I am implementing a neural network using Lux and Reactant + Enzyme. At each epoch, I need to resample the data, divide it in batches, and take a training step. For now, I am working on a CPU. What is the best way to do this efficiently? A MWE of my current implementation is the following. I first d…

Loading resampled data for PINN in Reactant + Enzyme + Lux

yolhan_mannes June 17, 2025, 6:02pm 2

you could compile the whole dataloader loop which I’m pretty sure Lux has a method for, also pay attention to FAQs | Reactant.jl especially the gc part you may need it

Topic		Replies	Views
Flux: Hard to use train! and DataLoader for minibatched NamedTuple dataset with GPU Machine Learning flux	2	1451	September 24, 2020
Have no idea how to train neural networks using sampled data from distributions New to Julia question , flux , distributions	2	448	November 26, 2020
Generic Function to train NN w/ Flux Machine Learning flux	7	1668	April 14, 2020
Training FLUX models with larger datasets Machine Learning cuda , flux	4	1542	April 7, 2022
Two questions on Flux Machine Learning	23	4856	October 2, 2020

Loading resampled data for PINN in Reactant + Enzyme + Lux

Related topics