Skip to content
Tags give the ability to mark specific points in history as being important
This project is mirrored from https://*****@github.com/SciML/DiffEqFlux.jl.git. Pull mirroring updated .
  • v1.33.0
    c759ee78 · Update Project.toml ·
    [Diff since v1.32.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.32.0...v1.33.0)
    
    **Closed issues:**
    - FastChain-Compatible Layers without bias term (#480)
    - FastChain is not GPU compatible anymore. (#487)
    - TensorLayer  update (#488)
    
    **Merged pull requests:**
    - Fix TensorLayer initialization (#489) (@ChrisRackauckas)
    - updated minibatch example to use Flux call (#490) (@khannay)
  • v1.32.0
    536112c6 · Update Project.toml ·
    [Diff since v1.31.1](https://github.com/SciML/DiffEqFlux.jl/compare/v1.31.1...v1.32.0)
    
    **Merged pull requests:**
    - FastChain-Compatible Layers without bias term (#482) (@Aman027)
    - Disable coverage statistics (#484) (@ChrisRackauckas)
    - Fix GPU CI (#485) (@ChrisRackauckas)
  • v1.31.1
    2295ff57 · Update Project.toml ·
    [Diff since v1.31.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.31.0...v1.31.1)
    
    **Merged pull requests:**
    - Update local_minima.md (#479) (@Manas2030)
  • v1.31.0
    [Diff since v1.30.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.30.0...v1.31.0)
    
    **Merged pull requests:**
    - [WIP] Extend collocation methods to use DataInterpolations.jl (#380) (@avik-pal)
    - Add buildkite pipeline (#474) (@ChrisRackauckas)
    - Update pipeline.yml (#475) (@ChrisRackauckas)
    - CompatHelper: add new compat entry for "DiffResults" at version "1.0" (#476) (@github-actions[bot])
  • v1.30.0
    55a5b250 · Update Project.toml ·
    [Diff since v1.29.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.29.0...v1.30.0)
    
    **Closed issues:**
    - StackOverFlowError in DiffEqFlux tutorial of constraints via Universal DAE (#468)
    - Typo in FastChain.md (#470)
    - `Using Flux Chain neural networks with Flux.train!` not working (#472)
    
    **Merged pull requests:**
    - Add neural_stiff_ode_sciml docs (#469) (@YingboMa)
    - CompatHelper: bump compat for "Adapt" to "3.0" (#473) (@github-actions[bot])
  • v1.29.0
    322ca54c · Update Project.toml ·
    [Diff since v1.28.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.28.0...v1.29.0)
    
    **Closed issues:**
    - `NeuralODE{TensorLayer}` has no parameters (#411)
    
    **Merged pull requests:**
    - Non-MM ndae updates (#426) (@ChrisRackauckas)
    - special view form for GPUs (#451) (@ChrisRackauckas)
    - add another hybrid example (#466) (@ChrisRackauckas)
  • v1.28.0
    bf6c5889 · Update Project.toml ·
    [Diff since v1.27.1](https://github.com/SciML/DiffEqFlux.jl/compare/v1.27.1...v1.28.0)
    
    **Closed issues:**
    - Using EnsembleDistributed() with Sciml_train? (#452)
    - ERROR: LoadError: InitError: Could not find a suitable CUDA installation (#453)
    - Multiple neural networks tutorial (#459)
    
    **Merged pull requests:**
    - Create tutorial for Bayesian Neural ODE: NUTS.  (#455) (@RajDandekar)
    - add distributed test (#456) (@ChrisRackauckas)
    - Restructure the documentation to have a bunch of subheaders (#457) (@ChrisRackauckas)
    - Create follow up tutorial for Bayesian Neural ODE: SGLD. (#458) (@RajDandekar)
    - Fix plot image links in bayesian neural ode examples (#460) (@Vaibhavdixit02)
    - add multiple nn tutorial (#464) (@ChrisRackauckas)
    - add parallelism tutorial (#465) (@ChrisRackauckas)
    - CompatHelper: bump compat for "Zygote" to "0.6" (#467) (@github-actions[bot])
  • v1.27.1
    59eeaecd · patch ·
    [Diff since v1.27.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.27.0...v1.27.1)
  • v1.27.0
    f1c095ed · Update Project.toml ·
    [Diff since v1.26.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.26.0...v1.27.0)
    
