Tweetovi

Blokirali ste korisnika/cu @A_K_Nain

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

  1. Prikvačeni tweet
    2. lis 2019.

    As promised, here is the first super clean notebook showcasing 2.0. An example of end-to-end DL with interpretability. Cc: PS: Wait for more!

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    prije 16 minuta
    Odgovor korisniku/ci

    Some teaching material that covers some of this (in code exercises)

    Poništi
  3. proslijedio/la je Tweet
    prije 11 sati

    Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation pdf: abs: github:

    Poništi
  4. proslijedio/la je Tweet
    prije 5 sati

    Want to code your own realtime object detection app with ? Be sure to check out this hands-on tutorial.

    Poništi
  5. proslijedio/la je Tweet
    prije 7 sati
    Poništi
  6. proslijedio/la je Tweet
    prije 8 sati
    Poništi
  7. proslijedio/la je Tweet

    We're having a Keras community meeting this Friday. If you want to make a Keras-related announcement or short presentation (~2 min) at the meeting, please send it to me by email and I'll include you.

    Prikaži ovu nit
    Poništi
  8. prije 21 sat

    If this isn't the best tweet, Idk what is!

    Poništi
  9. proslijedio/la je Tweet
    3. velj

    Check out the comments on the Facebook post for thoughts by Jitendra Malik, Alyosha Efros, Michael Black and others

    Poništi
  10. proslijedio/la je Tweet

    PyPI downloads for TensorFlow (and its closest competitor, added for scale). Notice how it starts jumping after the release of TF 2.0 late last year (the short gap afterwards is the holiday break) Up and to the right 📈

    Poništi
  11. 4. velj

    The biggest reasons why PyTorch became so popular on 1. Amazing model zoo. Very imp to start with a pretrained model in any comp based on NNs. 2. Compared to TF 1.x, writing models in it felt like writing C++ vs Python

    Poništi
  12. proslijedio/la je Tweet
    3. velj

    Googler asks a good question here, so I'll share my thoughts on Meena in a short thread. (1/6)

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    29. sij

    Finally watched 's talk, "Writing simpler and more maintainable Python" today. Some great visuals and analogies in this talk! 👍 I love the complexity mountain range, the functionality/users table, and the gravity of complexity. 🏔📈

    Poništi
  14. proslijedio/la je Tweet
    2. velj

    following my three-strikes-rule of "if you answer the same question three times in a short period write it down"; here's a simple example of loss masking for sequences with a custom training loop in tf2.0

    Poništi
  15. 2. velj
    Poništi
  16. 2. velj
    Poništi
  17. proslijedio/la je Tweet
    31. sij

    py-sanity: Opinionated Coding Guidelines and Best Practices in Python

    Poništi
  18. proslijedio/la je Tweet
    31. sij

    Success: I trained ResNet-50 on imagenet to 75.9% top-1 accuracy in 3.51 minutes using a 512-core TPUv3. (480,000 images per second. 224x224 res JPG.) Before you think highly of me, all I did was run Google’s code. It was hard though. Logs:

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    31. sij

    A full build of Autopilot neural networks involves 48 networks that take 70,000 GPU hours to train. Together, they output 1,000 distinct tensors (predictions) at each timestep. This is what a Tesla autopilot sees [source: ]

    Poništi
  20. proslijedio/la je Tweet
    31. sij

    Very excited to share "Learning Discrete Distributions by Dequantization" () in collaboration with and , from my internship at . We explore different methods and distributions for dequantization and reach 3.06 bpd on CIFAR10.

    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    31. sij

    FIS-Nets: Full-image Supervised Networks for Monocular Depth Estimation.

    Poništi

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:

    ·