Samuel Burbulla
Samuel Burbulla
Hey Jonathan, I'm interested in the name 'continuity' on PyPI for a new project. I saw that your last release was in 2017, so I wonder if you're still using...
The setup fails on MacOS together with Python 3.11 due to a missing `torch==1.11.0` distribution for Mac. This is unfortunate as Python 3.11 is the default Python version on MacOS....
# Feature: Add MINO implementation. ## Description Add the mesh-independent neural operator (MINO). Reference: Seungjun Lee. Mesh-Independent Operator Learning for Partial Differential Equations. 2nd AI4Science Workshop, ICML (2022) ### Which...
# Feature: Wrap models from NVIDIA Modulus. ## Description ### Which issue does this PR tackle? - Fixes #127 ### How does it solve the problem? - Implements `continuiti.wrapper.modulus` submodule...
Wrap operator implementations from [modulus](https://github.com/NVIDIA/modulus) in a `continuiti.operator.modulus` submodule.
Implement Convolutional Neural Operators: - https://arxiv.org/abs/2302.01178 - https://github.com/bogdanraonic3/ConvolutionalNeuralOperator In this task, we could also implement standard U-Nets as (discretization-dependent) neural operators.
- [x] Add test that ensures that functionality from [DeepXDE](https://github.com/lululxvi/deepxde) (torch backend) can be used with continuiti: - geometry - physics-informed loss - rebuilding pi-deeponet with continuity Added in #133...
Currently, we have sth. like ``` num_functions = 100 degree = 3 space = FunctionSet(lambda a: lambda x: sum(a[i] * x**i for i in range(degree + 1)) ) coeffs =...
Wrap operator implementations from [neuraloperator](https://github.com/neuraloperator/neuraloperator) in a `continuiti.wrapper.neuraloperator` submodule.