deeplearn.js

deeplearn.js has become TensorFlow.js

We want to point you to the new website for the successor to deeplearn.js. TensorFlow.js picks up where deeplearn.js v0.5 leaves off and adds a whole host of functionality we think you will find really useful.

This site will no longer be updated and will eventually redirect to TensorFlow.js. We will be keeping this site around for a little while to make the transition to TensorFlow.js smoother. Thanks and we hope you will give TensorFlow.js a try!

deeplearn.js is an open-source library that brings performant machine learning building blocks to the web, allowing you to train neural networks in a browser or run pre-trained models in inference mode.

We provide an API that closely mirrors the TensorFlow eager API.

deeplearn.js was originally developed by the Google Brain PAIR team to build powerful interactive machine learning tools for the browser. You can use the library for everything from education, to model understanding, to art projects.

Examples

Getting started

deeplearn.js is an open source hardware-accelerated JavaScript library for machine intelligence. deeplearn.js brings performant machine learning building blocks to the web, allowing you to train neural networks in a browser or run pre-trained models in inference mode.

We provide an API that closely mirrors the TensorFlow eager API. deeplearn.js was originally developed by the Google Brain PAIR team to build powerful interactive machine learning tools for the browser, but it can be used for everything from education, to model understanding, to art projects.

Usage

You can install this library via yarn/npm: yarn add deeplearn or npm install deeplearn

Alternatively you can use a script tag. Here we load it from a CDN. In this case it will be available as a global variable named dl.

You can replace also specify which version to load replacing @latest with a specific version string (e.g. 0.5.0).

<script src="https://cdn.jsdelivr.net/npm/deeplearn@latest"></script>
<!-- or -->
<script src="https://unpkg.com/deeplearn@latest"></script>

TypeScript / ES6 JavaScript

Let’s add a scalar value to a 1D Tensor. Deeplearn js supports broadcasting the value of scalar over all the elements in the tensor.

import * as dl from 'deeplearn'; // If not loading the script as a global

const a = dl.tensor1d([1, 2, 3]);
const b = dl.scalar(2);

const result = a.add(b); // a is not modified, result is a new tensor
result.data().then(data => console.log(data)); // Float32Array([3, 4, 5]

// Alternatively you can use a blocking call to get the data.
// However this might slow your program down if called repeatedly.
console.log(result.dataSync()); // Float32Array([3, 4, 5]

See the TypeScript starter project and the ES6 starter project to get you quickly started.

ES5 JavaScript

Let’s do the same thing in ES5 Javascript. Remember to include the script tag to load deeplearn.js

var a = dl.tensor1d([1, 2, 3]);
var b = dl.scalar(2);

var result = a.add(b); // a is not modified, result is a new tensor

// Option 1: With a Promise.
result.data().then(data => console.log(data)); // Float32Array([3, 4, 5])

// Option 2: Synchronous download of data. Blocks the UI.
console.log(result.dataSync());

Development

To build deeplearn.js from source, we need to clone the project and prepare the dev environment:

$ git clone https://github.com/PAIR-code/deeplearnjs.git
$ cd deeplearnjs
$ yarn prep # Installs dependencies.

Yarn vs NPM

Generally speaking it’s up to you. Yarn is fully interoperable with npm. You can either do yarn or npm install. However we use yarn, and if you are adding or removing dependencies you should use yarn to keep the yarn.lock file up to date.

Code editor

We recommend using Visual Studio Code for development. Make sure to install TSLint VSCode extension and the npm clang-format 1.2.2 or later with the Clang-Format VSCode extension for auto-formatting.

Interactive development

To interactively develop any of the demos (e.g. demos/nn-art/):

$ ./scripts/watch-demo demos/nn-art
>> Starting up http-server, serving ./
>> Available on:
>>   http://127.0.0.1:8080
>> Hit CTRL-C to stop the server
>> 1357589 bytes written to dist/demos/nn-art/bundle.js (0.85 seconds) at 10:34:45 AM

Then visit http://localhost:8080/demos/nn-art/. The watch-demo script monitors for changes of typescript code and does incremental compilation (~200-400ms), so users can have a fast edit-refresh cycle when developing apps.

Testing

Before submitting a pull request, make sure the code passes all the tests and is clean of lint errors:

$ yarn test
$ yarn lint

To run a subset of tests and/or on a specific browser:

$ yarn test --browsers=Chrome --grep='multinomial'
 
> ...
> Chrome 62.0.3202 (Mac OS X 10.12.6): Executed 28 of 1891 (skipped 1863) SUCCESS (6.914 secs / 0.634 secs)

To run the tests once and exit the karma process (helpful on Windows):

$ yarn test --single-run

Packaging (browser and npm)

To build a standalone ES5 library that can be imported in the browser with a <script> tag:

$ ./scripts/build-standalone.sh # Builds standalone library.
>> Stored standalone library at dist/deeplearn(.min).js

To build an npm package:

$ ./scripts/build-npm.sh
...
Stored standalone library at dist/deeplearn(.min).js
deeplearn-VERSION.tgz

To install it locally, run npm install ./deeplearn-VERSION.tgz.

On Windows, use bash (available through git) to use the scripts above.

Looking to contribute, and don’t know where to start? Check out our “help wanted” issues.

Supported environments

deeplearn.js targets environments with WebGL 1.0 or WebGL 2.0. For devices without the OES_texture_float extension, we fall back to fixed precision floats backed by a gl.UNSIGNED_BYTE texture. For platforms without WebGL, we provide CPU fallbacks.

Resources

Thanks

  for providing testing support.

Acknowledgements

deeplearn.js was originally developed by , , and Charles Nicholson.

We would like to acknowledge Chi Zeng, David Farhi, Mahima Pushkarna, Lauren Hannah-Murphy, Minsuk (Brian) Kahng, James Wexler, Martin Wattenberg, Fernanda Viégas, Greg Corrado, Jeff Dean for their tremendous help, and the Google Brain team for providing support for the project.