NGUYEN Thanh Tu

@thanhtu19392

Machine Learning, Data Science, Finance

Vrijeme pridruživanja: veljača 2015.
3 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @thanhtu19392

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @thanhtu19392

  1. proslijedio/la je Tweet
    12. stu 2019.

    Full comparison against state-of-the-art on ImageNet. Noisy Student is our method. Noisy Student + EfficientNet is 11% better than your favorite ResNet-50 😉

    5 replies 21 proslijeđeni tweet 110 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    21. lis 2019.

    Check out these winning scripts from the Utility Script Competition! 🏆🏆🏆 "There was some really excellent work submitted, but these scripts received the top scores from the Kaggle team." —

    1 reply 36 proslijeđenih tweetova 122 korisnika označavaju da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    4. lis 2019.

    We're open-sourcing Hydra, a new framework with a dynamic approach to code configuration that accelerates the development of complex Python applications.

    62 proslijeđena tweeta 169 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    30. ruj 2019.

    🎉 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 ↓

    36 replies 1.657 proslijeđenih tweetova 3.866 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    24. ruj 2019.

    Transformers have led to a wave of recent advances in such as BERT, XLNet and GPT-2, so here is a list of resources💻 I think are helpful to learn how Transformers work, from self-attention to positional encodings. I would loosely go through these in the following order👇

    9 replies 291 proslijeđeni tweet 906 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    11. ruj 2019.

    The paper that introduced Batch Norm combines clear intuition with compelling experiments (14x speedup on ImageNet!!) So why has 'internal covariate shift' remained controversial to this day? Thread 👇

    14 replies 353 proslijeđena tweeta 1.177 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 3. ruj 2019.

    My very first gold medal in kaggle, and in prize zone. This competition is very fun and tough. Proud to be a part of an amazing team with my colleagues. hope it is only a start.

    2 korisnika označavaju da im se sviđa
    Poništi
  8. 2. ruj 2019.

    Honoured to present our project OCR CardX with my colleague at BNP AI summer school

    Poništi
  9. proslijedio/la je Tweet
    26. kol 2019.

    We now released code and trained models for our GSCNN semantic segmentation work done at . Check it out! Paper (ICCV'19): Project page: Code ( ):

    204 proslijeđena tweeta 635 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    22. kol 2019.

    A further improvement upon the RAdam optimizer, combining it with LookAHead () gives even better performance than SGD while converging faster. Another great article from Less Wright with a implementation.

    102 proslijeđena tweeta 371 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 25. srp 2019.

    Very nice AI meetup organized by

    7 korisnika označava da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    9. srp 2019.

    New paper on studying how the critical batch size changes based on properties of the optimization algorithm (including momentum and preconditioning), through two different lenses: large scale experiments, and analysis of a simple noisy quadratic model.

    20 proslijeđenih tweetova 115 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    8. srp 2019.

    Excited to share our newest course: A Code-First Introduction to Natural Language Processing All code & videos are available for free online, please check it out!

    29 replies 856 proslijeđenih tweetova 2.661 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    2. srp 2019.

    We are open-sourcing a state-of-the-art deep learning recommendation model to help researchers and the systems and hardware community develop new, more efficient ways to work with categorical data.

    7 replies 221 proslijeđeni tweet 582 korisnika označavaju da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    8. srp 2019.

    Want to stay up-to-date on your literature but don’t have the time to read each paper? Np, I got you! 😏 I added short TLDR snippets to each entry in my growing list of essential papers: Thanks to for the awesome suggestion!

    11 replies 172 proslijeđena tweeta 530 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    18. velj 2019.

    implementation of the Box Convolution layer introduced by Burkov & Lempitsky at - box kernel is a rectangular averaging filter - filter values are fixed and unit - learning 4 parameters per rectangle: size & offset

    91 proslijeđeni tweet 286 korisnika označava da im se sviđa
    Poništi
  17. proslijedio/la je Tweet
    27. svi 2019.

    My PyTorch implementation of siamese and triplet networks with online mining recently got its 1000th star on GitHub! I really didn't expect it would get this popular. I'm happy to see people using it in their projects!

    6 replies 117 proslijeđenih tweetova 512 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    23. svi 2019.

    torchvision 0.3.0: segmentation, detection models, new datasets, C++/CUDA operators Blog with link to tutorial, release notes: Install commands have changed, use the selector on

    9 replies 300 proslijeđenih tweetova 956 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    23. svi 2019.

    Check out this Transformer Chatbot Tutorial with TensorFlow 2.0, by . Read more on the TensorFlow blog ↓

    1 reply 189 proslijeđenih tweetova 525 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    23. svi 2019.

    I'm very happy to announce the 0.3 release of torchvision. It brings several new features, including custom C++/CUDA ops, pre-trained Mask R-CNN models and much more! Check it out at Plus, training Mask R-CNN is even faster than in maskrcnn-benchmark!

    5 replies 63 proslijeđena tweeta 236 korisnika označava da im se sviđa
    Poništi

@thanhtu19392 još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·