Notes for browser-based machine-learning, for projects like synestizer.
Run Keras models (trained using Tensorflow backend) in your browser, with GPU support. Models are created directly from the Keras JSON-format configuration file, using weights serialized directly from the corresponding HDF5 file.
Tensor operations are extended on top of the ndarray library. GPU support is powered by WebGL through weblas.
hardmaru presents an amazing introduction to running sophisticated neural networks in the browser, targeted at artists
This looks genuinely amazing in terms of functionality and even includes native support for worker threads and concurrency. However… it is lacking modern web wrappings such as npm packaging etc, so is not convenient to use from e.g. webpack.
- mindjs is a simple one where you can see the moving parts.