In this codelab, you will learn how to build a simple "teachable machine", a custom image classifier that you will train on the fly in the browser using TensorFlow.js, a powerful and flexible machine learning library for Javascript. You will first load and run a popular pre-trained model called MobileNet for image classification in the browser. You will then use a technique called "transfer learning", which bootstraps our training with the pre-trained MobileNet model and customizes it to train for your application.
This demo shows the blazeface model detecting faces in a live camera feed. The demo renders a semi-transparent red box over faces, and blue dots over facial landmarks (eyes, ears, nose, and mouth).
This tutorial demonstrates how to generate images of handwritten digits using a Deep Convolutional Generative Adversarial Network (DCGAN). The code is written using the Keras Sequential API with a tf.GradientTape training loop.
Install TensorFlow 2
tensorflow/tfjs-models: Pretrained models for TensorFlow.js
TensorFlow.js Transfer Learning Image Classifier
TensorFlow.js models
blazeface demo
tensorflow/tfjs: A WebGL accelerated JavaScript library for training and deploying ML models.
Deep Convolutional Generative Adversarial Network | TensorFlow Core
Use face-api.js on node js