# Implementing Crystal Graph CNN in Julia

**URL:** https://discourse.julialang.org/t/implementing-crystal-graph-cnn-in-julia/33169
**Category:** Machine Learning
**Tags:** question, lightgraphs, flux
**Created:** [January 9, 2020, 9:44pm UTC](https://discourse.julialang.org/t/implementing-crystal-graph-cnn-in-julia/33169 "2020-01-09T21:44:11Z")
**Posts on this page:** 1
**Showing post:** 3

<div class="post-metadata">

### Author: ![rkurchin](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/rkurchin/32/16039_2.png) [@rkurchin](https://discourse.julialang.org/u/rkurchin)
#### Post date: [January 13, 2020, 4:43pm UTC](https://discourse.julialang.org/t/implementing-crystal-graph-cnn-in-julia/33169/3 "2020-01-13T16:43:41Z")

</div>

Thanks, this is all really useful perspective! The analogy to one-hot encoding makes perfect sense.

And yes, I was definitely planning on having a “modular” featurization scheme; I’m certainly keen to explore which atomic features actually matter in the first place as well as play with binning densities and other meta-, hyper-, etc.- parameters 😃

---

_[View the full topic](https://discourse.julialang.org/t/implementing-crystal-graph-cnn-in-julia/33169)._