Erkaman/regl-cnn
Digit recognition with Convolutional Neural Networks in WebGL
This project helps developers evaluate Convolutional Neural Networks directly in a web browser using WebGL. It takes a pre-trained digit recognition model and allows for real-time processing of handwritten digits on the GPU, without needing a server. It is ideal for web developers and researchers experimenting with client-side deep learning applications.
511 stars. No commits in the last 6 months.
Use this if you are a web developer or researcher looking to implement and test deep learning models, specifically for digit recognition, directly within a web browser for faster, client-side execution.
Not ideal if you need to train deep learning models, require state-of-the-art performance for complex networks, or are working outside of a web browser environment.
Stars
511
Forks
63
Language
JavaScript
License
MIT
Category
Last pushed
Aug 17, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Erkaman/regl-cnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hoffhannisyan/handwritten-digit-recognition
✨ Draw handwritten digits and get instant AI predictions! Neural network implemented in pure...
lifeparticle/Bengali-Alphabet
✍️ Bengali Alphabet (বাংলা বর্ণমালা)
bensonruan/Hand-Written-Digit-Recognition
Hand Written Digit Recognition
Gogul09/digit-recognizer-live
Recognize Digits using Deep Neural Networks in Google Chrome live!
minhazkamal/Arabic-Handwritten-Character-and-Digit-Recognition
A simple webapplication for Arabic Handwritten Character recognition. Users can write Arabic...