    **Merged pull requests:**
    - leanify the dependencies (#454) (@ChrisRackauckas)
  • v1.26.0
    449efcec · Update Project.toml ·
    [Diff since v1.25.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.25.0...v1.26.0)
    
    **Merged pull requests:**
    - CompatHelper: bump compat for "StaticArrays" to "1.0" (#449) (@github-actions[bot])
    - MassInstallAction: Install the GitHubActionsCI workflow on this repository (#450) (@christopher-dG)
  • v1.25.0
    1122fb90 · Update Project.toml ·
    [Diff since v1.24.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.24.0...v1.25.0)
    
    **Closed issues:**
    - How to calculate loss in a given time budget? (#434)
    - dt <= dtmin Aborting. There is either an error in your model specification or the true solution. (#435)
    - DiffEqFlux Failed to Train with Error "type BinaryHeap has no filed comparer" (#441)
    
    **Merged pull requests:**
    - Add warning to sciml_train, add a dispatch of sciml_train to GalacticOptim and rename layer_sciml test file to galacticoptim  (#424) (@Vaibhavdixit02)
    - Another strategy to avoid local minima (#431) (@ghost)
    - MassInstallAction: Install the TagBot workflow on this repository (#442) (@christopher-dG)
    - add an example with exogenous input (#444) (@ChrisRackauckas)
    - ready a release and see test results (#447) (@ChrisRackauckas)
  • v1.24.0
    0a4cab54 · Update Project.toml ·
    [Diff since v1.23.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.23.0...v1.24.0)
    
    **Closed issues:**
    - Training of UDEs with recurrent networks (#391)
    - Question regarding solution type (#418)
    - NEURAL ODE example with GPU not working (#419)
    
    **Merged pull requests:**
    - Work around missing matmul dispatch in CUDA.jl (#420) (@ChrisRackauckas)
    - Add GalacticOptim and update tests to use it (#421) (@Vaibhavdixit02)
    - CompatHelper: add new compat entry for "GalacticOptim" at version "0.2" (#423) (@github-actions[bot])
    - update GalacticOptim calls (#428) (@ChrisRackauckas)
    - CompatHelper: bump compat for "Distributions" to "0.24" (#430) (@github-actions[bot])
  • v1.23.0
    515e0fbe · Update Project.toml ·
    [Diff since v1.22.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.22.0...v1.23.0)
    
    **Closed issues:**
    - FFJORD for batched data (#342)
    - derivative definition of ude (#360)
    - Optimizing over a neural network and a (time-independent) coefficient simultaneously (#409)
    - CNF layers very slow with moderately sized Neural Networks (#413)
    
    **Merged pull requests:**
    - MNIST example DataLoader syntax bugfix (#369) (@mbeltagy)
    - Update collocation.jl (#406) (@ChrisRackauckas)
    - Update TagBot.yml (#410) (@kanav99)
    - Batched Implementation for FFJORD (#415) (@avik-pal)
    - work around trace for neldermead (#416) (@ChrisRackauckas)
    - Reduce allocations in collocation (#417) (@baggepinnen)
  • v1.22.0
    4e0210b2 · Update Project.toml ·
    ## DiffEqFlux v1.22.0
    
    [Diff since v1.21.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.21.0...v1.22.0)
    
    
    **Closed issues:**
    - DDE Example leads to " StackOverflowError:" (#396)
    - Differentiating with ReverseDiff fails on complex (#397)
    - Fail to compile (Julia 1.5.1) (#399)
    - sciml_train with Universal ODE fails on GPU (#400)
    
    **Merged pull requests:**
    - add hybrid example (#395) (@ChrisRackauckas)
    - Splat the MNIST Data for proper batching (#398) (@avik-pal)
    - Setup GPU tests to use CUDA (#404) (@ChrisRackauckas)
  • v1.21.0
    ## DiffEqFlux v1.21.0
    
    [Diff since v1.20.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.20.0...v1.21.0)
    
    
    **Closed issues:**
    - Direct access of DESolution fields during Zygote differentiation (#321)
    - EnsembleGPUArray() fails (#381)
    - example notebook not working (#388)
    - Handling sol.u interface (#389)
    - KernelError: passing and using non-bitstype argument (#390)
    
