Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Run Keras models in the browser, with GPU support using WebGL
| Date | Stars |
|---|---|
| 2026-07-24 | 4964 |
| 2026-07-25 | 4964 |
| 2026-07-28 | 4964 |
| 2026-07-30 | 4964 |
| 2026-08-06 | 4964 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<strong>**This project is no longer active. Please check out <a href="http://js.tensorflow.org">TensorFlow.js</a>.**<br/>The <a href="https://transcranial.github.io/keras-js">Keras.js demos</a> still work but is no longer updated.</strong>
</p>
<p align="center">
<a href="https://transcranial.github.io/keras-js">
<img src="https://cdn.rawgit.com/transcranial/keras-js/73aa4cca/assets/logo.svg" width="300px" />
</a>
</p>
<p align="center">
<strong>Run Keras models in the browser, with GPU support using WebGL</strong>
</p>
<div align="center">
<h3>
<a href="https://transcranial.github.io/keras-js">Interactive Demos</a>
<span> | </span>
<a href="https://transcranial.github.io/keras-js-docs">Documentation</a>
</h3>
</div>
<br/>
---
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)
<p align="center">
<a href="https://transcranial.github.io/keras-js"><img src="demos/assets/mnist-cnn.png" height="120" width="auto" /></a>
<a href="https://transcranial.github.io/keras-js"><img src="demos/assets/resnet50.png" height="120" width="auto" /></a>
<a href="https://transcranial.github.io/keras-js"><img src="demos/assets/inception-v3.png" height="120" width="auto" /></a>
<a href="https://transcranial.github.io/keras-js"><img src="demos/assets/imdb-bidirectional-lstm.png" height="120" width="auto" /></a>
</p>
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)
Excerpt of 2,337 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:020475a311c0f139, topic:deep-learning, topic:tensorflow
