---
title: "Comment by Julian Neagu on \"High Level Neural Network Modeling with Flax\" | Hashnode"
description: "The init and apply split is probably the part that clicked for me most. Keeping model structure separate from the actual weights feels much cleaner. Especially"
url: "https://hashnode.com/posts/high-level-neural-network-modeling-with-flax/6a8626026572584351d689f0/comment/6a86f75232254c1d143eedf1"
---

[Discussion](https://hashnode.com/posts/high-level-neural-network-modeling-with-flax/6a8626026572584351d689f0)

Comment [High Level Neural Network Modeling with Flax](https://hashnode.com/posts/high-level-neural-network-modeling-with-flax/6a8626026572584351d689f0)

[Julian Neagu](https://hashnode.com/@julianneagulab)

[Aug 20](https://hashnode.com/posts/high-level-neural-network-modeling-with-flax/6a8626026572584351d689f0/comment/6a86f75232254c1d143eedf1)

The `init` and `apply` split is probably the part that clicked for me most. Keeping model structure separate from the actual weights feels much cleaner. Especially when you start adding dropout and batch stats.
