skills.rest
jinzhezenggroup
jinzhezenggroupOFFICIAL
Explore all skills by this author →
WebsiteGitHub

deepmd-train-se-e2-a

Train DeePMD-kit models with SE_E2_A descriptor and PyTorch backend.

124|25|Updated Feb 20, 2026
Search Tags:#gpu#training#molecular-simulation#deepmd-kit#descriptor-se_e2_a#deep-potentials
One-click install
npx skills add https://github.com/jinzhezenggroup/computational-chemistry-agent-skills --skill deepmd-train-se-e2-a
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deepmd-train-se-e2-a
Source: https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/main/machine-learning-potentials/deepmd-train-se-e2-a
Command: npx skills add https://github.com/jinzhezenggroup/computational-chemistry-agent-skills --skill deepmd-train-se-e2-a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Train a DeePMD-kit model to learn a classical deep potential for a specified system using the SE_E2_A descriptor and PyTorch backend.

Core Features & Use Cases

  • Prepare training input.json in the DeePMD format (type_map, data, and network configuration).
  • Run training with dp --pt train and monitor learning curves.
  • Freeze the trained model to a .pth file and optionally test it with dp test.

Quick Start

Prepare training data paths and element types, then instruct the agent to generate a complete input.json and start training with dp --pt train.

Frequently Asked Questions about deepmd-train-se-e2-a

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I train a DeePMD-kit model with the SE_E2_A descriptor using PyTorch?▼

To train a DeePMD-kit model with the SE_E2_A descriptor, prepare a valid input.json with correct type_map and data paths, then execute training using the dp --pt train command to generate a deep potential.

What is needed to prepare DeePMD-kit training data for molecular simulation?▼

DeePMD-kit training data requires appropriate molecular simulation datasets formatted specifically for DeePMD, along with a correctly defined type_map for the system before generating the input.json configuration.

Can I run DeePMD-kit training on a GPU with the PyTorch backend?▼

Yes, you can run DeePMD-kit training on a GPU by configuring the input.json for the PyTorch backend, using the dp --pt train command to process your molecular simulation data.

How do I freeze and test a trained deep potential model?▼

After training a deep potential model, you freeze it into a .pth file and optionally validate its accuracy by running the dp test command on your prepared DeePMD formatted data.

What should I do if my DeePMD-kit learning curves are not converging?▼

If your DeePMD-kit learning curves are not converging, monitor the training output from dp --pt train to adjust network configurations in input.json and verify the DeePMD formatted training data.

Related Skills

Explore More Education & Research Skills→
jinzhezenggroupjinzhezenggroup
124

deepmd-train-dpa3

Train DeePMD-kit models with the DPA3 descriptor using dp --pt train.

Official
Advanced
shushuznshushuzn
4

shap

Compute SHAP values and generate interpretability visualizations for machine learning models.

Community
Advanced
jinzhezenggroupjinzhezenggroup
124

deepmd-finetune-dpa3

Fine-tunes a pre-trained DPA3 model on a downstream dataset using DeePMD-kit.

Official
Advanced
Hello-QMHello-QM
181

lammps-deepmd

Run LAMMPS molecular dynamics with DeePMD-kit potentials and frozen .pb models.

Community
Advanced