DiffEqFlux.jl
DiffEqFlux.jl copied to clipboard
SciML
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Strangely, the following codes work well if DiffEqFlux is not loaded but they break if it is. MWE ```julia using Zygote using StochasticDiffEq using SciMLSensitivity using DiffEqFlux # if used,...
https://github.com/FluxML/Zygote.jl/issues/1284#issuecomment-1228028759
**Describe the bug 🐞** When using a `NeuralODE` model within Turing.jl, specifically with parameters and data in `Float64`, the auto-promotion of parameters to Dual type for AD seems not to...
**Describe the bug 🐞** After enabling GC logging, there are lots of 45mb collections in v1.9 and similar but fewer collections in v1.10. Is there a hidden problem that causing...
Such that `makedocs` `warnonly = [:docs_block, :missing_docs]` can be removed.
I'm running the following MWE: ``` using DiffEqFlux, Lux, DifferentialEquations, ComponentArrays, CUDA using Optimization, OptimizationOptimJL using Random rng = Random.default_rng() trainingData = [collect(1:10)';rand(3,10)] chain = Lux.Chain(Lux.Dense(4,5),Lux.Dense(5,4)) ps, st = Lux.setup(rng,chain)...
Hello, I have been been facing an issue. Depending on the uODE I am solving I am getting the error: ``` ┌ Warning: EnzymeVJP tried and failed in the automated...
Hi everyone, I am trying to solve this neuralODE which describes a RC building thermal model. I start having problems when I include the dependence of the equation on Text...
I am opening an issue based on this discourse thread in which I ask about estimating intractable likelihood functions with normalizing flows. As described in this [paper](https://elifesciences.org/articles/77220), normalizing flows can...
