# Flux.jl: Convolutional VAE throws error after upgrading to 1.4.1/10.4

**URL:** https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746
**Category:** Machine Learning
**Tags:** debugging
**Created:** [May 19, 2020, 10:33am UTC](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746 "2020-05-19T10:33:25Z")
**Posts on this page:** 1
**Showing post:** 18

<div class="post-metadata">

### Author: ![alecokas](https://avatars.discourse-cdn.com/v4/letter/a/b5ac83/32.png) [@alecokas](https://discourse.julialang.org/u/alecokas)
#### Post date: [July 4, 2020, 12:18pm UTC](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746/18 "2020-07-04T12:18:55Z")

</div>

As per the discussion here [here](https://discourse.julialang.org/t/flux-jl-error-thrown-during-gradient-calculation-in-conv-vae/42397/2) with @flo, my problem is now solved. It had to do with package versions in my Julia environment. I needed to downgrade Zygote from v0.4.22 to v0.4.20.

---

_[View the full topic](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746)._
