# ForwardDiff.derivative pointwise
**URL:** https://discourse.julialang.org/t/forwarddiff-derivative-pointwise/92867
**Category:** Performance
**Tags:** forwarddiff
**Created:** [January 12, 2023, 11:12am UTC](https://discourse.julialang.org/t/forwarddiff-derivative-pointwise/92867 "2023-01-12T11:12:49Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@c\_sell](https://discourse.julialang.org/u/c_sell)
#### Post date: [January 12, 2023, 11:12am UTC](https://discourse.julialang.org/t/forwarddiff-derivative-pointwise/92867/1 "2023-01-12T11:12:49Z")
Hello,
is it possible to use ForwardDiff in the following way. I have a function (a forward diff through a neural network). I want to take the second derivative of the output with respect to the input.
If I use n input points, the n outputs are point independent.
Is it possible to use ForwardDiff for this? (The Jacobian obviously takes too many derivatives).
Thank you very much for your time.
---
### Author:  [@c\_sell](https://discourse.julialang.org/u/c_sell)
#### Post date: [January 12, 2023, 12:27pm UTC](https://discourse.julialang.org/t/forwarddiff-derivative-pointwise/92867/2 "2023-01-12T12:27:49Z")
Hi I wrote an own small extension for the forwardDiff api.
Maby someone will need this too:
```julia
@inline function derivative(f::F, x::AbstractArray{R}) where {F,R<:Real}
T = typeof(ForwardDiff.Tag(f, R))
dual_vec = ForwardDiff.Dual{T}.(x, ones(size(x)))
return ForwardDiff.extract_derivative(T,f(dual_vec))
end
```
---
### Author:  [@c\_sell](https://discourse.julialang.org/u/c_sell)
#### Post date: [January 12, 2023, 1:15pm UTC](https://discourse.julialang.org/t/forwarddiff-derivative-pointwise/92867/3 "2023-01-12T13:15:48Z")
Zygote.jl cant take the derivative of a loss function containing the above code.
```julia
MethodError: no method matching Zygote.OneElement(::NamedTuple{(:value, :partials), Tuple{Nothing, Zygote.OneElement{Float64, 1, Tuple{Int64}, Tuple{Base.OneTo{Int64}}}}}, ::Tuple{Int64},
::Tuple{Base.OneTo{Int64}})
Closest candidates are:
Zygote.OneElement(::T, ::I, ::A) where {N, T<:Number, I<:Tuple{Vararg{Int64, N}}, A<:Tuple{Vararg{AbstractUnitRange, N}}} at C:\Users\Lenovo\.julia\packages\Zygote\arfUC\src\lib\array.jl:69
```
There is a problem with the namedTuple of the Partials type I guess. Is there a work around?