NeuralOperator User Guide

NeuralOperator provides all the tools you need to easily use, build and train neural operators for your own applications and learn mapping between function spaces, in PyTorch.

Intro to operator learning

To get a better feel for the theory behind our neural operator models, see Neural Operators: an Introduction. Once you’re comfortable with the concept of operator learning, check out specific details of our Fourier Neural Operator (FNO) in Fourier Neural Operators. Finally, to learn more about the model training utilities we provide, check out Training neural operator models.

Interactive examples with code

We also provide interactive examples that show our library and neural operator models in action. To get up to speed on the code, and look through some interactive examples to help you hit the ground running, check out our Gallery of examples.

NeuralOperator library structure

Here are the main components of the library:

Module	Description
`neuralop`	Main library
`neuralop.models`	Full ready-to-use neural operators
`neuralop.layers`	Individual layers to build neural operators
`neuralop.data`	Convenience PyTorch data loaders for PDE datasets
`neuralop.training`	Utilities to train neural operators end-to-end

The full API documentation is provided in API reference.

Finally, if you’re building the library from source, your repository will also include the following directories:

Directory	Description
`scripts`	Training recipe scripts for our models on sample problems
`examples`	More documented interactive examples, seen in