👀 Looking for a community of devs?
💡 Share your projects, ask questions, and connect with fellow developers on the TensorFlow Forum!
Join this thriving community for discussions, support, and collaboration ➡️ goo.gle/2TJHykJ
Pinned
Follow
TensorFlow
@TensorFlow
TensorFlow is a fast, flexible, and scalable open-source machine learning library for research and production.
TensorFlow’s posts
🎉 The wait is over! TensorFlow 2.0 is finally here.
Driven by community feedback, this release provides a complete set of tools for developers, enterprises, and researchers to easily build ML applications.
Read the blog ↓
Learn Machine Learning concepts by taking the same course that over 10,000 Google engineers have completed (available in English, Spanish, French, Korean, and Mandarin)
Start the crash course here → goo.gl/kIEHFH
⚡️ Accelerating TensorFlow 2 performance on Mac
’s new Mac-optimized TensorFlow 2.4 fork lets you speed up training on Macs, resulting in up to 7x faster performance on platforms with the new M1 chip!
Learn how ↓
Today we’re launching Seedbank, a place to discover interactive ML examples which you can run from your browser, no set-up required. Each example can be edited, extended, and adapted into your own project.
Read 's post for more info ↓ bit.ly/2JhRG9E
Real time face + hand tracking in the browser with MediaPipe + TensorFlow.js
What will you create using these new models? #MadeWithTFJS
Read more → goo.gle/3cN1qZ8
GIF
Happy 3rd birthday TensorFlow! We've come a long way since the first release in 2015 & TensorFlow wouldn't be the framework it is today without you. As we work on #TensorFlow20, look at all the features we've added over the years to make TensorFlow easier to use. #HappyBirthdayTF
Using and , taught an AI to perform a simple in-game task: shoot balls into a hoop.
See how he did it on the post → bit.ly/2NAhG2m
GIF
BodyPix 2.0 has been released, including multi-person segmentation support and a new live demo!
To learn more, read the post by , , , , , , .
Details here → goo.gle/bodypix2
GIF
🌲 Introducing TensorFlow Decision Forests, a new library you can use to train popular models like Random Forests and Gradient Boosted Trees easily with Keras.
Learn more → goo.gle/3hZtZI2
GIF
read image description
ALT
☝ We have a recommendation for that
Introducing TensorFlow Recommenders, an open-source package that makes building, evaluating, and serving recommender models easy. Find recommendations for movies, restaurants, and much more!
Get started → goo.gle/2HrCwDq
GIF
Slide to the left, slide to the right 🕺
Announcing Pose Animator - an open source tool that brings SVG characters to life via motion capture in the browser with TensorFlow.js.
Read the blog → goo.gle/2ZOJWYi
#MadeWithTFJS
GIF
read image description
ALT
💃 Try our new model that enables 3D Pose Detection live in your web browser with MediaPipe BlazePose GHUM + TensorFlow.js.
Share your creations with #MadeWithTFJS.
Get started → goo.gle/3gKAYmy
Read the blog → goo.gle/2WCS3bb
GIF
read image description
ALT
TensorFlow 2 🤝 Object Detection API
Today we’re happy to announce that the TF Object Detection API officially supports TensorFlow 2! Learn more about the release and all its new features in the post.
Read the blog ↓
🖼️ With KerasCV, anyone can use the highest-throughput StableDiffusion pipeline to generate images!
Get started in under a minute: goo.gle/3CfEj8x
read image description
ALT
💃 Dance, jump, and twirl! 🤸
We just released MoveNet, a new lightning-fast pose model in browser that's #MadeWithTFJS and designed to track fast motions and tough poses.
Learn more at #GoogleIO and try it yourself → goo.gle/3uWeVP9
GIF
read image description
ALT
It’s official! 🙌 We’re excited to announce the TensorFlow Lite plugin for Flutter has been migrated to our GitHub account.
The latest version includes new features and example apps, such as object detection through a live camera feed.
Learn more → goo.gle/45uGW20
GIF
Learn probabilistic programming with TensorFlow Probability, from the ground up. The Bayesian Methods for Hackers book is now available in open source in TFP!
