Why TensorFlow

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.

Easy model building

Build and train ML models easily using intuitive high-level APIs like Keras with eager execution, which makes for immediate model iteration and easy debugging.

Robust ML production anywhere

Easily train and deploy models in the cloud, on-prem, in the browser, or on-device no matter what language you use.

Powerful experimentation for research

A simple and flexible architecture to take new ideas from concept to code, to state-of-the-art models, and to publication faster.

Solutions to common ML problems

Simple step-by-step walkthroughs to solve common ML problems with TensorFlow.

For beginners
Your first neural network

Train a neural network to classify images of clothing, like sneakers and shirts, in this fast-paced overview of a complete TensorFlow program.

For experts
Generative adversarial networks

Train a generative adversarial network to generate images of handwritten digits, using the Keras Subclassing API.

For experts
Neural machine translation with attention

Train a sequence-to-sequence model for Spanish to English translation using the Keras Subclassing API.

News & announcements
A recap of the 2019 TensorFlow Dev Summit
June 24, 2019
Registration for TensorFlow World is now open

TensorFlow World is the first event of its kind—gathering the TensorFlow team and machine learning developers to share best practices, use cases, and a firsthand look at the latest TensorFlow product developments.

June 21, 2019
TensorFlow in Practice

Announcing the deeplearning.ai TensorFlow Specialization, which teaches you best practices for using TensorFlow's high-level APIs to build neural networks for computer vision, natural language processing, and time series forecasting.

Mar 6, 2018
Intro to TensorFlow for Deep Learning

This course was developed by Google and Udacity as a practical approach to deep learning for software developers. Learn how to build deep learning applications with TensorFlow.

Resources and community support

We are committed to fostering an open and welcoming ML community. Join the TensorFlow community and help grow the ecosystem.

Connect with participants and explore the winning projects from our #PoweredByTF DevPost Challenge.

2.0 feature tracker 

See details of in-progress, planned, and completed development activities for TensorFlow 2.0.

TensorFlow Blog 

We post regularly to the TensorFlow Blog, with content from the TensorFlow team and the best articles from the community.

YouTube 

Our YouTube Channel focuses on machine learning and AI with TensorFlow. Explore a number of new shows, including TensorFlow Meets, Ask TensorFlow, and Coding TensorFlow.

For up-to-date news and updates from the community and the TensorFlow team, follow @tensorflow on Twitter.

TensorFlow announcements 

Join the TensorFlow announcement mailing list to learn about the latest release updates, security advisories, and other important information from the TensorFlow team.