• Saturday , 6 June 2020

Machine Learning in JavaScript (TensorFlow Dev Summit 2018)

Code Canyon



Nikhil Thorat and Daniel Smilkov discuss TensorFlow.js, which is TensorFlow’s new machine learning framework for JavaScript developers. It supports building ML models in JavaScript, and training and deploying them in browser for execution using WebGL. They focus on tensorflow.js-Core which is a rebranding of deeplearn.js, and a new high-level layers API to make it easier to develop ML models in JavaScript. Initial set of converters for converting saved TF models into JS is also being released.

Visit the site → https://js.tensorflow.org/
Check out the blog for an article on Machine Learning in JavaScript → https://medium.com/tensorflow/

TensorFlow Dev Summit 2018 All Sessions playlist → https://goo.gl/Lsaq1R
Subscribe to the TensorFlow channel → https://goo.gl/ht3WGe

Original source

3d Ocean

Related Posts

28 Comments

  1. wilwad
    April 18, 2019 at 16:59

    Am struggling to get much for TensorFlow and node JS. Am not much into browser code.
    Right now am looking at 163% CPU running TensorFlow browser demos

  2. Daniyaal Hadzami
    April 18, 2019 at 16:59

    This is awesome. We are now in the future.

  3. Raunak Mitra
    April 18, 2019 at 16:59

    Nikhil, were you in a short film named "The most beautiful thing?"

  4. Juraj Vitko
    April 18, 2019 at 16:59

    Glad the emoticon game didn't show a 💩 :)))

  5. username
    April 18, 2019 at 16:59

    https://pair-code.github.io/deeplearnjs why it does not work anymore
    ?

  6. Andrew Appiah
    April 18, 2019 at 16:59

    These kids are really changing the world. It's amazing!!! Bigup

  7. Thomas Bingel
    April 18, 2019 at 16:59

    Great stuff

  8. Andres Carbo
    April 18, 2019 at 16:59

    Does anyone know where I can find the example from 3:40?

  9. some Guy
    April 18, 2019 at 16:59

    Will there be a windows binding?

  10. Bhaskar Kumar Das
    April 18, 2019 at 16:59

    Wow just can't wait !!!!!!!!!!!!!!!!!!!!!!!!!!!!! because Js is very close to my heart

  11. Aqib Mumtaz
    April 18, 2019 at 16:59

    superb!!

  12. Vadim Bolshakov
    April 18, 2019 at 16:59

    Next up. Brainfuck TensorFlow. C'mon Google! People believe in you

  13. fake Apple Store
    April 18, 2019 at 16:59

    I thought this was an April fool's joke

  14. Juan Pablo Villaseca
    April 18, 2019 at 16:59

    OMFG. AWESOME!

  15. Niels Hoogeveen
    April 18, 2019 at 16:59

    So now I don't need python to code my backend for ML for a web app? I can use this library?

  16. nfcopier1
    April 18, 2019 at 16:59

    Is there an ETA for the Node release?

  17. Sunny D.
    April 18, 2019 at 16:59

    such stuff insipire us to think and create more forward ideas.Tensor flow.js one of that.

  18. Linssen Diocares
    April 18, 2019 at 16:59

    can we use tensorflow.js with php?

  19. Van Lim
    April 18, 2019 at 16:59

    How can you achieve a good prediction in the browser if you need plentiful data to train given a minuscule device memory? Someone might be willing to explain.

  20. Aman Singh
    April 18, 2019 at 16:59

    Hi All!

    I created a small demo app using Tensorflow JS.
    This framework is beautiful!

    visit: https://amansingh.ml

  21. Carpio Erwin John T.
    April 18, 2019 at 16:59

    Hi, tried it on laptop chrome and the emoji app works great. Then I tried it on android chrome (android 5 using latest chrome) but it says that the browser does not support the web app. Any suggestions? or is it the old android version? thanks. #AskTensorFlow

  22. AAAjMMMiRRR
    April 18, 2019 at 16:59

    Who else wants to swear because of the awesomeness here?

  23. Alberto D
    April 18, 2019 at 16:59

    Which NVIDIA GPU is good to start playing with this code?

  24. Sharl Sherif
    April 18, 2019 at 16:59

    Javascript is seriously taking over.

  25. scikick
    April 18, 2019 at 16:59

    After the brief mobile-detour, the world is moving back to web. With progressive apps, and these super interactive real-time apps, I can see using just bookmarks instead of apps on my phone. This looks promising.

  26. ricky singh
    April 18, 2019 at 16:59

    hi i have a object detection model, using tensorflow object detection inception v2.
    cant able to figure out output node name which is required for tensorflow js… any help…

  27. Melroy van den Berg
    April 18, 2019 at 16:59

    wauw nice does it work in NodeJS?

Leave A Comment

You must be logged in to post a comment.