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

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:

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:

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:)