PyTorch

@PyTorch

pytorch.org
Joined September 2016
76 Photos and videos Photos and videos

Tweets

You blocked @PyTorch

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

  1. Dec 11

    We are holding an informal PyTorch meetup for attendees on this Thursday (Dec 12) from 3:05 PM to 3:50 PM PT (a long coffee break). Meet us at West Level 2 next to rooms 220-222 in the hallway area.

    2 replies 14 retweets 82 likes
    Show this thread
    Image
    Show this thread
    Undo
  2. Dec 9

    If you are at , visit the PyTorch team at East Exhibition Hall A Booth 509. At 4:45 PM PT today, we’ll be walking through a demo of PyTorch running fast neural style transfer on a Cloud TPU. If you can’t join us in-person, check out:

    Image
    3 replies 43 retweets 203 likes
    Undo
  3. Retweeted
    Dec 6

    The first full paper on after 3 years of development. It describes our goals, design principles, technical details uptil v0.4 Catch the poster at Authored by , et. al.

    12 replies 463 retweets 1,816 likes
    Show this thread
    Image
    Show this thread
    Undo
  4. Retweeted
    Dec 6

    We are very excited to announce that and are partnering to fund work on including: - Joint technical work on and - 7 Remote, Open Source Dev Fellowships - Security and Performance Competitions Learn more:

    Image
    3 replies 83 retweets 261 likes
    Undo
  5. Dec 6

    PyTorch Elastic for distributed elastic training — where nodes can join and leave during training — is now available as an experimental feature, along with ClassyVision, a new framework for large-scale training of image and video classification models:

    1 reply 75 retweets 238 likes
    Undo
  6. Retweeted
    Dec 4

    [News] Preferred Networks (PFN) migrates its DL platform from Chainer to PyTorch. Chainer moves to maintenance support. PFN jointly works with Facebook and the OSS community to develop PyTorch. For more information, please look at the news release:

    2 replies 238 retweets 457 likes
    Undo
  7. Retweeted
    Dec 4

    BertViz now supports ALBERT, CamemBERT, CTRL, and other transformers through a simplified API: Can you guess which model below is BERT and which is ALBERT? (hint: cross-layer parameter sharing)

    Image
    4 replies 67 retweets 252 likes
    Undo
  8. Retweeted
    Nov 28

    We have released our platform for source separation in music. We adapt Conv-Tasnet and introduce the Demucs architecture, leading to two state-of-the-art models surpassing all previously known methods such as Wave-U-Net, Open-Unmix or Spleeter.

    14 replies 143 retweets 470 likes
    Show this thread
    Image
    Show this thread
    Undo
  9. Retweeted
    Dec 2

    Have a good level of ? Interested in and developing further the library? Join us Dec 14th at (Barcelona, Spain) for a full hands on session on differentiable Computer vision with PyTorch. More info:

    Image
    4 replies 20 retweets 63 likes
    Undo
  10. Nov 26

    3-Step Transfer Learning using Transformers and training framework. A step-by-step post by

    Image
    96 retweets 324 likes
    Undo
  11. Retweeted
    Nov 25

    We just released the paper and code for Mellotron: a multispeaker voice synthesis model that can make a voice emote and sing without emotive or singing training data.

    3 replies 128 retweets 415 likes
    Show this thread
    Image
    Show this thread
    Undo
  12. Nov 21

    To help developers get started with PyTorch, we’re making the 'Deep Learning with PyTorch' book, written by Luca Antiga and Eli Stevens, available for free to the community:

    Image
    39 replies 1,038 retweets 2,872 likes
    Undo
  13. Retweeted
    Nov 18

    Few people seem to realize that master is easily built for 's ROCm. For this reason and my own reference I wrote a short how-to at If there is enough interest, I could probably also put up binaries for selected Python versions.

    14 replies 70 retweets 268 likes
    Show this thread
    Image
    Show this thread
    Undo
  14. Retweeted
    Nov 15

    Pyro 1.0 is released: stable APIs, a jit-compatible Predictive helper, new normalizing flows, parallel-scan GPs and state space models, more-automatic AutoGuides, an OED tutorial, FoldedDistribution, and PyroModule[-] to make your nn.Modules Bayesian

    1 reply 95 retweets 382 likes
    Undo
  15. Nov 14

    Learn how Caltech uses PyTorch to build deep learning systems that can understand the aerodynamics of how aircrafts interact with the ground to enable much smoother and safer landings:

    1 reply 88 retweets 360 likes
    Undo
  16. Retweeted
    Nov 13

    Frequent users of gradient penalty (WGAN-GP, StyleGAN, etc.), make sure to try out the new Linfinity hinge gradient penalty from for better results. See for how to quickly and easily implement it in .

    My new paper is out! We show a framework in which we can both derive and gradient penalized ! We also show how to make better gradient penalties!
    Show this thread
    1 reply 44 retweets 169 likes
    Undo
  17. Retweeted
    Nov 13

    Excited to release a library for 3D deep learning! Check it out, and give us feedback! Great effort by Edward Smith, JF Lafleche Artem Rozantsev, Tommy Xiang, Gav State, . We plan to extend it with many exciting features!

    Research efforts in computer vision and are on the rise. To accelerate 3D research, NVIDIA releases Kaolin as a PyTorch library. See how researchers use Kaolin to move 3D models into the realm of neural networks.
    3 replies 160 retweets 709 likes
    Show this thread
    Image
    Show this thread
    Undo
  18. Retweeted
    Nov 8

    nnAudio: CQT layers + etc. Done by Kin Wai Cheuk et al. And yes, it’s fast.

    Image
    Image
    3 replies 25 retweets 106 likes
    Show this thread
    Image
    Show this thread
    Undo
  19. Retweeted
    Nov 7

    I've made a PyTorch-based fork of neural-style which adds spatial control when using multiple styles (aka masked style transfer). Code is here:

    Image
    Image
    6 replies 43 retweets 272 likes
    Show this thread
    Image
    Show this thread
    Undo
  20. Nov 7

    torchvision v0.4.2: Optimized video reader backend This minor release provides up to 6x speedup for video reading using a new backend option. Read more at:

    1 reply 50 retweets 215 likes
    Undo

@PyTorch 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

    ·