🆕rename package

Author: pzimbrod

.github/workflows/CI.yml

@@ -54,6 +54,6 @@ jobs:
         - run: |
             julia --project=docs -e '
               using Documenter: DocMeta, doctest
-              using NeuralOperator
-              DocMeta.setdocmeta!(NeuralOperator, :DocTestSetup, :(using NeuralOperator); recursive=true)
-              doctest(NeuralOperator)'
+              using OperatorLearning
+              DocMeta.setdocmeta!(OperatorLearning, :DocTestSetup, :(using OperatorLearning); recursive=true)
+              doctest(OperatorLearning)'

Project.toml

@@ -1,4 +1,4 @@
-name = "NeuralOperator"
+name = "OperatorLearning"
 uuid = "5913d0e6-5bb6-45e3-8a06-341cf4fd0203"
 authors = ["Patrick Zimbrod <[email protected]>"]
 version = "0.1.0"

README.md

@@ -5,8 +5,9 @@
 [![Dev](https://img.shields.io/badge/docs-dev-blue.svg)](https://pzimbrod.github.io/OperatorLearning.jl/dev)
 [![Build Status](https://github.com/pzimbrod/OperatorLearning.jl/actions/workflows/CI.yml/badge.svg?branch=main)](https://github.com/pzimbrod/OperatorLearning.jl/actions/workflows/CI.yml?query=branch%3Amaster++)
 
-A `Julia` implementation of the Fourier Neural Operator conceived by [Zongyi et al.](https://arxiv.org/abs/2010.08895) 
-using (mainly) [Flux.jl](https://github.com/FluxML/Flux.jl) and [FFTW.jl](https://github.com/JuliaMath/FFTW.jl).
+A Package that provides Layers for the learning of (nonlinear) operators in order to solve parametric PDEs.
+
+For now, this package contains the Fourier Neural Operator originally proposed by Li et al.
 
 I decided to implement this method in Julia because coding up a layer using PyTorch in Python is rather cumbersome in comparison and Julia as a whole simply runs at comparable or faster speed than Python. Please do check out the [original work](https://github.com/zongyi-li/fourier_neural_operator) at GitHub as well.
 
@@ -17,7 +18,7 @@ The implementation of the layers is influenced heavily by the basic layers provi
 Simply install by running in a REPL:
 
 ```julia
-pkg> add NeuralOperator
+pkg> add OperatorLearning
 ```
 
 ## Usage/Examples
@@ -30,7 +31,7 @@ Additionally, higher Fourier modes are filtered out in the convolution path wher
 The syntax for a single Fourier Layer is:
 
 ```julia
-using NeuralOperator
+using OperatorLearning
 using Flux
 
 # Input = 101, Output = 101, Batch size = 200, Grid points = 100, Fourier modes = 16
@@ -57,3 +58,7 @@ To see a full implementation, check the Burgers equation example at `examples/bu
 ## Contributing
 
 Contributions are always welcome!
+
+## References
+
+- Li et al., 2020 [arXiv:2010.08895](https://arxiv.org/abs/2010.08895)

benchmarks/Project.toml

@@ -2,5 +2,5 @@
 BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 Flux = "587475ba-b771-5e3f-ad9e-33799f191a9c"
-NeuralOperator = "5913d0e6-5bb6-45e3-8a06-341cf4fd0203"
+OperatorLearning = "5913d0e6-5bb6-45e3-8a06-341cf4fd0203"
 Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"

benchmarks/bench_utils.jl

@@ -1,6 +1,6 @@
 using BenchmarkTools
 using Flux
-using NeuralOperator
+using OperatorLearning
 using CUDA
 using Zygote: pullback
 

benchmarks/runbenchmarks.jl

@@ -1,4 +1,4 @@
-using NeuralOperator, Flux
+using OperatorLearning, Flux
 
 versioninfo()
 include("bench_utils.jl")

docs/Manifest.toml

@@ -57,7 +57,7 @@ uuid = "a63ad114-7e13-5084-954f-fe012c677804"
 [[NetworkOptions]]
 uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
 
-[[NeuralOperator]]
+[[OperatorLearning]]
 path = ".."
 uuid = "1338832d-e311-4fa7-a4df-210c2f38d798"
 version = "0.1.0"

docs/Project.toml

@@ -1,3 +1,3 @@
 [deps]
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
-NeuralOperator = "5913d0e6-5bb6-45e3-8a06-341cf4fd0203"
+OperatorLearning = "5913d0e6-5bb6-45e3-8a06-341cf4fd0203"

docs/make.jl

@@ -1,10 +1,10 @@
-using NeuralOperator
+using OperatorLearning
 using Documenter
 
-DocMeta.setdocmeta!(NeuralOperator, :DocTestSetup, :(using NeuralOperator); recursive=true)
+DocMeta.setdocmeta!(OperatorLearning, :DocTestSetup, :(using OperatorLearning); recursive=true)
 
 makedocs(;
-    modules=[NeuralOperator],
+    modules=[OperatorLearning],
     authors="Patrick Zimbrod <[email protected]> and contributors",
     repo="https://github.com/pzimbrod/OperatorLearning.jl/blob/{commit}{path}#{line}",
     sitename="OperatorLearning.jl",
@@ -21,6 +21,5 @@ makedocs(;
 
 deploydocs(;
     repo="github.com/pzimbrod/OperatorLearning.jl",
-    versions = ["stable" => "v^", "v#.#", devurl => devurl],
     #devbranch="main",
 )

docs/src/index.md

@@ -1,10 +1,10 @@
 ```@meta
-CurrentModule = NeuralOperator
+CurrentModule = OperatorLearning
 ```
 
-# NeuralOperator
+# OperatorLearning
 
-Documentation for [NeuralOperator](https://github.com/Patrick Zimbrod/OperatorLearning.jl).
+Documentation for [OperatorLearning](https://github.com/pzimbrod/OperatorLearning.jl).
 
 ```@index
 ```
@@ -14,7 +14,7 @@ Documentation for [NeuralOperator](https://github.com/Patrick Zimbrod/OperatorLe
 Simply install by running in a REPL:
 
 ```julia
-pkg> add NeuralOperator
+pkg> add OperatorLearning
 ```
 
 ## Usage/Examples
@@ -27,7 +27,7 @@ Additionally, higher Fourier modes are filtered out in the convolution path wher
 The syntax for a single Fourier Layer is:
 
 ```julia
-using NeuralOperator
+using OperatorLearning
 using Flux
 
 # Input = 101, Output = 101, Batch size = 200, Grid points = 100, Fourier modes = 16