deepmd-python-inference

Official

Inference for DeePMD-kit models in Python efficiently.

Authorjinzhezenggroup
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Load a trained DeePMD-kit model in Python and perform fast predictions of energy, forces, and virial for atomic configurations. It also covers descriptor evaluation and cross-model comparison using the DeepPot API, plus CLI tools for batch testing.

Core Features & Use Cases

  • Inference: load PyTorch (.pth) or TensorFlow (.pb) models, or built-in pretrained models, and obtain energy, forces, and virial.
  • Descriptor evaluation: compute atomic environment descriptors from configurations.
  • Model comparison: compute model deviation across multiple models; batch evaluation for datasets.
  • CLI testing: run dp test-like workflows for labeled data and benchmarking.

Quick Start

Run a Python script to load a trained or pretrained DeePMD-kit model and perform a simple inference on a sample configuration.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: deepmd-python-inference
Download link: https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/archive/main.zip#deepmd-python-inference

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.