SciML/DeepEquilibriumNetworks.jl

This is stars and forks stats for /SciML/DeepEquilibriumNetworks.jl repository. As of 08 May, 2024 this repository has 43 stars and 5 forks.

DeepEquilibriumNetworks DeepEquilibriumNetworks.jl is a framework built on top of DifferentialEquations.jl and Lux.jl enabling the efficient training and inference for Deep Equilibrium Networks (Infinitely Deep Neural Networks). Installation using Pkg Pkg.add("DeepEquilibriumNetworks") Quickstart import DeepEquilibriumNetworks as DEQs import Lux import Random import Zygote seed = 0 rng = Random.default_rng() Random.seed!(rng, seed) model = Lux.Chain(Lux.Dense(2, 2), DEQs.DeepEquilibriumNetwork(Lux.Parallel(+, ...