# Single number and array as input in Flux model
**URL:** https://discourse.julialang.org/t/single-number-and-array-as-input-in-flux-model/54986
**Category:** Machine Learning
**Created:** [February 10, 2021, 12:04pm UTC](https://discourse.julialang.org/t/single-number-and-array-as-input-in-flux-model/54986 "2021-02-10T12:04:27Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@anon74562486](https://discourse.julialang.org/u/anon74562486)
#### Post date: [February 10, 2021, 12:04pm UTC](https://discourse.julialang.org/t/single-number-and-array-as-input-in-flux-model/54986/1 "2021-02-10T12:04:27Z")
Suppose I have a Flux simple model like this:
```julia
model = Dense(1, 10)
```
If I try to call this model with a single number I get an error:
```julia
model(0.3) # ERROR
```
However If I do this the model works correctly:
```julia
model([0.3])
```
Do I always have to convert the number into an array?
Is there a more elegant way to do this?
How can I call the model on an array or on a matrix? (I want to call the model on every single number of the array)
This doesn’t works with single numbers:
```julia
my_model(x) = reshape(reshape(x, (1, length(x))) |> model, size(x))
```
Thank you and sorry for my english
---
### Author:  [@DeepQ](https://discourse.julialang.org/u/DeepQ)
#### Post date: [February 10, 2021, 3:50pm UTC](https://discourse.julialang.org/t/single-number-and-array-as-input-in-flux-model/54986/2 "2021-02-10T15:50:44Z")
A neural network is a combination of some matrices and vectors. So every input is an array and not a number.