Fork me on GitHub

ConvNetJS is a Javascript library for training Deep Learning models (Neural Networks) entirely in your browser. Open a tab and you're training. No software requirements, no compilers, no installations, no GPUs, no sweat.

ConvnetJs2 is a successor of ConvNetJS originally created by Karpathy.

However, Karpathy is not actively maintaining ConvNetJS anymore because he don't have time.

I, ccckmit, fork ConvNetJS from github and rename it to ConvNetJs2 as a successor of ConvNetJS.

After that, I modify and modularize the code and add more examples for the ConvNetJs2 project.

You may install the ConvnetJs2 by the following command.

npm i convnetjs2

There are some examples for node.js in the convnetjs2example project.

There is a project for the web demo of ConvNetJs2 that published on

Browser Demos


The library allows you to formulate and solve Neural Networks in Javascript, and was originally written by @karpathy (I am a PhD student at Stanford). However, the library has since been extended by contributions from the community and more are warmly welcome. Current support includes:

Head over to Getting Started for a tutorial that lets you get up and running quickly, and discuss Documentation for all specifics.


The code is available on Github under MIT license and I warmly welcome pull requests for new features / layers / demos and miscellaneous improvements. The library is also available on npm for use in Node.js, under name convnetjs2.