Getting Started

In this text, we will call the deep neural network that is used to represent the interatomic interactions (Deep Potential) the model. The typical procedure of using DeePMD-kit is

• 1. Easy install
  • 1.1. Install DeePMD-kit in 1s
  • 1.2. Install off-line packages
  • 1.3. Install with conda
  • 1.4. Install with docker
  • 1.5. Install Python interface with pip
• 2. DeePMD-kit Quick Start Tutorial
  • 2.1. Task
  • 2.2. Background
  • 2.3. Practice
• 3. Distilling a Cyclohexane Potential from a DPA3 Pretrained Model
  • 3.1. Install the required packages
  • 3.2. Import dependencies
  • 3.3. Prepare the Teacher model weights
  • 3.4. Prepare the distillation dataset
  • 3.5. Generate the Student training configuration
  • 3.6. Train the Student model
  • 3.7. Plot the training curve
  • 3.8. Freeze and evaluate the Student model on the distillation dataset
  • 3.9. Run MD with the distilled Student model
  • 3.10. Visualize representative Student MD structures