# Working with CSV of MNIST sign language in Julia deep learning

**URL:** https://discourse.julialang.org/t/working-with-csv-of-mnist-sign-language-in-julia-deep-learning/41152
**Category:** New to Julia
**Created:** [June 10, 2020, 5:41pm UTC](https://discourse.julialang.org/t/working-with-csv-of-mnist-sign-language-in-julia-deep-learning/41152 "2020-06-10T17:41:07Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![Asia087](https://avatars.discourse-cdn.com/v4/letter/a/47e85d/32.png) [@Asia087](https://discourse.julialang.org/u/Asia087)
#### Post date: [June 10, 2020, 5:41pm UTC](https://discourse.julialang.org/t/working-with-csv-of-mnist-sign-language-in-julia-deep-learning/41152/1 "2020-06-10T17:41:08Z")

</div>

Hello,  
I am trying to make a convolusional neural network on MNISt sign language dataset. It si provided in a CSV format where each row is one picture and there are 784 columns refering to a single pixel (the pictures have a size 28x28).  
My problem is that in order to perform the algorithm I need to transpose my data to a different format, the same as is the format of a built-in ML dataset fashion MNIST, which is:

Array{Array{ColorTypes.Gray{FixedPointNumbers.Normed{UInt8,8}},2},1}.

I would like to end up with the following format, where my data is joined with the encoded labels:

Array{Tuple{Array{Float32,4},Flux.OneHotMatrix{Array{Flux.OneHotVector,1}}},1}:

I was trying to use reshape function to convert it to a 4-domensional array, but all I get is:  
7172×28×28×1 Array{Float64,4}.

My labels are in the following (correct) format:  
25×7172 Flux.OneHotMatrix{Array{Flux.OneHotVector,1}}:

I am new to Julia and some of the code I am using has been written by someone else.  
I would appreciate your explanation of the format and please feel free to tell me if I haven’t put all the necessary information.