On-Device AI Co., Ltd.

@device_ai

Our Services : Deploy deep learning models on mobile and IoT devices.

Taipei City, Taiwan
on-device-ai.com
Vrijeme pridruživanja: travanj 2019.
2 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @device_ai

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

  1. proslijedio/la je Tweet
    prije 9 sati

    It's great to see new datasets and examples for embedded ML from SensiML: Includes predictive maintenance and gesture recognition!

    1 reply 10 proslijeđenih tweetova 24 korisnika označavaju da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    2. velj
    Odgovor korisniku/ci

    Would love to see this running on the Octopus! The code output from Edge Impulse is standard C++11 aimed at most MCUs, explanation here: Let us know how it goes!

    1 reply 2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  3. proslijedio/la je Tweet
    1. velj

    Deeply impressive if you understand what hw this can run on, and just as importantly, the reach of a device to communicate what has been deduced. Don't send all the data, send the state. Up to us to use this to solve real life problems.

    2:16
    A video of our live sheep activity tracking demo from featuring as the sheep!
    1 proslijeđeni tweet 5 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    1. velj

    Want to become a contributor to AutoKeras? This would be a good start.

    4 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    31. sij

    Geilste Demo auf der ever

    1 proslijeđeni tweet 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    1. velj

    A video of our live sheep activity tracking demo from featuring as the sheep!

    35 proslijeđenih tweetova 122 korisnika označavaju da im se sviđa
    Poništi
  7. proslijedio/la je Tweet
    31. sij

    "The chip delivers a good migration path from Arduino-based prototypes to production systems without the need to develop a complex circuit board." highlights our new Portenta H7 module:

    , , i još njih 2
    28 proslijeđenih tweetova 87 korisnika označava da im se sviđa
    Poništi
  8. proslijedio/la je Tweet
    31. sij

    We just released v0.12 in time for & it is a big one! Support for new and boards, many compiler improvements, better support for and so much more. Thank you to all the contributors!

    37 proslijeđenih tweetova 107 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    31. sij

    My slides from on adding intelligence to LoRaWAN devices (with sheep!)

    13 proslijeđenih tweetova 43 korisnika označavaju da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    31. sij

    Want to build your first tiny machine learning model? Learn how to capture data from an accelerometer, train and validate a model, and deploy it back to an embedded device in 20 minutes!

    1 reply 10 proslijeđenih tweetova 31 korisnik označava da mu se sviđa
    Poništi
  11. proslijedio/la je Tweet
    30. sij

    We’re live! You can now use to bring machine learning to your embedded device, and make devices truly smarter!

    7 proslijeđenih tweetova 22 korisnika označavaju da im se sviđa
    Poništi
  12. proslijedio/la je Tweet
    30. sij

    🎉🎊🍾 is now live! You should sign up and check it out ☺️ Grab one of these boards to try our data capture firmware and start training some TinyML models:

    We are live! launches a free service for software developers to deploy the next generation of intelligent devices
    8 proslijeđenih tweetova 24 korisnika označavaju da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    30. sij

    We are live! launches a free service for software developers to deploy the next generation of intelligent devices

    28 proslijeđenih tweetova 45 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    30. sij

    Hey ! Come join our launch party tonight for 🎤 and 🍻. Sign up for free here:

    3 proslijeđena tweeta 5 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    29. sij

    With our Dataset Generator, train a custom finger tracking model in 4 steps: 1) Get 12 pictures of hands 2) Generate 5k images & annotations 3) Train a mobile-optimized model w/ our notebooks 4) Integrate w/ our training template & SDK Request access:

    4 proslijeđena tweeta 16 korisnika označava da im se sviđa
    Poništi
  16. proslijedio/la je Tweet
    28. sij

    Researchers in 🧠 If you’re pushing the boundaries of machine learning research, you won't want to miss . Join us for two days of technical talks, demos, breakout sessions and more. Request an invite here →

    55 proslijeđenih tweetova 141 korisnik označava da mu se sviđa
    Poništi
  17. proslijedio/la je Tweet
    27. sij

    If you need someone to walk you through TinyML, you cannot find a better person than . I highly recommend his TinyML book screencast.

    1 reply 5 proslijeđenih tweetova 29 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    24. sij

    Cosmos aligned. We'll be back at Shoreline Amphitheatre in Mountain View for this year's on May 12-14!

    165 replies 953 proslijeđena tweeta 5.039 korisnika označava da im se sviđa
    Poništi
  19. proslijedio/la je Tweet
    23. sij

    Machine Learning Zero to Hero is now available in Chinese! Join us as we introduce the beginning of our initiative to inform and inspire developers from all around the world. All for ML and ML for all! Learn more here →

    Machine Learning Zero to Hero in Chinese
    1 reply 23 proslijeđena tweeta 60 korisnika označava da im se sviđa
    Poništi
  20. proslijedio/la je Tweet
    23. sij

    Machine learning... learning. – mjesto: Google UK

    4 proslijeđena tweeta 20 korisnika označava da im se sviđa
    Poništi

@device_ai 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:

    ·