Elegant easy-to-use neural networks in JAX
JAX library for neural networks and PyTree manipulations. Equinox is a JAX library that provides everything you need that isn't already in core JAX: - neural networks (or more generally any model), with easy-to-use PyTorch-like syntax; - filtered APIs for transformations; - useful PyTree manipulation routines; - advanced features like runtime errors; Equinox isn't a framework: everything you write in Equinox is compatible with anything else in JAX or the ecosystem.
$
pkg install py311-equinoxOrigin
misc/py-equinox
Size
1.92MiB
License
APACHE20
Maintainer
yuri@FreeBSD.org
Dependencies
5 packages
Required by
0 packages