modulus
modulus copied to clipboard
NVIDIA
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
### Is this a new feature, an improvement, or a change to existing functionality? Improvement ### How would you describe the priority of this feature request Low (would be nice)...
Hi, I was wondering where the sfnonet.py file is in the modulus repository please? I can see it provided here but not in the main branch: https://github.com/NVIDIA/modulus/blob/b8e27c5c4ebc409e53adaba9832138743ede2785/modulus/models/sfno/sfnonet.py
# Modulus Pull Request ## Description ## Checklist - [x] I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/modulus/blob/main/CONTRIBUTING.md). - [ ] New or existing tests cover these changes. - [ ]...
# Modulus Pull Request ## Description Fixes a bug where the dlwp_healpix dataloader uses a prebuilt dataset with more channels than used by the model. This fix adds channel selection...
# Modulus Pull Request ## Description Fix the bug where dlwp_healpix constant coupler did not support batch coupled inputs for inference ## Checklist - [x] I am familiar with the...
# Modulus Pull Request ## Description Unify the coupled dlwp-healpix atmosphere-ocean model config with original dlwp-healpix config ## Checklist - [x] I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/modulus/blob/main/CONTRIBUTING.md). - [x]...
# Modulus Pull Request ## Description Update stochastic sampler ## Checklist - [ ] I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/modulus/blob/main/CONTRIBUTING.md). - [ ] New or existing tests cover these...
# Modulus Pull Request for Lagrangian MeshGraphNet ## Description We implemented Meshgraphnet for particle-based simulation on the water dataset based on in PyTorch. It demonstrates how to train a Graph...
### Is this a new feature, an improvement, or a change to existing functionality? New Feature ### How would you describe the priority of this feature request Medium ### Please...