# Reshaping outputs between layers in Flux.jl
**URL:** https://discourse.julialang.org/t/reshaping-outputs-between-layers-in-flux-jl/17838
**Category:** Machine Learning
**Created:** [November 22, 2018, 12:44am UTC](https://discourse.julialang.org/t/reshaping-outputs-between-layers-in-flux-jl/17838 "2018-11-22T00:44:08Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@Rademcaher](https://discourse.julialang.org/u/Rademcaher)
#### Post date: [November 22, 2018, 12:44am UTC](https://discourse.julialang.org/t/reshaping-outputs-between-layers-in-flux-jl/17838/1 "2018-11-22T00:44:08Z")
The input to my network are N x 2 arrays and I’d like to implement a Dense layer, followed by a convolution. This requires reshaping the output of the dense layer. The forward pass seems to work fine, but I think there’s an error on the backprop somewhere. Any help is appreciated.
```julia
m = Chain(
Dense(N, N, relu),
x -> reshape(x, N, 1, 2, 1),
Conv((2,1), 2=>1, relu),
x -> x[:],
Dense(N-1, N, relu)) |> gpu
m(train[1][1])
loss(x, y) = Flux.mse(m(x), y)
```
This is the error, some kind of dimension mismatch?:
```julia
MethodError: no method matching *(::TrackedArray{…,CuArray{Float32,2}}, ::CuArray{Float32,3})
Closest candidates are:
*(::Any, ::Any, !Matched::Any, !Matched::Any...) at operators.jl:502
```
---
### Author:  [@y4lu](https://discourse.julialang.org/u/y4lu)
#### Post date: [November 22, 2018, 1:02am UTC](https://discourse.julialang.org/t/reshaping-outputs-between-layers-in-flux-jl/17838/2 "2018-11-22T01:02:41Z")
Probably a type mismatch, multiply isn’t currently implemented between types (CuArray, Tracked{CuArray}) is basically what it’s telling us
See the first example here [http://fluxml.ai/Flux.jl/stable/training/optimisers.html](http://fluxml.ai/Flux.jl/stable/training/optimisers.html) for tracking a gradient
Making y a flux param will probably work