PhysicsNeMo Symbolic

PhysicsNeMo Sym
| Getting started
| Documentation
| Contributing Guidelines
| Communication

What is PhysicsNeMo Symbolic?

PhysicsNeMo Symbolic (PhysicsNeMo Sym) is sub-module of PhysicsNeMo framework that provides
algorithms and utilities to explicitly physics inform the
training of AI models.

Please refer to the PhysicsNeMo framework
to learn more about the full stack.

This includes utilities for explicitly integrating symbolic PDEs,
domain sampling and computing PDE-based residuals using various gradient computing schemes.

Please refer to the
Physics informing surrogate model for Darcy flow
that illustrates the concept.

It also provides an abstraction layer for developers that want to compose a training loop
from specification
of the geometry, PDEs and constraints like boundary conditions using simple symbolic APIs.
Please refer to the
Lid Driven cavity
that illustrates the concept.

Additional information can be found in the
PhysicsNeMo documentation.

Getting started

Please use the getting started guide here for PhysicsNeMo

Please refer Introductory Example
for usage of the physics utils in custom training loops and
Lid Driven cavity
for an end-to-end PINN workflow.

Installation

Please ensure you have installed PhysicsNeMo using the steps here.

You can then install this package following the steps outlined below:

PyPi

The recommended method for installing the latest version of PhysicsNeMo Symbolic is
using PyPi:

pip install "Cython"
pip install nvidia-physicsnemo.sym --no-build-isolation

Note, the above method only works for x86/amd64 based architectures. For installing
PhysicsNeMo Sym on Arm based systems using pip,
Install VTK from source as shown
here
and then install PhysicsNeMo-Sym and other dependencies.

pip install nvidia-physicsnemo.sym --no-deps
pip install "hydra-core>=1.2.0" "termcolor>=2.1.1" "chaospy>=4.3.7" "Cython==0.29.28" \
    "numpy-stl==2.16.3" "opencv-python==4.5.5.64" "scikit-learn==1.0.2" \
    "symengine>=0.10.0" "sympy==1.12" "timm>=1.0.3" "torch-optimizer==0.3.0" \
    "transforms3d==0.3.1" "typing==3.7.4.3" "pillow==10.0.1" "notebook==6.4.12" \
    "mistune==2.0.3" "pint==0.19.2" "tensorboard>=2.8.0"

Container

The recommended PhysicsNeMo docker image can be pulled from the
NVIDIA Container Registry:

docker pull nvcr.io/nvidia/physicsnemo/physicsnemo:<tag>

From Source

Package

For a local build of the PhysicsNeMo Symbolic Python package from source use:

git clone [email protected]:NVIDIA/physicsnemo-sym.git && cd physicsnemo-sym

pip install --upgrade pip
pip install .

Source Container

To build release image insert next tag and run below:

docker build -t physicsnemo-sym:deploy \
    --build-arg TARGETPLATFORM=linux/amd64 --target deploy -f Dockerfile .

Currently only linux/amd64 and linux/arm64 platforms are supported.

Contributing to PhysicsNeMo

PhysicsNeMo is an open source collaboration and its success is rooted in community
contribution to further the field of Physics-ML. Thank you for contributing to the
project so others can build on top of your contribution.

For guidance on contributing to PhysicsNeMo, please refer to the
contributing guidelines.

Cite PhysicsNeMo

If PhysicsNeMo helped your research and you would like to cite it, please refer to the
guidelines

Communication

• Github Discussions: Discuss new architectures, implementations, Physics-ML research, etc.
• GitHub Issues: Bug reports, feature requests, install issues, etc.
• PhysicsNeMo Forum: The PhysicsNeMo Forum
  hosts an audience of new to moderate-level users and developers for general chat, online
  discussions, collaboration, etc.

Feedback

Want to suggest some improvements to PhysicsNeMo? Use our feedback form.

License

PhysicsNeMo is provided under the Apache License 2.0, please see LICENSE.txt
for full license text.