I am writing a training program for the VAEAC model, but when I use Optimisers.Adam(lr), I get an error. When I use, for example, Optimisers.Descent(lr), this problem does not occur. Error message: ERROR: MethodError: no method matching Float32(::Reactant.TracedRNumber{Float32}) The type `Float32`…

Thank you for your desire to help. The problem was solved by clearing all packages and downloading all project dependencies again.

Reactant.jl and Lux.jl don't work with Adam optimiser

avikpal September 25, 2025, 5:24am 7

This is different from the above case. Updates11 · grero/RecurrentNetworkModels.jl@7ce9e3d · GitHub the rng type being carried around is not compatible with reactant. use Random.default_rng()

Topic		Replies	Views
ADAM optimizer error in Flux Machine Learning	1	1727	February 19, 2019
sciML_train func running but not optimizing New to Julia diffeq , flux , optimization , sciml	5	560	April 14, 2021
[blog post] Implement your own AD with Julia in ONE day Community blog-post	33	4378	November 3, 2018
Flux differentiation error Machine Learning zygote	19	1735	November 19, 2020
Generic Function to train NN w/ Flux Machine Learning flux	7	1666	April 14, 2020