A Journey into the World of Machine Learning with TensorFlow.js
summary
Shows a hands-on TensorFlow.js workflow: converts or trains models in-browser with WebGL/node backends, cites 1.4M npm installs and 10M CDN hits, benchmarks MobileNet inference ~20 ms on laptops and ~22 ms on iPhone X, server CPU ~23 ms and GPU ~9 ms. Builds a convolutional MNIST digit classifier in Angular 9+, trains with up to 40 epochs, reports 25-epoch results (digit 9: 100% on 43 samples; digit 3: 89% on 54), and demos working live inference.
AI-written summary · about
chapters (6)
- 0:00Start
- 14:40Load Data
- 15:21Build Model
- 16:40Compile Model
- 17:43Model Training
- 19:03Step 4: Make prediction
related talks
48mTensorFlow.js
20mTensorFlow.js Bringing Machine Learning to the Web and Beyond
31mIntroduction to Machine Learning in Tensorflow.js
37mTensorFlow.js - Bringing ML and Linear Algebra to Node.js
32mUsing Machine Learning Models in JavaScript Application
41mTensorFlow.js 101: ML in the Browser and Beyond
28mMachine Learning on the web with TensorFlow.js
34mA Powerful Introduction to Machine Learning with Js