NVIDIA/physicsnemo

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

3.2kStars on the repository
31Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

NVIDIA/physicsnemo

Cursor rule Cursor

Reusable layers and building blocks should be placed in physicsnemo/nn, not physicsnemo/models. Examples include FullyConnected, attention layers, and UNetBlock.

3.2k 3d ago A 34 tokens original Apache-2.0

NVIDIA/physicsnemo

Cursor rule Cursor

Complete models composed of multiple layers should be placed in physicsnemo/models, not physicsnemo/nn. These are domain-specific or modality-specific models.

3.2k 3d ago A 31 tokens original Apache-2.0

NVIDIA/physicsnemo

Cursor rule Cursor

All model and layer classes must inherit from physicsnemo.Module (not torch.nn.Module directly) to ensure proper serialization, versioning, and registry functionality.

3.2k 3d ago A 31 tokens original Apache-2.0

NVIDIA/physicsnemo

Cursor rule Cursor

Model classes being deprecated must include deprecation warnings in both docstring and runtime, explaining why and what users should use instead, for at least 1 release cycle.

3.2k 3d ago A 33 tokens original Apache-2.0

NVIDIA/physicsnemo

Cursor rule Cursor

Every model/layer requires comprehensive docstrings following NumPy style with Sphinx RST formatting, including all sub-rules MOD-003b through MOD-003k.

3.2k 3d ago A 34 tokens original Apache-2.0

NVIDIA/physicsnemo

Cursor rule Cursor

All utility functions specific to a model must be in the same module file as the model itself, not in separate utility files, to maintain self-contained modules.

3.2k 3d ago A 31 tokens original Apache-2.0