RegNeuralDE.jl

RegNeuralDE.jl copied to clipboard

pytorch implementation

1

Is there pytorch implementation for your approach?

EyalRozenberg1

GPU Compilation for Tracker Backward Pass through savevals

3

Backward Pass on GPUs currently fail due to ``` ERROR: InvalidIRError: compiling kernel broadcast_kernel(CUDA.CuKernelContext, CuDeviceArray{Float32,2,CUDA.AS.Global}, Base.Broadcast.Broadcasted{Nothing,Tuple{Base.OneTo{Int64},Base.OneTo{Int64}},typeof(Tracker.partial),Tuple{CUDA.CuRefValue{typeof(DiffEqBase.calculate_residuals)},Base.Broadcast.Extruded{CuDeviceArray{Float32,2,CUDA.AS.Global},Tuple{Bool,Bool},Tuple{Int64,Int64}},Int64,Base.Broadcast.Extruded{CuDeviceArray{Float32,2,CUDA.AS.Global},Tuple{Bool,Bool},Tuple{Int64,Int64}},Base.Broadcast.Extruded{CuDeviceArray{Float32,2,CUDA.AS.Global},Tuple{Bool,Bool},Tuple{Int64,Int64}},Base.Broadcast.Extruded{CuDeviceArray{Float32,2,CUDA.AS.Global},Tuple{Bool,Bool},Tuple{Int64,Int64}},Float32,Float32,CUDA.CuRefValue{typeof(DiffEqBase.ODE_DEFAULT_NORM)},Float32}}, Int64) resulted in invalid LLVM IR Reason: unsupported dynamic function invocation (call to partial(f::F,...

avik-pal

Significantly Faster Adjoint Solves

1

@ChrisRackauckas have you seen this work by Ricky already? https://arxiv.org/abs/2009.09457 **"Hey, that's not an ODE": Faster ODE Adjoints with 12 Lines of Code** Patrick Kidger, Ricky T. Q. Chen, Terry...

jessebett