OperatorLearning.jl
OperatorLearning.jl copied to clipboard
SciML
No need to train, he's a smooth operator
This pull request changes the compat entry for the `OMEinsum` package from `0.6` to `0.6, 0.7`. This keeps the compat entries for earlier versions. Note: I have not tested your...
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "github-actions[bot] avatar"){kind=avatar}
Issue : From the example for the FNO, collecting parameters throws an error as such.  Potential cause: In https://github.com/SciML/OperatorLearning.jl/blob/master/src/FourierLayer.jl#L55-L56 and subsequently https://github.com/FluxML/Flux.jl/blob/master/src/utils.jl#L500-L502, there is trivial Bool return that FourierLayer.jl...
I have added a couple of simple tests for Fourier Layer and DeepONet Layer. What more tests can we add for the same? One thing that I wanted to add...
Similar to the `FastDense` optimizations in https://github.com/SciML/DiffEqFlux.jl/pull/671, this library can definitely benefit from having pre-cached versions of the operations since the neural networks are generally small. In addition, the `plan_fft`...
#31 introduces Fourier Layer for higher dimensions. For now, `rfft` has been replaced by `fft` since it's simpler to implement. However, `rfft` can save memory and computation time considerably (~2x),...
The tests don't seem to cover the use and training of the operators, just a few properties. It would be good to get a few integration tests.
It would be nice to check if this is compatible with Schrodinger equation applications, as that's a common PDE that can go to very high dimensions.
In order to assimilate `FourierLayer` to the yet to implement DeepONet, it would be nice to have a Fourier Neural Operator (FNO) constructor that creates the entire architecture. Something like:...