# Yolo2OutputLayer for 3D

**URL:** <https://community.konduit.ai/t/yolo2outputlayer-for-3d/1869>\
**Category:** DL4J\
**Created:** [May 18, 2022, 11:49am UTC](https://community.konduit.ai/t/yolo2outputlayer-for-3d/1869 "2022-05-18T11:49:32Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Booker](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/booker/32/987_2.png) [@Booker](https://community.konduit.ai/u/Booker)\
**Post date:** [May 18, 2022, 11:49am UTC](https://community.konduit.ai/t/yolo2outputlayer-for-3d/1869/1 "2022-05-18T11:49:32Z")

</div>

Should I implement Yolo2Output3DLayer by referring Yolo2OutputLayer or implement a SameDiff op to do Yolo2 operation for 3D input? Thanks.

---

<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:** [May 18, 2022, 12:29pm UTC](https://community.konduit.ai/t/yolo2outputlayer-for-3d/1869/2 "2022-05-18T12:29:31Z")

</div>

@Booker I would use samediff + a samediff layer for that. Otherwise you have to hand derive the gradients for the backward op yourself. Try to use the samediff namespace ops like:

```auto
SameDiff sd = SameDiff.create();
sd.nn().conv2d(..)
sd.image().

```

to set everything up. If you see anything missing please do let us know.