Elegant & Performant Scientific Machine Learning in Julia

Documentation with Documenter.jl and VitePress

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

Weight Initialization Schemes for Deep Learning Frameworks

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.

Backend for Lux.jl

Trigger Package for AMDGPU Support in Lux.jl

Trigger Package for CUDA Support in Lux.jl

Data Transfer Functionalities across Backends for Machine Learning Applications

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