Read post here ↓ bit.ly/2rwaiMA
📣 Announcing TensorFlow GNN, a new graph neural network library for researchers and developers.
Learn more → goo.gle/3ns00e4
Swift for TensorFlow is now open source!
It is a new programming model for machine learning combining the performance of graphs and the expressivity of Eager execution, with first-class autodiff built right into the compiler
Learn more on the TF blog ↓
Thanks for sharing your Intro to Deep Learning class online! 🙌 They include slides and videos, as well as labs in TensorFlow - and don't forget to follow for more updates! 🧠
Try it out here 👉 introtodeeplearning.com
TensorFlow 2.2.0 has been released!
Check out the release notes for major features and improvements such as a new Profiler for TF 2 for CPU/GPU/TPU, updates on tf.distribute, tf.keras, and more.
Learn more here ↓
We are excited to announce tfjs-vis, a browser based visualization library for TensorFlow.js. It has charts to let you see the data flowing through your model, and a convenient hide-able drawer to put them in while developing your apps.
Check it out → bitly.com/2R6XeZu
Graph models allow for all kinds of optimization, but it can be tricky to move between Python and graph code. To help with this, TensorFlow has AutoGraph, a new feature that converts Python code into pure TensorFlow graph code.
Learn more on the blog ↓
We are so excited to announce the Developer Preview of #TensorFlowLite!
Read all about it in our blogpost → goo.gl/a9czwZ
🎂 Happy 6th birthday #TensorFlow! 🎂
We're proud of the community we've built with you all and how far we've come with TFLite, TFX, TensorFlow.js and more.
Learn how you can get started → tensorflow.org
GIF
Introducing TF-Coder 🖥
A program synthesis tool that helps you write tensor manipulations in TensorFlow. Simply provide an input/output example of the desired behavior, and leave the rest to TF-Coder!
Learn more → goo.gle/3gwTbB6
Try it out → goo.gle/3gtexPX
read image description
ALT
🏅 #TFCommunitySpotlight Winner: Olesya Chernyavskaya 🏅
Working from home and trying to improve your posture? Olesya created a tool in TF to track posture and blur the screen if a person is sitting poorly. Well done, Olesya!
Olesya's GitHub → goo.gle/2CAHvz9
GIF
👀 Iris tracking is now supported in the browser
In this blog, you'll learn how to incorporate Iris landmark tracking to your models through TensorFlowJS. This work is made possible by the MediaPipe Iris model.
Learn how → goo.gle/2HUt0cH
GIF
Check out the new and first blog post by from on Deep Learning Basics with #TensorFlow, as part of the MIT Deep Learning series of courses, lectures, and tutorials.
Read the post here ↓
We’re excited to announce the release of BodyPix!
Real-time Person Segmentation in the Browser with TensorFlow.js (try the live demo!) by , , and others.
Learn more here → bit.ly/2SXz6MA
GIF
The TensorFlow Object Detection API has been updated with image segmentation!
Check it out 👉 goo.gl/NDns6d
New to TensorFlow? Check out this sequence of beginner-friendly tutorials. All of them can be run in (or downloaded as a notebook) with a single click.
Get started here → bit.ly/2NQlZHM
We’re thrilled to announce Intro to TensorFlow for Deep Learning by ! This free course provides a practical approach to learning TensorFlow so that any developer can build #ML models easily. #TFDevSummit
Get started today → udacity.com/tensorflow
TensorFlow now supports SVMs and kernel methods!
Check out our tutorial → tensorflow.org/versions/maste
It's been our goal since we launched to run on as many platforms as possible. We're happy to announce that it's now easier than ever to install TensorFlow on your !
Learn more in 's post ↓
🏅#TFCommunitySpotlight Winner: Moch Galang Rivaldo🏅
Moch created a workout web app with a pose detector to analyze poses and count reps. Great job!
Check it out ➡️ goo.gle/3ohrHJq
0:17
TensorFlow 2 is now the default in Colab → goo.gle/2wHkB6F
(But the `%tensorflow_version 1.x` magic is still there if you need it.) → goo.gle/2wyYNKB
read image description
ALT
Take a sneak peek into TensorFlow 2.0’s new features!
