Fragcolor

@fragcolor

AI engineering focusing on small devices, drones, cinema and games. Creators of . DMs are open.

Kyoto City, Kyoto
Vrijeme pridruživanja: rujan 2018.

Tweetovi

Blokirali ste korisnika/cu @fragcolor

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

  1. Prikvačeni tweet
    16. sij 2019.

    We just launched our new website! Take a look and see what we are working on!

    Poništi
  2. proslijedio/la je Tweet
    11. lip 2019.

    We are working on a product very much inspired by this and neuroevolution in general. MNIST was a huge challenge for me in terms of CPU optimizations. Given you work at google and google cloud is probably cheap for you :) I wonder, how many VMs you had to throw at it?

    Poništi
  3. proslijedio/la je Tweet
    10. velj 2019.

    I'm sharing a basic skeleton plugin written in using our nimline magic. Just build and drop, only the headers are required.

    Poništi
  4. 22. sij 2019.

    We just released a small but quite magic library that allows you to literally inline and consume C/C++ from your code. Wrappers and bindings are a thing from the past. No performance stolen from useless jumps, less cache misses etc...

    Poništi
  5. 13. sij 2019.

    Another teaser of the plugin we are going to release.

    Poništi
  6. 12. sij 2019.

    A small teaser of the first plug-in we are going to release soon! Powered by and ATen/C10 ()

    Poništi
  7. proslijedio/la je Tweet
    21. pro 2018.
    Poništi
  8. proslijedio/la je Tweet
    15. stu 2018.

    We ran almost the full experience on an iPhone. Check why it matters in this article!

    Poništi
  9. proslijedio/la je Tweet
    11. stu 2018.

    A new weekly release of NimTorch is out. Version: 2018.11.11.1678 As usual integrating all those precious changes the community made! Available on or

    Poništi
  10. proslijedio/la je Tweet
    5. stu 2018.

    After fixing a bug... Check smoking on some style transfer convolution heavy task: Nim: Style description: 6.876438856124878 Synthesis step 0: 4.357500076293945, Loss: 260892944.0 Py: Style description: 12.565336733998265 Synthesis step 0: 7.518403548980132

    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:

    ·