# Flux.jl, treat rows independently

**URL:** <https://discourse.julialang.org/t/flux-jl-treat-rows-independently/28822>\
**Category:** General Usage\
**Tags:** flux\
**Created:** [September 16, 2019, 5:08pm UTC](https://discourse.julialang.org/t/flux-jl-treat-rows-independently/28822 "2019-09-16T17:08:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![modedec](https://avatars.discourse-cdn.com/v4/letter/m/ac8455/32.png) [@modedec](https://discourse.julialang.org/u/modedec)\
**Post date:** [September 16, 2019, 5:08pm UTC](https://discourse.julialang.org/t/flux-jl-treat-rows-independently/28822/1 "2019-09-16T17:08:01Z")

</div>

I would like to train on the rows feature independently. Therefore, I would like to have a dense layer for row 1, row 2 …, row n and at the end combine the 12 row outputs. Is it possible in Flux.jl. At the end I would like to do the same with a CNN. Thx for any clue.

´´´  
x=rand(1000,12,2000)  
Chain(Dense(…))  
´´´