Elegant and Performant Scientific Machine Learning in Julia

Accelerate your ML research using pre-built Deep Learning Models with Lux

Documentation with Documenter.jl and VitePress

Data Transfer Functionalities across Backends for Machine Learning Applications

Backend for Lux.jl

Collection of Functions useful for testing various packages in the Lux Ecosystem

LuxCore.jl defines the abstract layers for Lux. Allows users to be compatible with the entirely of Lux.jl without having such a heavy dependency.

Weight Initialization Schemes for Deep Learning Frameworks

Routines for batching regular code and make them fast!

Trigger Package for CUDA Support in Lux.jl