Keras
What's new in TensorFlow 2.16
Google Article
Announcement · Estimator
What's new in TensorFlow 2.16

Posted by the TensorFlow team

TensorFlow 2.15 update: hot-fix for Linux installation issue
Google Article
Announcement · Explore
TensorFlow 2.15 update: hot-fix for Linux installation issue

Posted by the TensorFlow team

What's new in TensorFlow 2.15
Google Article
Announcement · Explore
What's new in TensorFlow 2.15

Posted by the TensorFlow team

Simulated Spotify Listening Experiences for Reinforcement Learning with TensorFlow and TF-Agents
Google Article
AI · Documentation
Simulated Spotify Listening Experiences for Reinforcement Learning with TensorFlow and TF-Agents

Posted by Surya Kanoria, Joseph Cauteruccio, Federico Tomasi, Kamil Ciosek, Matteo Rinaldi, and Zhenwen Dai – Spotify

What's new in TensorFlow 2.13 and Keras 2.13?
Google Article
Keras · TensorFlow Core
What's new in TensorFlow 2.13 and Keras 2.13?

Posted by the TensorFlow and Keras Teams

Google I/O 2023: What’s new in TensorFlow and Keras?
Google Article
Keras · Tensorflow
Google I/O 2023: What’s new in TensorFlow and Keras?

Posted by Ayush Jain, Carlos Araya, and Mani Varadarajan for the TensorFlow team

AI and Machine Learning @ I/O Recap
Google Article
Generative AI · Google AI
AI and Machine Learning @ I/O Recap

Posted by Lauren Usui and Joe Fernandez

An Introduction to Keras Preprocessing Layers
Google Article
Keras · TensorFlow Core
An Introduction to Keras Preprocessing Layers

Posted by Matthew Watson, Keras Developer

Hyperparameter tuning with Keras Tuner
Google Article
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…

Combining multiple TensorFlow Hub modules into one ensemble network with AdaNet
Google Article
Keras · TensorFlow Hub
Combining multiple TensorFlow Hub modules into one ensemble network with AdaNet

Posted by Sara Robinson

Have you ever started building an ML model, only to realize you’re not sure which model architecture will yield the best results? Enter the TensorFlow-based AdaNet framework. With AdaNet, you can feed multiple models into AdaNet’s algorithm and it’ll find the optimal combination of all of them as part of the training process. I’ve been playing with it recently and have bee…

What’s coming in TensorFlow 2.0
Google Article
Keras
What’s coming in TensorFlow 2.0

Posted by the TensorFlow Team

Thanks to an incredible and diverse community, TensorFlow has grown to become one of the most loved and widely adopted ML platforms in the world. This community includes:
Researchers (e.g., to forecast earthquake aftershocks and detect breast cancer).
Developers (e.g., to build apps to identify diseased plants and to help people lose weight).
Companies (e.g., by eBay, D…

Standardizing on Keras: Guidance on High-level APIs in TensorFlow 2.0
Google Article
Keras · TensorFlow Core
Standardizing on Keras: Guidance on High-level APIs in TensorFlow 2.0

Posted by Sandeep Gupta, Josh Gordon, and Karmel Allison on behalf of the TensorFlow team

TensorFlow is preparing for the release of version 2.0. In this article, we want to preview the direction TensorFlow’s high-level APIs are heading, and answer some frequently asked questions.

Training and Serving ML models with tf.keras
Google Article
Community · Keras
Training and Serving ML models with tf.keras

Posted by Stijn Decubber, machine learning engineer at ML6.

Neural Style Transfer: Creating Art with Deep Learning using tf.keras and eager execution
Google Article
Community · Keras
Neural Style Transfer: Creating Art with Deep Learning using tf.keras and eager execution

Posted by Raymond Yuan, Software Engineering Intern

In this tutorial, we will learn how to use deep learning to compose images in the style of another image (ever wish you could paint like Picasso or Van Gogh?). This is known as neural style transfer! This is a technique outlined in Leon A. Gatys’ paper, A Neural Algorithm of Artistic Style, which is a great read, and you should definitely check …

Deep Reinforcement Learning: Playing CartPole through Asynchronous Advantage Actor Critic (A3C) with tf.keras and eager execution
Google Article
Keras
Deep Reinforcement Learning: Playing CartPole through Asynchronous Advantage Actor Critic (A3C) with tf.keras and eager execution

By Raymond Yuan, Software Engineering Intern

In this tutorial we will learn how to train a model that is able to win at the simple game CartPole using deep reinforcement learning. We’ll use tf.keras and OpenAI’s gym to train an agent using a technique known as Asynchronous Advantage Actor Critic (A3C). Reinforcement learning has been receiving an enormous amount of attention, but what is it exact…

Train a model in tf.keras with Colab, and run it in the browser with TensorFlow.js
Google Article
Keras · TensorFlow.js
Train a model in tf.keras with Colab, and run it in the browser with TensorFlow.js

Posted by Zaid Alyafeai

Fashion-MNIST with tf.Keras
Google Article
Community · Keras
Fashion-MNIST with tf.Keras

Posted by Margaret Maynard-Reid

This is a tutorial of how to classify the Fashion-MNIST dataset with tf.keras, using a Convolutional Neural Network (CNN) architecture. In just a few lines of code, you can define and train a model that is able to classify the images with over 90% accuracy, even without much optimization.