On: Deep Learning in JavaScript

[ralusek]

Many people seem to be unaware of tensorflow.js, an official JS implementation of TF

https://github.com/tensorflow/tfjs

I'd love to see PyTorch in JS, but I think unless you get it running on the GPU it won't be able to do much.

[ipsum2 → ralusek]

tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browser using webassembly/webGL (and nodejs if you wanted to, but why?).

[fire_lake → ipsum2]

> nodejs if you wanted to, but why?

Node.js is better backend than something like Flask.

[ipsum2 → fire_lake]

Performance is a lot worse on NodeJS with a WebAssembly/WebGL backend versus Flask with a PyTorch/CUDA backend.

[throwaway4aday → ipsum2]

If you're using Node you can write whatever you want in C++ and then add a binding to call it from within your Node app. Don't need WebGL.

[goatlover → throwaway4aday]

But you're having to write whatever in C++ versus just using Flask/Pytorch.

[throwaway4aday → goatlover]

A lot of what you need is already written, you just need to find the right libraries and write the bindings. From my encounters with Python ML it seems like "just use Pytorch" is a bit like "simply walk into Mordor".

[ipsum2 → throwaway4aday]

Yeah, but why...?

[eduardoleao052 → ralusek]

Adding GPU support soon is absolutely my goal in the future! I think a PyTorch-based JavaScript library could be useful, as PyTorch has been way more dominant than TensorFlow recently.

[richrichie → ralusek]

With PyTorch dominating the landscape, my guess was that tf will resurrect itself through tfjs. Seems may not.

[jsight → ralusek]

I had the same thought, but it does seem that tensorflow usage is in steady decline.