Learn more here ↓
Thanks to for all their work on for #rstats! Native R interfaces for Keras and TF Estimators along with access to the entire TF API from R
Learn more at → tensorflow.rstudio.com
GIF
🌟 introduced their first microcontroller, the Raspberry Pi Pico! We'll be releasing a port of TensorFlow Lite Micro for it soon.
Check out the GitHub here → goo.gle/39a2pTP
And learn more here → goo.gle/2LTwLkr
#TinyML
Introducing Danfo.js 👋
Danfo.js is a Pandas-like Library in #JavaScript that’s #MadeWithTFJS, and provides intuitive data structures for manipulating and processing structured data. Learn more in this article by and .
Read now → goo.gle/2YzqYUj
GIF
🟢 NOW ONLINE: The On-Device ML website
Starting out with on-device machine learning? We just launched a new page with learning pathways to help you master the basics and run ML models client-side in your Android, iOS, and Web app. #GoogleIO
Learn more→ goo.gle/ondevice-ml
GIF
TFLite now also leverages mobile GPUs with OpenGL ES Compute Shaders on Android devices and Metal Compute Shaders on iOS devices!
Learn more here 👉 bit.ly/2ANJrRh
GIF
Take your ML skills to the next level with over 100 Keras code examples! 💯
These workflows cover computer vision, natural language processing, and more! All created by the #Keras community.
Check it out → keras.io/examples
GIF
Introducing Eager Execution - an imperative, define-by-run interface for #TensorFlow!
Learn more here → goo.gl/rk5EFs
GIF
Standardizing on Keras: Guidance on High-level APIs in TensorFlow 2.0.
Read the article here ↓
"I was unemployed due to COVID, and decided to take the TensorFlow Certificate exam. I'm now a Google employee, the certificate helped my resume stand out from other applications." Fran Marmousez, Conversational AI Engineer at Google.
Learn more → goo.gle/2VBU5Yv
read image description
ALT
Thanks for sharing Project DeepSpeech! Open source speech recognition, with pre-trained model & dataset: goo.gl/p7jV27
🗣 Attention #TensorFlow community!
We are excited to announce TensorFlow 2.0. Inspired by all of your feedback, this powerful and easy-to-use framework includes tight Keras integration, expanded TF datasets, and more.
Watch present here → goo.gle/2nTRZCp
GIF
Learn the foundations of Deep Learning and TensorFlow from : complete lecture series and code examples for TensorFlow 2.0 now online!
Read more here ↓
👀 Bring the Mona Lisa effect to life
Urban legend says that Mona Lisa's eyes follow you as you move around the room. brought this effect to life in the browser with #TensorFlowJS.
Read all about it → goo.gle/365z0sv
GIF
TensorFlow 2.0.0-rc0 has been released! With a focus on simplicity and ease of use, this release features API simplification, easy model building with Keras, and more.
See the full release notes for details on added features and changes ↓
We just added a new tutorial that shows how to write Transformer (‘attention’ is all you need) in #TensorFlow 2.0 from scratch.
Check it out here → goo.gl/6e9Xca
Introducing TensorFlow Probability: empowering ML researchers and practitioners to build sophisticated models quickly, leveraging state-of-the-art hardware
Read about it on the TensorFlow blog ↓
🎉 TensorFlow 2.4 is here!
This latest release includes increased support for distributed training and mixed precision, new NumPy frontend, and tools for monitoring and diagnosing performance bottlenecks.
Learn more ↓
🏅#TFCommunitySpotlight Winner: Javier Gamazo Tejero 🏅
Javier used TF to capture movement with a webcam and transfer it to Google Street View to give a virtual experience of walking through different cities. Great work, Javier!
Javier’s GitHub → goo.gle/3hgkmBc
0:07
We just released PoseNet 2.0 with TensorFlow.js, including a much more accurate ResNet-based model!
