Walkthrough: Aerodynamic CFD with Noether

Authors: Maurits Bleeker, Markus Hennerbichler, and Pavel Kuksa

This walkthrough demonstrates how to use the Noether Framework through a practical project based on the experiments from Section 4.4 of the AB-UPT paper. While this walkthrough covers the core functionality of the framework, it does not cover every possible feature or use case.

Note

This walkthrough presents recommended practices and patterns, but it is not a full blueprint on how to use the framework. The Noether Framework is flexible and supports multiple approaches to implementing the same functionality.

The full source code for this walkthrough lives in the recipes/aero_cfd/ directory of the repository.

• Introduction
  • File structure of the project
  • Project setup
• Configuration
  • Configuration architecture
  • Example: ShapeNet-Car configuration
  • Defining experiment configurations
  • Running experiments
  • Pydantic schemas for type safety
  • Example: Transformer configuration schema
  • From schema to YAML
  • Configuration inheritance
  • Configuration schemas
• Datasets
  • Object instantiation
  • The Dataset
  • The getitem_* pattern: Modular data loading
  • ShapeNet-Car dataset structure
  • Dataset configuration
  • Selective data loading with excluded_properties
  • Essential dataset methods
  • Tensor normalization with decorators
  • Computing dataset statistics
  • Noether dataset zoo
  • Creating custom datasets
• The Multi-Stage Pipeline
  • Sample processors
  • Collators
  • Batch processors
• The Trainer
  • BaseTrainer implementation
  • BaseTrainer configuration
  • AerodynamicsCFDTrainer implementation
• Models
  • The ModelBaseConfig schema
  • Implementing a custom model
  • Aerodynamic model wrappers
  • Handling model outputs
  • Composite Models
  • Noether model zoo
• Callbacks
  • Overview
  • Implementing PeriodicDataIteratorCallback
  • Configuring callbacks
  • Denormalization for metrics
  • Computed metrics
  • Final evaluation with repeated testing
• Running the Experiments
  • Running SLURM jobs
  • Running a single experiment
  • Running multi-GPU experiments
  • Running inference
  • Resuming training after interruption
  • Initializing model weights
  • WandB tracker
  • Extra utilities and tips
• AB-UPT Showcase
  • Dataset
  • Training
  • Evaluation
  • Model sizes
  • Results
  • Customization