Run WASM, a client side Python runtime

Tensorflow (and by extension Keras) offload most of the actual work to C++ or C, so having those compile to WebAssembly would (I imagine) be a herculean effort.

Instead, The TF team maintains TFJS, which can run on WebAssembly[0].

There are also tractjs[1], and onnyxjs[2], both of which allow you to run (most) ONNX models (which is an open standard for specifying ML models) using WebAssembly and WebGL(only onnyxjs supports WebGL). A bunch of frameworks (caffe, pytorch, TF) support exporting to/importing from ONNX.

[0] https://blog.tensorflow.org/2020/03/introducing-webassembly-...

[1] https://github.com/bminixhofer/tractjs

[2] https://github.com/microsoft/onnxjs

Author here :)

Yeah today it's Pyodide inside React. The long term vision is to have an easy way for folks to embed executable code examples in the browser of many types of languages/frameworks and to make it easy.

TF would be cool but as someone else said, TFJS is a more approachable path for adding it :)