Hacker News Reader

What is relevant now?

PyTorch has the nicest debugging experience. JAX is supposed to be powerful too, but I'm skeptical of its static graph which is what made TensorFlow such a chore. I'm whishful about Mojo, in theory it sounds great.

On the contrary, that's why I find Keras 3 interesting (although I don't see myself switching anytime soon). It supports both PyTorch and JAX, and Keras Core models/layers can be used interchangeably with PyTorch modules: https://twitter.com/fchollet/status/1697020631752298982

I use keras for CV but for DL at work, we started moving towards pytorch and closely following modular.

Reply on news.ycombinator.com