woudsma/retrain-mobilenet-for-the-web
Retrain a MobileNet V1 or V2 model and use it in the browser with TensorFlow.js
This project helps web developers quickly build and deploy custom image classification models directly into web browsers. You provide your own image dataset, train a MobileNet model (which is optimized for mobile devices and web use), and then integrate that model into a web application. This is ideal for developers creating interactive web experiences that require on-device image analysis.
No commits in the last 6 months.
Use this if you need to perform image classification directly within a web browser using your own custom categories, without sending images to a server.
Not ideal if you need to train extremely large or complex models, or if you don't intend to deploy your image classification feature on the web.
Stars
22
Forks
12
Language
JavaScript
License
—
Category
Last pushed
Nov 06, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/woudsma/retrain-mobilenet-for-the-web"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ntedgi/node-efficientnet
tensorflowJS implementation of EfficientNet 🚀
SashiDo/teachablemachine-node
Using Teachable Machine Models in Node.js
thekevinscott/ml-classifier
A tool for quickly training image classifiers in the browser
thekevinscott/ml-classifier-ui
A UI tool for quickly training image classifiers in the browser
fastai/tinypets
Minimal JS interface to an image classifer