Machine learning for next gen web apps with TensorFlow.js
summary
Library updates and concrete wins: 3.2M NPM downloads with ~50M CDN hits and 12.5k GitHub dependents; Face Mesh adds iris tracking; new pose models MoveNet (17 keypoints) and BlazePose (33 keypoints); TensorFlow Lite runs in the browser; WebAssembly gains SIMD and multi‑threading and outperforms WebGL on some CPUs (face detector >2× faster on a 2019 MacBook Pro). Live demos show real‑time toxicity filtering, physiotherapy pose estimation, sign language recognition, and Magenta tone transfer all running successfully in-browser.
AI-written summary · about
chapters (11)
- 0:00Start
- 0:15What Is Tensorflow Js and How Are People Using It Today
- 4:09Sign Language Gestures
- 4:56What's New for 2021 with Tensorflow Js
- 5:29Model Updates
- 5:53Pose Estimation Models
- 6:39Conversation Intent Detection
- 7:43Question and Answer Model
- 10:45Tensorflow Lite Models in Tensorflow
- 10:57Tf Lite Task Library
- 13:07Inspiration
related talks
29mSuperpowers for next gen web apps: Machine learning
20mTensorFlow.js Bringing Machine Learning to the Web and Beyond
41mTensorFlow.js 101: ML in the Browser and Beyond
39mMachine Learning Magic for Your JavaScript Application
21mMachine Learning & JS Take your PWA to the next level
15mThe future of machine learning using JavaScript
35mThe Future of JavaScript & Machine Learning
54mDeep Learning in JS