Abhishek Bhatt

This is related to https://github.com/SciML/DiffEqFlux.jl/pull/736 where I am trying to make the doc example work, with the Lux compatible constructor for NeuralDSDE defined in the same pr. The error occurs...

It is really strange that it uses 0.4.3 while I have 0.4.6, do you have any ideas on what could cause that? ```julia (@v1.7) pkg> st Status `C:\Users\user\.julia\environments\v1.7\Project.toml` [4fba245c] ArrayInterface...

With the Lux v0.4.6, this issue shows up ```julia ERROR: DimensionMismatch("arrays could not be broadcast to a common size; got a dimension with lengths 20 and 2") Stacktrace: _bcs1 at...

Same thing in doctests https://github.com/SciML/DiffEqFlux.jl/runs/7009484845?check_suite_focus=true#step:5:22

Do these tests need to run on gpu?

Would we need a dataset in the library for that?

Maybe we can add a smaller version of the Burgers' equation dataset which contains just what we need for the test, because the whole data file is like 600MB

It has data for 2048 initial conditions at 8192 points for each😅. We can use like 100 - 200 ICs at 1024 points(just like the tutorial), would that work?

So I tried implementing a training test for fourier layer, I think there could be a bug here, I have followed the burgers' equation example here Code: vars = matread("burgerset.mat")...

The test for DeepONet works fine