I am currently implementing a toy version of the architecture as found in: Deep learning for universal linear embeddings of nonlinear dynamics | Nature Communications , which is effectively an encoder → affine → decoder process. I have already implemented the architecture and have been testing on …

I was referring to the MWE, in which only model.K is used. Incidentally, the gradient there is nothing as well in the MWE because of an interaction between implicit parameters (i.e. the thing you get from params and pass to gradient) and the AD (Zygote). c.f: julia> using Zygote, LinearAlgebra jul…

Flux.jl Inconsistent Training on Custom Architecture

New to Julia

than123 June 22, 2021, 1:47am 3

I see! Will do. Thanks for letting me know.

Topic		Replies	Views
Incorrect (implicit) gradients for a custom model in Flux Machine Learning question , flux	3	456	March 12, 2021
Flux.jl manual training loop results in `error gradent(F, ::Params) are deprecated` New to Julia	2	147	June 16, 2025
Gradients of custom functions with Flux Machine Learning flux	2	1220	April 5, 2020
Lux (And Flux), "parallel" Network Input. When Input is flat, Zygote gradient works, when input is not flat it doesn't Machine Learning flux , zygote , lux	10	746	February 5, 2024
Another error with defining Flux.jl gradients Machine Learning first-steps , flux	5	1688	December 5, 2018

Flux.jl Inconsistent Training on Custom Architecture

Related topics