TensorFlowVerified account

@TensorFlow

TensorFlow is a fast, flexible, and scalable open-source machine learning library for research and production.

Joined February 2011

Tweets

You blocked @TensorFlow

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @TensorFlow

  1. Pinned Tweet
    Nov 8

    TensorFlow 1.12.0 has been released! Please see the full release notes for details on added features and changes. More info here ↓

    Undo
  2. Nov 9

    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 , look at all the features we've added over the years to make TensorFlow easier to use.

    Undo
  3. Retweeted
    Nov 7

    Super excited: are now available in a public alpha, including public pricing (linear, see: ). It's really amazing to (with zero code changes-thanks ) crank the dial to 11 to train models and iterate 10-64x faster than ever before.

    Undo
  4. Nov 6

    Introducing QuantumCasts, our new series on everything you want to know about quantum computers and how to program them! Learn more here →

    Undo
  5. Nov 5

    The On-device Visual Intelligence Competition (OVIC) is back! Check out Track 1 of the Low Power Image Recognition Challenge, and submit your real-time on-device image classification or detection model in Lite. Learn more here →

    Undo
  6. Nov 2

    Facilitate the process of serving ML models from experimentation to production with TensorFlow Serving and . Learn more here ↓

    Undo
  7. Retweeted
    Nov 1

    I really enjoyed reading 's The Illustrated Transformer . Transformer-style architectures are very promising, and underpin the latest SotA NLP such as BERT and Mesh . Great for 2

    Undo
  8. Oct 29

    Thank you for your help updating the text generation tutorial! Check it out here →

    Undo
  9. Oct 26

    If you missed the TensorFlow team at the O’Reilly AI Conference in San Francisco, the full playlist is now available. Topics include: TensorFlow Lite, TensorFlow.js, TFX (Extended) & Hub, Distributed TensorFlow, and more! Find more info and videos here →

    Undo
  10. Oct 25

    Training ML models takes time and losing your weight values can happen at the touch of CTRL-C. In this shows you how to load and save models at every epoch so you never lose time or data. Watch here →

    Undo
  11. Oct 25

    Image augmentation lets you get the most of your dataset. We released state-of-the-art AutoAugment Modules on allowing you to train better image models with less data! Check it out here →

    Undo
  12. Retweeted

    🛰Will never stop being enchanted by creative applications of machine learning in new problem spaces. 📃Check out this paper on SmallSats: the authors use Hub + Lite to deploy deep learning models on low-memory, low-power, space-grade, embedded platforms.

    Show this thread
    Undo
  13. Oct 18

    In last week's , we looked at model overfitting/underfitting. Now takes a closer look at regularizing models, training, testing and launching them for comparison. Watch here →

    Undo
  14. Retweeted

    Eager Execution Enabled In this notebook I explain different concepts in eager execution. I go over variables, ops, gradients, custom gradients, callbacks, metrics and creating models with tf.keras and saving/restoring them.

    Show this thread
    Undo
  15. Oct 12

    TensorFlow 1.12.0-rc0 has been released! Please see the full release notes for details on added features and changes. Learn more here ↓

    Undo
  16. Oct 11

    Overfitting models are too specialized to generalize, and underfitting models are too generalized to specialize! looks at how this happens and how to avoid it in the first of a two parter . Watch here →

    Undo
  17. Oct 11

    In this guest post on the TensorFlow blog, VP Data Science & Analytics at BHGE Arun Subramaniyan explores industrial ML with probabilistic deep learning andTensorFlow Probability. Read the post here ↓

    Undo
  18. Oct 10

    Take a closer look at how we used to bring Emoji Scavenger Hunt to life! Read the post here →

    Undo
  19. Retweeted

    New Developer Blog: Mixed Precision Training for and Speech Recognition with OpenSeq2Seq - an open-source, -based toolkit.

    Undo
  20. Retweeted
    Oct 5

    The 1st ever roadshow in India has come to an end. 🇮🇳🎊 Thank you to the wonderful audience for your enthusiastic participation. We look forward to seeing all of you soon!

    , , and 2 others
    Undo

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·