NVIDIA PhysicsNeMo is an open-source deep-learning framework for building, training, fine-tuning and inferring Physics AI models using state-of-the-art SciML methods for AI4science and engineering.
PhysicsNeMo provides python modules to compose scalable and optimized training and inference pipelines to explore, develop, validate and deploy AI models that combine physics knowledge with data, enabling real-time predictions.
Provides an abstraction layer for using PDE-based symbolic loss functions.
Additional resources to help you plan when using PhysicsNeMo.
GitHub Repo for PhysicsNeMo
Container with all the PhysicsNeMo components and dependencies pre-installed, ready to use.
Join PhysicsNeMo Forums for questions and discussions