Try the live demo by , , , , , → goo.gle/2IuKbPb
Learn more here → goo.gle/2IxakwY
GIF
We are so excited to announce support for Core ML in #TensorFlowLite.
Read about the announcement in our blog post:
Not an expert in machine learning? TensorFlow has you covered. Check out this talk from #io17: goo.gl/yj7CiU
Learn how to train a model using tf.keras in Colab, then run it in the browser with TensorFlow.js, in this article by
Read his post here → bit.ly/2IZfMpk
GIF
Lingvo is a deep learning framework used for sequence modeling tasks like machine translation, speech recognition, and speech synthesis.
Learn more here ↓
🚨 New & TensorFlow course coming in December!
announces a new 4-course specialization called TensorFlow Data & Deployment
Bring your ML skills to the real world!
1:45
Good hyperparameters lead to ML success! 🙌
Learn how you can find the best parameters with Keras Tuner— a fully-featured, scalable, and easy-to-use hyperparameter tuning library for Keras and beyond.
Read the blog → goo.gle/2uCnJzt
read image description
ALT
🔔 Update!
TensorFlow 2.3 has been released with new tools to make it easier to load and preprocess data, and solve input-pipeline bottlenecks. Check out all the latest features and updates in the blog.
Learn more ↓
MLIR is a new compiler framework designed to optimize the execution time of #machinelearning models and make it easier to add support for new devices to TensorFlow.
Check out this article to learn more → bit.ly/2UqhJFK
and our Github repo → bit.ly/2UtOSRj
TensorFlow 1.12.0 has been released! Please see the full release notes for details on added features and changes.
More info here ↓ bit.ly/2qzMzuv
⚡ Use Machine Learning models in all your web prototypes.
Join and see how Machine Learning can give your web apps a whole new set of superpowers. #ChromeDevSummit
Start learning with us → goo.gle/39XZ2jh
0:07
🦸♀️🦸♂️️Superpowers straight from your browser
Discover how to achieve superpowers in the browser by embracing machine learning in JavaScript using TensorFlow.js, and follow along as shows several creative prototypes.
Check it out → goo.gle/37n7FkE
GIF
We’re excited to share that weight pruning is now part of the TensorFlow Model Optimization Toolkit!
Learn how sparsity can dramatically reduce model sizes with negligible accuracy loss.
Read here → goo.gle/2vYWBrO
GIF
Using Graph Neural Networks and Long Short-Term Memory networks, ML developers can now forecast traffic conditions!
Learn how in the latest #Keras walkthrough → goo.gle/3ttJD47
Effective TensorFlow 2.0: A Guide for Best Practices and What’s Changed.
Read more here → bit.ly/2N6f0dG
Now you can translate between languages, using tf.keras + eager! Check out this nice example of Neural Machine Translation with Attention, by .
Try it on Colab → bit.ly/2MHCKEE
TensorFlow 1.6.0 has been released!
Please see the full release notes for details on added features and changes ↓
TensorFlow 2.0 alpha is here! We've asked the community what they wanted and we're working to make TensorFlow simpler and easier to use for everyone.
Read up on how to get started here → bit.ly/2Tt7eQY
GIF
🎉To make ML accessible beyond ML experts, we’ve released Simple ML for Sheets.
#SimpleMLForSheets is an add-on for Google Sheets from the TensorFlow team that can help make machine learning accessible to all without programming or ML expertise.
Try it→ goo.gle/sml
read image description
ALT
🆕 If you're new to quantum machine learning...
Check out this post to see how TensorFlow Quantum (TFQ) helped one researcher publish their first paper, and what it can do for you!
Learn more → goo.gle/33kURu2
read image description
ALT
The release of the Beta for TensorFlow 2.0 is here! We've closed over 100 issues you reported against the alpha release. Your feedback has helped us get to where we are today, please keep it coming!
Get more info here → goo.gle/2IpE5OZ
read image description
ALT
You can now build and run ML pipelines in an interactive Colab notebook using TensorFlow Extended (TFX)! 📓
Develop in a notebook and then export to a production-ready ML pipeline.
