# NEAT using DL4J?

**URL:** <https://community.konduit.ai/t/neat-using-dl4j/1901>\
**Category:** DL4J\
**Created:** [June 17, 2022, 3:31pm UTC](https://community.konduit.ai/t/neat-using-dl4j/1901 "2022-06-17T15:31:59Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Smurfy98](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/smurfy98/32/763_2.png) [@Smurfy98](https://community.konduit.ai/u/Smurfy98)\
**Post date:** [June 17, 2022, 3:31pm UTC](https://community.konduit.ai/t/neat-using-dl4j/1901/1 "2022-06-17T15:31:59Z")

</div>

I was recently toying around with the idea to use a NEAT neural network. I’d like to implement this in Java using DL4J, but I can’t find anything about NEATs in DL4J. Can someone point me in the right direction?

---

<div class="post-metadata">

**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Post date:** [June 22, 2022, 12:37pm UTC](https://community.konduit.ai/t/neat-using-dl4j/1901/2 "2022-06-22T12:37:31Z")

</div>

@Smurfy98 NEAT would only partially work. It looks like there’s a requirement for an eager mode. We don’t currently have a full eager mode in our graph library but you are welcome to import from tensorflow or pytorch via our model import feature and try it if you’d like.

You can enable that with:

```auto
SameDiff sd = ...importedGraph...;
sd.enableEagerMode();

```

Again though this feature was mainly built for internal purposes initially for our model import but I’d be at least happy to take a look at the use case.