# How to code RealNVP using invertibleNetworks.jl?

**URL:** <https://discourse.julialang.org/t/how-to-code-realnvp-using-invertiblenetworks-jl/114267>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [May 14, 2024, 6:32pm UTC](https://discourse.julialang.org/t/how-to-code-realnvp-using-invertiblenetworks-jl/114267 "2024-05-14T18:32:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![josemanuel22](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/josemanuel22/32/20668_2.png) [@josemanuel22](https://discourse.julialang.org/u/josemanuel22)\
**Post date:** [May 14, 2024, 6:32pm UTC](https://discourse.julialang.org/t/how-to-code-realnvp-using-invertiblenetworks-jl/114267/1 "2024-05-14T18:32:21Z")

</div>

I am using `invertibleNetworks.jl` as a library for normalizing flows. However, the examples included are for the `GLOW` architecture and others, but I would like to use the RealNVP architecture, and I have not been able to do so. Could someone guide me on how to create a RealNVP model using the API provided by `invertibleNetworks.jl`?