Thanks! Just to be clear, this is an early access of the book. The book is still work in progress. We'd love to hear feedback from readers like you on how we can make the book better :)
Today we're releasing a new blog illustrating how our autonomous vehicle uses computer vision to see the world 👀 Including a new web demo which allows you to try our algorithm on your own images! wayve.ai/blog/2018/10/8/visi…
We added an overview table to tfjs-examples, so you can find the examples of interest to you faster. It summarizes the ML problems, dataset types, model types, APIs, etc. that are covered so far.
Stay tuned as this repo expands further! #tensorflowjs ↓
github.com/tensorflow/tfjs-e…
I just open-sourced a project here at Google!
Here is a headless WebGL/OpenGL ES binding for #NodeJS - powered by ANGLE. WebGL shaders are translated to native hardware for acceleration. Future run-time option for #tensorflowjs...
github.com/google/node-gles@TensorFlow@GoogleOSS
With colab, @github and @TensorFlow.js you can train, convert and deploy a model super fast. All of this in just one notebook and solely in the browser. No GPU setup, no server for running the model on the browser.
colab.research.google.com/dr…
We are excited to announce tfjs-vis, a browser based visualization library for TensorFlow.js. It has charts to let you see the data flowing through your model, and a convenient hide-able drawer to put them in while developing your apps.
Check it out → bitly.com/2R6XeZu
We recently released TensorFlow.js v0.13 which contains significant performance improvements, complex64 dtypes, a new profiling API tf.profile, new ops, precision / recall metrics to the layers API, and much more!
Release notes here: github.com/tensorflow/tfjs/r…