Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Try writing anything other than ML in pytorch. You can't?

Of course you can! It's a library of vectorized math operations. You don't need to do gradient descent on the graph either.



I tried that, tensorflow is actually better for general purpose compute, jax a lot better. Pytorch seems to omit most of the non-ml basic building blocks, while tf kind of gives you most of the XLA api.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: