Hello, I use the warp function as part of my loss function for which I need to compute a Jacobian. I've tried ForwardDiff, and Zygote, and both seem to throw errors during the warp call.
In the case of ForwardDiff, I get a stack overflow error, and in the case of Zygote, I get the following:
ERROR: MethodError: no method matching iterate(::Nothing)
Closest candidates are:
iterate(::Union{LinRange, StepRangeLen}) at range.jl:872
iterate(::Union{LinRange, StepRangeLen}, ::Integer) at range.jl:872
iterate(::T) where T<:Union{Base.KeySet{<:Any, <:Dict}, Base.ValueIterator{<:Dict}} at dict.jl:712
Do you have any ideas on what I can do to get warp working with autodiff?
Hello, I use the
warpfunction as part of my loss function for which I need to compute a Jacobian. I've tried ForwardDiff, and Zygote, and both seem to throw errors during thewarpcall.In the case of ForwardDiff, I get a stack overflow error, and in the case of Zygote, I get the following:
Do you have any ideas on what I can do to get
warpworking with autodiff?