# DL4J Classification Speed

**URL:** <https://community.konduit.ai/t/dl4j-classification-speed/187>\
**Category:** DL4J\
**Created:** [February 27, 2020, 3:56pm UTC](https://community.konduit.ai/t/dl4j-classification-speed/187 "2020-02-27T15:56:39Z")\
**Posts on this page:** 2\
**Page:** 2

<div class="post-metadata">

**Author:** ![treo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/treo/32/47_2.png) [@treo](https://community.konduit.ai/u/treo)\
**Post date:** [March 9, 2020, 8:51pm UTC](https://community.konduit.ai/t/dl4j-classification-speed/187/21 "2020-03-09T20:51:05Z")

</div>

`networkOutput` is a 10000x2 tensor, giving you all of those values. `argMax` would give you a 10000x1 array, telling you if it was the first or the second option that was the larger one. If you finally want to have a `double[10000]` array, all you need to do is call `toDoubleVector` on the result.

Or if you still aren’t convinced about the `argMax` thing, you might want to call `toDoubleMatrix` on it to get back your `double[10000][2]`.

(There are also variants of it for Float and Int)

---

<div class="post-metadata">

**Author:** ![torstenbm](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/torstenbm/32/101_2.png) [@torstenbm](https://community.konduit.ai/u/torstenbm)\
**Post date:** [March 9, 2020, 8:52pm UTC](https://community.konduit.ai/t/dl4j-classification-speed/187/22 "2020-03-09T20:52:20Z")

</div>

Well then it turn’s out [argMax](https://deeplearning4j.org/api/latest/org/nd4j/linalg/api/ndarray/INDArray.html#argMax-int...-) is exactly what I’m looking for, thank you so much!

[Previous page](https://community.konduit.ai/t/dl4j-classification-speed/187.md?page=1)