Physics-informed Machine Learning with NVIDIA Modulus
Physics-Informed Machine Learning with NVIDIA Modulus (Latest Version)


Welcome to the trial of NVIDIA Modulus on NVIDIA LaunchPad!

NVIDIA Modulus is a deep learning framework that blends the power of physics and partial differential equations (PDEs) with AI to build more robust models for better analysis.

With NVIDIA Modulus, we aim to provide researchers and industry specialists, various tools that will help accelerate your development of such models for the scientific discipline of your need.

Visit the NVIDIA Modulus Website for more information.

Modulus Documentation


Included in this Modulus LaunchPad Developer Lab are a few getting started examples. ‘Getting Started with Modulus Training’ walks you through a simple example of the common workflow steps in setting up training of a model in Modulus. The other two Jupyter notebooks, you will learn how to train a physics informed neural network for a canonical lid driven cavity example and how to train a Fourier Neural Operator for Darcy flow.

These notebooks focus on the key steps of the training process, the high level Python APIs to set up the geometry, the boundary conditions and the governing equations and defining the neural networks to train a Physics-ML Model.

© Copyright 2022-2023, NVIDIA. Last updated on Jan 10, 2023.