https://github.com/transcranial/keras-js

Run Keras models in the browser, with GPU support using WebGL
https://github.com/transcranial/keras-js

deep-learning javascript keras machine-learning neural-networks tensorflow webgl

Last synced: 2 days ago
JSON representation

Run Keras models in the browser, with GPU support using WebGL

• Host: GitHub
• URL: https://github.com/transcranial/keras-js
• Owner: transcranial
• License: mit
• Created: 2016-09-30T14:40:35.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2022-06-15T12:11:24.000Z (over 2 years ago)
• Last Synced: 2024-12-04T14:00:11.484Z (9 days ago)
• Topics: deep-learning, javascript, keras, machine-learning, neural-networks, tensorflow, webgl
• Language: JavaScript
• Homepage: https://transcranial.github.io/keras-js
• Size: 17.2 MB
• Stars: 4,962
• Watchers: 179
• Forks: 501
• Open Issues: 81
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow - keras-js - Run Keras models (tensorflow backend) in the browser, with GPU support (Libraries)
• awesome-github-star - keras-js
• Awesome-TensorFlow-Chinese - keras-js - Run Keras models (tensorflow backend) in the browser, with GPU support (库 / 微信群)
• awesome-tensorflow - keras-js - Run Keras models (tensorflow backend) in the browser, with GPU support (Libraries)
• fucking-awesome-tensorflow - keras-js - Run Keras models (tensorflow backend) in the browser, with GPU support (Libraries)

README

        


  **This project is no longer active. Please check out TensorFlow.js.**
The Keras.js demos still work but is no longer updated.





  

    

  





  Run Keras models in the browser, with GPU support using WebGL





  


    Interactive Demos

     | 

    Documentation

  






---

Run [Keras](https://github.com/keras-team/keras) models in the browser, with GPU support provided by WebGL 2. Models can be run in Node.js as well, but only in CPU mode. Because Keras abstracts away a number of frameworks as backends, the models can be trained in any backend, including TensorFlow, CNTK, etc.

Library version compatibility: Keras 2.1.2

## [Interactive Demos](https://transcranial.github.io/keras-js)



  

  

  

  



Check out the `demos/` directory for real examples running Keras.js in VueJS.

- Basic Convnet for MNIST

- Convolutional Variational Autoencoder, trained on MNIST

- Auxiliary Classifier Generative Adversarial Networks (AC-GAN) on MNIST

- 50-layer Residual Network, trained on ImageNet

- Inception v3, trained on ImageNet

- DenseNet-121, trained on ImageNet

- SqueezeNet v1.1, trained on ImageNet

- Bidirectional LSTM for IMDB sentiment classification

## [Documentation](https://transcranial.github.io/keras-js-docs)

[MIT License](https://github.com/transcranial/keras-js/blob/master/LICENSE)