Try it in your browser today → goo.gle/TFXnotebook
GIF
We are excited to announce the open sourcing of TFRT, a new TensorFlow runtime that is going to improve the performance, extensibility, and modularity of TensorFlow.
Read all about it → goo.gle/2xid3rd
read image description
ALT
Architecture meets AI. ArchiGAN is an app that uses #Pix2Pix and TensorFlow to generate floor plans.
See how it’s done on the blog → goo.gle/2YeCCkq
Try Pix2Pix yourself → goo.gle/2YezrJs
GIF
MoveMirror matches your movements with images from around the world. Built with TensorFlow.js and #PoseNet.
Learn more here→ bit.ly/2NZLNS5
GIF
📢 Blazeface is now available in browsers with TensorFlow.js!
The model detects faces and facial features in real-time 👨👩⏰
Try it out now → goo.gle/2QP3iqd
GIF
The brand new TensorFlow Datasets, make it super easy to load a variety of public datasets into #TensorFlow programs in both tf.data and NumPy format!
Read ’s article to learn more ↓
Quantify the uncertainty in your forecasts with structural time series models. Now available in TensorFlow Probability!
Read the post here ↓ bit.ly/2FpaJjA
Get started with ML on with #TensorFlow Lite in this second guest article by the Arduino team. Learn step-by-step how to classify objects, in this fruit identification example!
Read the blog for more details → goo.gle/2NSOhSG
GIF
🥳 Introducing TensorFlow Similarity!
Our newest python package is focused on making similarity learning quick and easy, and is now in Beta.
Full details ↓
🧘♂️ MoveNet is now on mobile!
The state-of-the-art pose estimation model finally comes to mobile via TensorFlow Lite with CPU acceleration enabled. Now you can run pose estimation in realtime on modern smartphones.
Learn more 👉 goo.gle/3m494pn
GIF
Check out this helpful guide to text classification, including an end-to-end walkthrough, flowchart, and best practices learned from ~450k experiments. Implemented with tf.keras → bit.ly/2NGUS0U
TensorFlow Serving has released version 1.8.0 & now supports a RESTful API out of the box! You can now easily make classification, regression & prediction requests to your TensorFlow models using JSON objects.
Learn more here ↓ bit.ly/2y2xR5N
The new Machine Learning Engineering for Production course teaches how to get your ML models into production. Learn from the experts!
Details here ↓
You can perform machine learning inference and training right in the browser with TensorFlow.js
put together a tutorial for getting started. All you need is a little HTML and JS.
Read the post here → bit.ly/2MhyJqf
Track human poses on iOS devices with TensorFlow Lite! 💃
📹TensorFlow Lite takes the camera input and overlays the key body parts in real-time, thanks to
Try it out here → goo.gle/2Qzv6Qv
GIF
Introducing TensorBoard.dev: a new way to share your ML experiment results online!
Read the blog → goo.gle/2LbOyzK
read image description
ALT
Help Protect the Great Barrier Reef!
Announcing a new competition with and TensorFlow to help protect coral reefs, with prizes for accuracy and performance.
Learn more → goo.gle/3l1r0zr
⚡️TensorFlow 2.1.0 is out NOW!⚡️
This will be the last TF release supporting Python 2. Please see the full release notes for details on added features and changes!
Learn more here ↓
🧩 The Real-time AR Sudoku Solver.
See how developer Chris Greening built an augmented reality web app to solve Sudoku puzzles in real-time on today's #MadewithTFJS with .
Learn more → goo.gle/3nI7dEx
GIF
Introducing the TensorFlow Research Cloud: 1,000 Cloud TPUs to support open machine learning research. goo.gl/2mnD0p
What if you could use BERT right in your browser?
This #TensorflowJS experiment helps you find answers to your questions on any webpage. #madeWithTFJS
Learn more about it here → goo.gle/2W5gE65
GIF
☁️ Train your model with TensorFlow Cloud
The TensorFlow Cloud repository provides APIs that allow you to go from debugging and training your Keras models locally to distributed training in the cloud with no code changes to your model.
Learn more → goo.gle/3fw72Yg
read image description
ALT