JingYu Ning

> Maybe [WGLMakie](http://juliaplots.org/WGLMakie.jl/stable/) This might work. I'll give it a try

The `.deb` package seems to be empty. Inside the `avalon-studio.desktop` file (located under `/usr/share/applications`) ``` [Desktop Entry] Name=Avalon Studio Comment=A Torrent of Embedded Creativity GenericName=Development Environment Exec=/opt/vitalelement/avalonstudio/bin/AvalonStudio %U Icon=avalon-studio Type=Application...

> The `.deb` package seems to be empty. > > Inside the `avalon-studio.desktop` file (located under `/usr/share/applications`) > > ``` > [Desktop Entry] > Name=Avalon Studio > Comment=A Torrent of...

Hi @DhairyaLGandhi , I have tried ```julia c_glorot_uniform(dims...) = Flux.glorot_uniform(dims...) + Flux.glorot_uniform(dims...) * im m = Chain( Conv((3, ), 1=>2, pad=1, init=c_glorot_uniform), ) |> gpu ``` And I got the...

Still need some revise, discussed F2F

@MilkshakeForReal Please take a look at [this](https://github.com/zongyi-li/fourier_neural_operator/blob/74b1572d4e02f215728b4aa5bf46374ed7daba06/utilities3.py#L161), it is the relative L2 loss Update: Sorry I misunderstand the question. If you are asking about the value of the loss after...

I am not sure what kind of magic you expect to see in the GNO. Just like the eqs you mentioned in #74 is nothing but a message passing NN?

The main idea of neural operator is to learn the mapping in the spectral space. In GNO, the implementation is done by graph signal laplace transform and message passing neural...

@MilkshakeForReal About the encoder, you mean [the `GaussianNormalizer`](https://github.com/zongyi-li/graph-pde/blob/08ab9d8f8e9d1a6d95017a6f803a53d8a603e66e/graph-neural-operator/utilities.py#L109)?

@MilkshakeForReal Take your time, and please feel free to open a PR if you still think there is anything wrong 😄