out!

Introducing TensorFlow Videos for a Global Audience: Korean
Korean
Introducing TensorFlow Videos for a Global Audience: Korean

When the TensorFlow YouTube channel launched in 2018, we had a vision to inform and inspire developers around the world about what was possible with Machine Learning. With series like Coding TensorFlow showing how you can use it, and Made with TensorFlow showing inspirational stories about what people have done with TensorFlow and much more, the channel has grown greatly. But we learned an import…

PhotoBooth Lite on Raspberry Pi with TensorFlow Lite
TensorFlow Lite
PhotoBooth Lite on Raspberry Pi with TensorFlow Lite

Posted by Lucia Li, TensorFlow Lite Intern

Hyperparameter tuning with Keras Tuner
Keras · TensorFlow Core
Hyperparameter tuning with Keras Tuner

Posted by Tom O’Malley

The success of a machine learning project is often crucially dependent on the choice of good hyperparameters. As machine learning continues to mature as a field, relying on trial and error to find good values for these parameters (also known as “grad student descent”) simply doesn’t scale. In fact, many of today’s state-of-the-art results, such as EfficientNet, were discove…

 Introducing TensorFlow Videos for a Global Audience: Chinese
Chinese
Introducing TensorFlow Videos for a Global Audience: Chinese

Posted by the TensorFlow team

Creating a Custom TFX Component
TFX
Creating a Custom TFX Component

Posted by Ruoyu Liu and Robert Crowe on behalf of the TFX team

TensorFlow Extended (TFX) is a platform for creating production-ready machine learning (ML) pipelines. TFX was created by Google and provides the backbone of Google’s ML services and applications, and now Google has open sourced TFX for anyone who wants to create production ML pipelines.

Building An AI-Empowered Music Library with TensorFlow
Developer Stories
Building An AI-Empowered Music Library with TensorFlow

A guest post by Tencent QQ Music Audio Engineering Team

Autonomous Dog Training with Companion
Developer Stories
Autonomous Dog Training with Companion

A guest post by Michael Wang and Noemie Guerin from Companion

Run a TensorFlow SavedModel in Node.js directly without conversion
TensorFlow.js
Run a TensorFlow SavedModel in Node.js directly without conversion

Posted by Kangyi Zhang, Sandeep Gupta, and Brijesh Krishnaswami

Ecovacs Robotics: the AI robotic vacuum cleaner powered by TensorFlow
Developer Stories · TensorFlow Lite
Ecovacs Robotics: the AI robotic vacuum cleaner powered by TensorFlow

A guest post by Liang Bao, Chengqi Lv, from Ecovacs Robotics AI Department.
Translated by Ziqian Xu, from Ecovacs Robotics Technology Development Department.

Looking Back at 2019
TensorFlow Core
Looking Back at 2019

Posted by the TensorFlow Team

2019 was an exciting year for TensorFlow. From releasing TensorFlow 2.0 and several product updates to hosting a global roadshow in 11 different countries and the first ever TensorFlow World, this year highlighted how TensorFlow is helping to empower developers, researchers, and enterprises around the world to solve challenging, real-world problems with ML. With Tens…

An Introduction to the New and Improved TensorFlow Hub
TensorFlow Core
An Introduction to the New and Improved TensorFlow Hub

By Jordan Grimstad
It’s been a year and a half since we introduced TensorFlow Hub, an open-source repository of ready to use pre-trained models published by Google and DeepMind. Since then, we’ve published hundreds of models -- some that are general-purpose and fine-tunable to specific tasks, others which are more specialized -- to help you get faster, smarter ML applications even with little dat…

Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs
TensorFlow Lite
Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs

Posted by Karim Nosseir and Sachin Joglekar, Software Engineers

Digital Signal Processors (DSPs), such as Hexagon DSPs, are microprocessors present on most modern phones alongside other compute units such as the CPU and GPU. Developed with the primary goal of improving communication and multimedia processing, these chips can dramatically speed up model inference on mobile / edge devices. DSPs are …

Example on-device model personalization with TensorFlow Lite
TensorFlow Lite
Example on-device model personalization with TensorFlow Lite

Posted by Pavel Senchanka, Software Engineering Intern at Google

TensorFlow Lite is an industry-leading solution for on-device inference with machine learning models. While a complete training solution for TensorFlow Lite is still in progress, we're delighted to share with you a new on-device transfer learning example. This illustrates a way of personalizing your machine learning models on-d…

Fairness Indicators: Scalable Infrastructure for Fair ML Systems
TFX
Fairness Indicators: Scalable Infrastructure for Fair ML Systems

Posted by Catherina Xu and Tulsee Doshi, Product Managers, Google Research

While industry and academia continue to explore the benefits of using machine learning (ML) to make better products and tackle important problems, algorithms and the datasets on which they are trained also have the ability to reflect or reinforce unfair biases. For example, consistently flagging non-toxic text comments fro…