Metadata-Version: 2.4
Name: lightning-pose-app
Version: 2.3.0.2
Summary: Lightning Pose user interface for labeling, training, and visualization
License-Expression: MIT
Author: Karan Sikka
Requires-Python: >=3.10
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Provides-Extra: dev
Requires-Dist: PyYAML (>=6.0.2,<6.1.0)
Requires-Dist: aiofiles (>=24.1.0,<24.2.0)
Requires-Dist: aniposelib (>=0.7.2,<0.8.0)
Requires-Dist: fastapi (>=0.116.0,<0.117.0)
Requires-Dist: honcho (>=2.0,<3.0)
Requires-Dist: honcho ; extra == "dev"
Requires-Dist: httpx (>=0.28.0,<0.29.0) ; extra == "dev"
Requires-Dist: omegaconf (>=2.3.0,<2.4.0)
Requires-Dist: opencv-python (>=4.12.0.88,<4.13.0.0)
Requires-Dist: pandas (>=2.3.0,<2.4.0)
Requires-Dist: portalocker (>=3.2.0,<3.3.0)
Requires-Dist: pre-commit ; extra == "dev"
Requires-Dist: psutil (>=7.0.0,<7.1.0)
Requires-Dist: pydantic-settings
Requires-Dist: pytest (>=8.4.0,<8.5.0) ; extra == "dev"
Requires-Dist: pytest-asyncio (>=1.0.0,<1.1.0) ; extra == "dev"
Requires-Dist: pytest-mock (>=3.14.0,<3.15.0) ; extra == "dev"
Requires-Dist: python-multipart
Requires-Dist: scikit-learn (>=1.7.1,<1.8.0)
Requires-Dist: tomli (>=2.2.0,<2.3.0)
Requires-Dist: tomli_w (>=1.2.0,<1.3.0)
Requires-Dist: tqdm (>=4.67.1,<4.68.0)
Requires-Dist: uvicorn[standard] (>=0.35.0,<0.36.0)
Requires-Dist: wcmatch (>=10.0,<11.0)
Project-URL: Documentation, https://lightning-pose.readthedocs.io/
Project-URL: Repository, https://github.com/paninski-lab/lightning-pose-app
Description-Content-Type: text/markdown

# Lightning Pose App

[![PyPI version](https://img.shields.io/pypi/v/lightning-pose-app.svg)](https://pypi.org/project/lightning-pose-app/)

Web-based GUI for [Lightning Pose](https://github.com/paninski-lab/lightning-pose) —
a semi-supervised pose estimation library for single- and multi-view animal tracking.

The app provides an end-to-end workflow:

- **Project management** — create and organize pose estimation projects
- **Labeler** — extract video frames and annotate keypoints
- **Models** — configure and launch model training, monitor progress in real time
- **Inference** — run trained models across video sessions
- **Viewer** — inspect predictions overlaid on video with per-keypoint controls

## Installation

Install Lightning Pose and the app:

```bash
pip install lightning-pose lightning-pose-app
```

## Usage

```bash
litpose run_app
```

Then open `http://localhost:4200` in your browser.

## Documentation

Full documentation, including installation guides and tutorials:

👉 **[https://lightning-pose.readthedocs.io](https://lightning-pose.readthedocs.io)**

## Requirements

- Linux or WSL (Windows Subsystem for Linux)
- NVIDIA GPU with CUDA 12+
- Python 3.10–3.12

## Source

This package contains only the app server and compiled UI.
The core modeling library lives at
[paninski-lab/lightning-pose](https://github.com/paninski-lab/lightning-pose).