    **Merged pull requests:**
    - CompatHelper: add new compat entry for "LoggingExtras" at version "0.4" (#392) (@github-actions[bot])
    - CompatHelper: add new compat entry for "ConsoleProgressMonitor" at version "0.1" (#393) (@github-actions[bot])
    - CompatHelper: add new compat entry for "TerminalLoggers" at version "0.1" (#394) (@github-actions[bot])
  • v1.20.0
    ad45871e · Update Project.toml ·
    ## DiffEqFlux v1.20.0
    
    [Diff since v1.19.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.19.0...v1.20.0)
  • v1.19.0
    b6e168a4 · Update Project.toml ·
    ## DiffEqFlux v1.19.0
    
    [Diff since v1.18.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.18.0...v1.19.0)
    
    
    **Closed issues:**
    - HamiltonianProblem not supported (#53)
    - Hamiltonian Graph Networks with ODE Integrators (#80)
    - torchdiffeq comparison (#322)
    - Hamiltonian Neural Networks (#357)
    - Error on the "Optimization of Ordinary Differential Equations" Tutorial (#376)
    - ERROR: MethodError: no method matching -(::NTuple{29,Float64}) (#383)
    
    **Merged pull requests:**
    - Add support for Hamiltonian Neural Networks (#370) (@avik-pal)
    - Regularized ffjord [WIP] (#372) (@d-netto)
    - docs (#382) (@d-netto)
    - additional fixes in cnf documentation (#384) (@d-netto)
  • v1.18.0
    ed92e198 · Update Project.toml ·
    ## DiffEqFlux v1.18.0
    
    [Diff since v1.17.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.17.0...v1.18.0)
    
    
    **Closed issues:**
    - Flesh out documentation (#244)
    - Multiple ODE solves from a single time series on GPU (#279)
    - Zygote.gradient doesn't work with basic `solve` example (#344)
    - Is it possible to learn neuralode for stiff problem of Robertson's problem? (#367)
    - More pictures (#375)
    
    **Merged pull requests:**
    - spline: more tests (#345) (@d-netto)
    - Spline docs (#348) (@d-netto)
    - Finish GDE PR (#355) (@ChrisRackauckas)
    - Use travis_wait (#356) (@christopher-dG)
    - add smoothed collocation fitting (#359) (@ChrisRackauckas)
    - change in ffjord tests (#361) (@d-netto)
    - Update ffjord.jl (#363) (@nirmal-suthar)
    - revised minibatch docs (#365) (@collinwarner)
    - CompatHelper: add new compat entry for "MLDataUtils" at version "0.5" (#366) (@github-actions[bot])
    - Require Zygote 0.5 (#373) (@ChrisRackauckas)
    - test the fixed ensemble parallelism (#374) (@ChrisRackauckas)
  • v1.17.0
    3cfc2ec2 · Update Project.toml ·
    ## DiffEqFlux v1.17.0
    
    [Diff since v1.16.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.16.0...v1.17.0)
    
    
    **Closed issues:**
    - One dimensional universal approximators and tensor product basis (#173)
    - ANODEV2 (#289)
    - Neural ODE trains but throws an error when trying to show the result from Optim (#327)
    - Augmented neural ODE on GPU errors out (#329)
    - Compilation fails (#334)
    - Neural Stochastic DiffEq example no longer working (#336)
    - Neural DAE tutorial code not working (#337)
    
    **Merged pull requests:**
    - typos in documentation (#326) (@d-netto)
    - CompatHelper: bump compat for "Optim" to "0.22" (#330) (@github-actions[bot])
    - Tutorial (#331) (@d-netto)
    - fix output statuses (#332) (@ChrisRackauckas)
    - ANODE Example on GPU (#333) (@avik-pal)
    - changes in tensor layer (#338) (@d-netto)
    - Spline layer [WIP] (#339) (@d-netto)
    - restructure layer docs (#341) (@ChrisRackauckas)
  • v1.16.0
    0ee53419 · Update Project.toml ·
    ## DiffEqFlux v1.16.0
    
    [Diff since v1.15.0](https://github.com/SciML/DiffEqFlux.jl/compare/v1.15.0...v1.16.0)
    
    
    **Closed issues:**
    - Augmented neural ODEs (#288)
    
    **Merged pull requests:**
    - Augmented Neural DE (#316) (@avik-pal)
    - add text to pde_constrained.md (#324) (@JeremyFongSP)
    - Tensor Layer: documentation and optimization (#325) (@d-netto)