https://github.com/blinkdl/blinkdl

A minimalist deep learning library in Javascript using WebGL + asm.js. Run convolutional neural network in your browser.
https://github.com/blinkdl/blinkdl

alphago deep-learning deep-neural-networks deeplearning neural-network neural-networks

Last synced: 21 days ago
JSON representation

A minimalist deep learning library in Javascript using WebGL + asm.js. Run convolutional neural network in your browser.

• Host: GitHub
• URL: https://github.com/blinkdl/blinkdl
• Owner: BlinkDL
• License: apache-2.0
• Created: 2017-11-19T16:30:44.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-11-21T11:43:00.000Z (over 7 years ago)
• Last Synced: 2025-03-30T13:51:16.192Z (about 2 months ago)
• Topics: alphago, deep-learning, deep-neural-networks, deeplearning, neural-network, neural-networks
• Language: JavaScript
• Homepage:
• Size: 6.27 MB
• Stars: 84
• Watchers: 8
• Forks: 19
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# BlinkDL

A minimalist deep learning library in Javascript using WebGL + asm.js. Runs in your browser. 

Currently it is a proof-of-concept (inference only). Note: Convolution is buggy when memories overlap.

The WebGL backend is powered by weblas: https://github.com/waylonflinn/weblas.

## Example

https://withablink.coding.me/goPolicyNet/ : a weiqi (baduk, go) policy network in AlphaGo style:



    const N = 19;

    const NN = N * N;

    const nFeaturePlane = 8;

    const nFilter = 128;

    const x = new BlinkArray();

    x.Init('weblas');

    x.nChannel = nFeaturePlane;

    x.data = new Float32Array(nFeaturePlane * NN);

    for (var i = 0; i < NN; i++)

        x.data[5 * NN + i] = 1; // set feature plane for empty board

    

    // pre-act residual network with 6 residual blocks

    const bak = new Float32Array(nFilter * NN);

    x.Convolution(nFilter, 3);

    x.CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak).CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak).CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak).CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak).CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak).CopyTo(bak);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.BatchNorm().ReLU().Convolution(nFilter, 3);

    x.Add(bak);

    x.BatchNorm().ReLU().Convolution(1, 1).Softmax();



    

## Usage

    

    

 

## Todo

- [x] Convolution (3x3_pad_1 and 1x1), BatchNorm, ReLU, Softmax

- [ ] Pooling layer

- [ ] FC layer

- [ ] Strided convolution

- [ ] Transposed convolution

- [ ] Webworker and async

- [ ] Faster inference with weblas pipeline, WebGPU, WebAssembly

- [ ] Memory manager

- [ ] Training