TensorFlowVerified account

@TensorFlow

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

Mountain View, CA
tensorflow.org
Joined February 2011
266 Photos and videos Photos and videos

Tweets

You blocked @TensorFlow

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

  1. Pinned Tweet
    Mar 7

    That's a wrap on 2019! Thank you to everyone who attended and tuned in. Don't worry if you missed anything, we've got you covered. Check out our recap blog for all the major highlights and announcements! Read the recap here →

    7 replies 83 retweets 315 likes
    Undo
  2. Retweeted
    Apr 30

    Even if you have a small dataset, you can still leverage existing models that have been trained on millions of images using transfer learning. Course 2 of the TensorFlow Specialization teaches you how to implement it:

    37 retweets 148 likes
    Undo
  3. Apr 30

    TensorFlow CPU optimizations accelerate genomics computations in DeepVariant by >3x. Learn how in this blog from the Brain Genomics team ↓

    1 reply 81 retweets 232 likes
    Undo
  4. Retweeted
    Apr 21

    Learn how to activate your in with just 2 lines of code for up to 3X speedup on training. Register here:

    62 retweets 167 likes
    Undo
  5. Apr 26

    In this episode of TensorFlow Meets, Megan Kacholia, TensorFlow Engineering Director shares how TensorFlow has evolved to become more developer friendly, the run-time options for developers, and the latest update on TensorFlow 2.0! Watch here →

    46 retweets 146 likes
    Undo
  6. Apr 24

    In this special episode live from 2019, and answer questions on using callbacks to cancel training, getting started with 2.0, and more! Watch here →

    2 replies 35 retweets 101 likes
    Undo
  7. Retweeted
    Apr 22

    Don't miss your chance to take the stage at the first . We're looking for case studies, technology deep-dives, and more. The call for speakers closes tomorrow, April 23.

    1 reply 10 retweets 24 likes
    Undo
  8. Apr 19

    In this video from 2019, and founder, chat about the future of Swift for TensorFlow and the new Swift online course coming to this June! Watch this TensorFlow Meets here →

    2 replies 56 retweets 211 likes
    Undo
  9. Apr 19

    Take an inside look into the team’s own internal training sessions! Follow along as Skye Wanderman-Milne dives into Control Flow, from its low-level ops & base APIs, to the new “functional” ops in Control Flow v2. Watch here →

    1 reply 81 retweets 249 likes
    Undo
  10. Retweeted
    Mar 31

    My new blog post is on air. Neural machine translation with Luong attention on 2.0. Building complicated models is just as easy as stacking up Lego pieces with . Check it out below:

    6 replies 197 retweets 630 likes
    Undo
  11. Apr 18

    Learn about the new library using Swift for directly from & at this upcoming workshop. (Tickets for the course are priced at $500, and space is limited!) Sign up here ↓

    1 reply 37 retweets 120 likes
    Undo
  12. Apr 17

    Create a real production ML pipeline with this new step-by-step tutorial! It guides developers through the process from ingesting data and training a model, to deploying, and production. Get started here →

    8 replies 181 retweets 519 likes
    Undo
  13. Retweeted
    Apr 13

    Loads of new information in this just-published talk on MLIR from and Tatiana Shpeisman. But *this* is the money slide. *This* is why we're investing in Swift for Tensorflow. This is how we get to the next stage of deep learning.

    4 replies 102 retweets 382 likes
    Undo
  14. Retweeted
    Apr 11

    "If you’re in industry, 2.0 has for production pipelines, for deploying to mobile, TF.js for the web. [...] For research, I’ve found that TF 2.0 and PyTorch 1.0 are sufficiently similar that I’m comfortable using either one." ✨🙌 Great primer, Akshay!

    A Primer on 2.0 | Debug Mind Differentiating through control statements is now easy, and no more global collections! I 👍 this: "What TF 2.0 and PyTorch 1.0 accomplish in Python is impressive, but they’re pushing the language to its limits"
    6 replies 13 retweets 66 likes
    Undo
  15. Retweeted
    Apr 11

    is where today’s top minds bring to life. Apply to speak by April 23 for your chance to join other pioneers and practitioners of the machine learning revolution.

    28 retweets 39 likes
    Undo
  16. Apr 12

    In this episode of TensorFlow Meets, joins to discuss the new Intro to for Deep Learning course and how TF 2.0 makes it easy to get started with Deep Learning. Watch here →

    1 reply 36 retweets 162 likes
    Undo
  17. Retweeted
    Apr 4

    It’s easy for humans to tell the difference between a shirt and shoes, but not so easy for a computer. and explain why in Course 1 of the TensorFlow Specialization, available for $49 or to audit for free:

    43 retweets 166 likes
    Undo
  18. Apr 11

    We just added a new tutorial that shows how to write Transformer (‘attention’ is all you need) in 2.0 from scratch. Check it out here →

    6 replies 296 retweets 863 likes
    Undo
  19. Retweeted
    Apr 8

    I created a Colab notebook for this blog post (full training included) and committed to Tensorflow's examples repo. You can now "click and run" at . Many thanks to and team for making this happen.

    My new blog post is on air. Neural machine translation with Luong attention on 2.0. Building complicated models is just as easy as stacking up Lego pieces with . Check it out below:
    4 replies 38 retweets 174 likes
    Undo
  20. Apr 9

    In this episode of TensorFlow Meets, shares with some of the ways we are building as a community including the Request for Comments process, 6 special interest groups, codebase modularity, and more! Watch here →

    16 retweets 56 likes
    Undo
  21. Retweeted
    Apr 8

    Here's a minimal implementation of Deep Dream in 2.0, using the Keras Functional API for feature extraction (it's just a few lines!) and a GradientTape for hackability.

    6 replies 75 retweets 332 likes
    Show this thread
    Show this thread
    Undo

@TensorFlow hasn't Tweeted yet.

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

    ·