Optimiser
struct
defined in module
Flux.Optimise
Optimiser(a, b, c...)
Combine several optimisers into one; each optimiser produces a modified gradient that will be fed into the next, and this is finally applied to the parameter as usual.
This will be replaced by
Optimisers.OptimiserChain
in Flux 0.14.
There are
2
methods for Flux.Optimise.Optimiser
:
The following pages link back here:
FastAI.jl , training/discriminativelrs.jl , training/finetune.jl , training/onecycle.jl , deprecations.jl , optimise/Optimise.jl , optimise/optimisers.jl