HamGNN v2.1 Documentation
Welcome to HamGNN v2.1 documentation!
Introduction to HamGNN
HamGNN is an E(3) equivariant graph neural network designed to train and predict ab initio tight-binding (TB) Hamiltonians for molecules and solids. It can be used with common ab initio DFT software that rely on numerical atomic orbitals, such as OpenMX, Siesta, and ABACUS. Additionally, it supports predictions of SU(2) equivariant Hamiltonians with spin-orbit coupling effects. HamGNN provides a high-fidelity approximation of DFT results and offers transferable predictions across material structures. This makes it ideal for high-throughput electronic structure calculations, accelerating computations on large-scale systems.
Contents:
- HamGNN User Guide
- HamGNN Introduction
- Environment Configuration and Installation
- Construction of graph_data.npz File
- Model Training Process
- Model Prediction Operation
- Band Structure Calculation
- Uni-HamGNN Universal Model
- HamGNN Parameter Details
- setup (Basic Settings)
- profiler_params (Profiler Parameters)
- dataset_params (Dataset Parameters)
- losses_metrics (Loss Functions and Evaluation Metrics)
- optim_params (Optimizer Parameters)
- output_nets.HamGNN_out (Output Network Parameters)
- representation_nets.HamGNN_pre (Representation Network Parameters)
- Parameter Adjustment Recommendations
- Model Structure
- GNN Core Layers
- Model Components
- Data Processing
- Configuration
- Utilities
Other
Tutorials, etc (todo)