# Flux.jl: Convolutional VAE throws error after upgrading to 1.4.1/10.4

**URL:** <https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746>\
**Category:** Machine Learning\
**Tags:** debugging\
**Created:** [May 19, 2020, 10:33am UTC](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746 "2020-05-19T10:33:25Z")\
**Posts on this page:** 1\
**Showing post:** 15

<div class="post-metadata">

**Author:** ![alecokas](https://avatars.discourse-cdn.com/v4/letter/a/b5ac83/32.png) [@alecokas](https://discourse.julialang.org/u/alecokas)\
**Post date:** [July 4, 2020, 10:34am UTC](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746/15 "2020-07-04T10:34:22Z")

</div>

I have been unable to get the code snippet provided by @contradict to work (with the same 1.4.1/10.4 setup). What further debugging did you need to do to have the code run @flo?

When I leave the `Float32` as is in `dummy_data()` I get:

```julia
ERROR: LoadError: MethodError: no method matching ∇maxpool(::Array{Float64,4}, ::Array{Float32,4}, ::Array{Float32,4}, ::PoolDims{2,(8, 8),(4, 4),(2, 2, 2, 2),(1, 1)})
Closest candidates are:
  ∇maxpool(::AbstractArray{T,N}, !Matched::AbstractArray{T,N}, !Matched::AbstractArray{T,N}, ::PoolDims; kwargs...) where {T, N} at /home/aleco/.julia/packages/NNlib/FAI3o/src/pooling.jl:123
....

```

and when I change it to `Float64` I get:

```julia
ERROR: LoadError: UndefRefError: access to undefined reference
Stacktrace:
 [1] getindex at ./array.jl:789 [inlined]
 [2] conv_direct!(::Array{AbstractFloat,5}, ::Array{AbstractFloat,5}, ::Array{Float32,5}, ::NNlib.DenseConvDims{3,(8, 8, 1),4,4,(4, 4, 1),(2, 2, 2, 2, 0, 0),(1, 1, 1),false}; alpha::Float64, beta::Bool) at /home/aleco/.julia/packages/NNlib/FAI3o/src/impl/conv_direct.jl:98
 [3] conv_direct! at /home/aleco/.julia/packages/NNlib/FAI3o/src/impl/conv_direct.jl:51 [inlined]
 [4] conv!(::Array{AbstractFloat,5}, ::Array{AbstractFloat,5}, ::Array{Float32,5}, ::NNlib.DenseConvDims{3,(8, 8, 1),4,4,(4, 4, 1),(2, 2, 2, 2, 0, 0),(1, 1, 1),false}; kwargs::Base.Iterators.Pairs{Union{},Union{},Tuple{},NamedTuple{(),Tuple{}}}) at /home/aleco/.julia/packages/NNlib/FAI3o/src/conv.jl:99
 [5] conv!(::Array{AbstractFloat,5}, ::Array{AbstractFloat,5}, ::Array{Float32,5}, ::NNlib.DenseConvDims{3,(8, 8, 1),4,4,(4, 4, 1),(2, 2, 2, 2, 0, 0),(1, 1, 1),false}) at /home/aleco/.julia/packages/NNlib/FAI3o/src/conv.jl:97
...

```

Any further assistance from anyone in the thread would be greatly appreciated:)

---

_[View the full topic](https://discourse.julialang.org/t/flux-jl-convolutional-vae-throws-error-after-upgrading-to-1-4-1-10-4/39746)._