GDPy Documentation

GDPy stands for Generating Deep Potential with Python, including a set of tools and Python modules to automate the structure exploration and the model training for machine learning interatomic potentials (MLIPs). It is developed and maintained by Jiayan Xu under supervision of Prof. P. Hu at Queen’s University Belfast.

Supported Potentials

eann, deepmd, lasp, nequip / allegro

Supported Expeditions

molecular dynamics, genetic algorithm, grand canonical monte carlo, graph-theory adsorbate configuration, artificial force induced reaction

Introduction:

• About
  • Features
  • Overview
• Installation
  • Requirements
  • From Source, Conda or Pip

Basic Guides:

• Getting Started
  • Units
  • Potential
  • Driver
  • Scheduler
  • Worker
• Potentials
  • Formulations
  • Simulation
  • Training
• Trainers
  • Related Commands
  • Configuration File
  • List of Trainers
  • Use Scheduler
• Computations
  • Potential
  • Driver
  • Worker
• Builders
  • Related Commands
  • List of Builders
  • Related Components
• Selections
  • List of Selectors
  • Property
  • Graph
• Expeditions
  • Related Commands
  • List of Expeditions
• Tutorials
  • List of Tutorials

Advanced Guides:

• Sessions
  • Related Commands
  • Minimal Configuration
  • Variables
  • Operations
• Workflows
  • List of Workflows

Developer Guides:

• Extensions
  • Custom Potential

Gallery:

• Applications