reshape used in the wrong way

[benedict-96]

In

SymbolicNeuralNetworks.jl/src/utils/build_function.jl

Lines 27 to 30 in 8d610cc

	gen_fun_returned(x, ps) = mapreduce(k -> gen_fun(x, ps, k), hcat, axes(x, 2))
	gen_fun_returned(x::Union{AbstractVector, Symbolics.Arr}, ps) = gen_fun_returned(reshape(x, length(x), 1), ps)
	# check this! (definitely not correct in all cases!)
	gen_fun_returned(x::AbstractArray{<:Number, 3}, ps) = reshape(gen_fun_returned(reshape(x, size(x, 1), size(x, 2) * size(x, 3)), ps), size(x, 1), size(x, 2), size(x, 3))

and

SymbolicNeuralNetworks.jl/src/utils/build_function2.jl

Lines 21 to 23 in 8d610cc

	gen_fun_returned(input, output, ps) = mapreduce(k -> gen_fun(input, output, ps, k), +, axes(input, 2))
	gen_fun_returned(input::AT, output::AT, ps) where {AT <: Union{AbstractVector, Symbolics.Arr}} = gen_fun_returned(reshape(input, length(input), 1), reshape(output, length(output), 1), ps)
	gen_fun_returned(input::AT, output::AT, ps) where {T, AT <: AbstractArray{T, 3}} = gen_fun_returned(reshape(input, size(input, 1), size(input, 2) * size(input, 3)), reshape(output, size(output, 1), size(output, 2) * size(output, 3)), ps)

reshape is used on the dimensions of the input array and not of the output array.
This is possibly also the cause behind the problem observed in #18 (comment).