![](https://github.com/danbider/lightning-pose/raw/main/docs/images/LightningPose_horizontal_light.png)
[![Discord](https://img.shields.io/discord/1103381776895856720)](https://discord.gg/tDUPdRj4BM)
![GitHub](https://img.shields.io/github/license/danbider/lightning-pose)
[![Documentation Status](https://readthedocs.org/projects/lightning-pose/badge/?version=latest)](https://lightning-pose.readthedocs.io/en/latest/?badge=latest)
![PyPI](https://img.shields.io/pypi/v/lightning-pose)
Pose estimation models implemented in **Pytorch Lightning**, supporting massively accelerated training on _unlabeled_ videos using **NVIDIA DALI**.
The whole process is orchestrated by **Hydra**.
Models can be evaluated with **TensorBoard**, **FiftyOne**, and **Streamlit**.
Preprint: [Lightning Pose: improved animal pose estimation via semi-supervised learning, Bayesian ensembling, and cloud-native open-source tools](https://www.biorxiv.org/content/10.1101/2023.04.28.538703v1)
## Try our demo!
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/danbider/lightning-pose/blob/main/scripts/litpose_training_demo.ipynb)
Train a network on an example dataset and visualize the results in Google Colab.
## Getting Started
Please see the [Lightning Pose documentation](https://lightning-pose.readthedocs.io/)
for installation instructions and user guides.
Note that the Lightning Pose package provides tools for training and evaluating models on
_already labeled data_ and unlabeled video clips.
We also offer a [browser-based application](https://github.com/Lightning-Universe/Pose-app) that
supports the full life cycle of a pose estimation project, from data annotation to model training
to diagnostic visualizations.
## Community
Lightning Pose is primarily maintained by
[Dan Biderman](https://dan-biderman.netlify.app) (Columbia University)
and
[Matt Whiteway](https://themattinthehatt.github.io/) (Columbia University).
Lightning Pose is under active development and we welcome community contributions.
Whether you want to implement some of your own ideas or help out with our [development roadmap](docs/roadmap.md), please get in touch with us on Discord (see contributing guidelines [here](CONTRIBUTING.md)).
Raw data
{
"_id": null,
"home_page": "https://github.com/danbider/lightning-pose",
"name": "lightning-pose",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "machine learning, deep learning, computer_vision",
"author": "Dan Biderman and Matt Whiteway",
"author_email": "danbider@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/19/5c/c7618e9421b66686ca7feb33d1eda8bf2313ab0ce40f12c5a533119741eb/lightning-pose-1.3.1.tar.gz",
"platform": null,
"description": "![](https://github.com/danbider/lightning-pose/raw/main/docs/images/LightningPose_horizontal_light.png)\n\n[![Discord](https://img.shields.io/discord/1103381776895856720)](https://discord.gg/tDUPdRj4BM)\n![GitHub](https://img.shields.io/github/license/danbider/lightning-pose)\n[![Documentation Status](https://readthedocs.org/projects/lightning-pose/badge/?version=latest)](https://lightning-pose.readthedocs.io/en/latest/?badge=latest)\n![PyPI](https://img.shields.io/pypi/v/lightning-pose)\n\nPose estimation models implemented in **Pytorch Lightning**, supporting massively accelerated training on _unlabeled_ videos using **NVIDIA DALI**. \nThe whole process is orchestrated by **Hydra**. \nModels can be evaluated with **TensorBoard**, **FiftyOne**, and **Streamlit**.\n\nPreprint: [Lightning Pose: improved animal pose estimation via semi-supervised learning, Bayesian ensembling, and cloud-native open-source tools](https://www.biorxiv.org/content/10.1101/2023.04.28.538703v1)\n\n## Try our demo!\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/danbider/lightning-pose/blob/main/scripts/litpose_training_demo.ipynb)\n\nTrain a network on an example dataset and visualize the results in Google Colab.\n\n## Getting Started\nPlease see the [Lightning Pose documentation](https://lightning-pose.readthedocs.io/) \nfor installation instructions and user guides.\nNote that the Lightning Pose package provides tools for training and evaluating models on \n_already labeled data_ and unlabeled video clips. \n\nWe also offer a [browser-based application](https://github.com/Lightning-Universe/Pose-app) that \nsupports the full life cycle of a pose estimation project, from data annotation to model training \nto diagnostic visualizations.\n\n## Community\n\nLightning Pose is primarily maintained by \n[Dan Biderman](https://dan-biderman.netlify.app) (Columbia University) \nand \n[Matt Whiteway](https://themattinthehatt.github.io/) (Columbia University). \n\nLightning Pose is under active development and we welcome community contributions.\nWhether you want to implement some of your own ideas or help out with our [development roadmap](docs/roadmap.md), please get in touch with us on Discord (see contributing guidelines [here](CONTRIBUTING.md)). \n",
"bugtrack_url": null,
"license": null,
"summary": "Semi-supervised pose estimation using pytorch lightning",
"version": "1.3.1",
"project_urls": {
"Homepage": "https://github.com/danbider/lightning-pose"
},
"split_keywords": [
"machine learning",
" deep learning",
" computer_vision"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f33b7a124f9edd2bd6dc88b6252d43927e98cf30c2a258bb9c180cdbe8d1761e",
"md5": "20a7fc3c07abf5c39d73e84b8feb18c3",
"sha256": "3394ee8e9344e857762ccb3668448faab050986ea4877ff76a5854eed8dfc394"
},
"downloads": -1,
"filename": "lightning_pose-1.3.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "20a7fc3c07abf5c39d73e84b8feb18c3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 7335891,
"upload_time": "2024-04-17T16:51:07",
"upload_time_iso_8601": "2024-04-17T16:51:07.923473Z",
"url": "https://files.pythonhosted.org/packages/f3/3b/7a124f9edd2bd6dc88b6252d43927e98cf30c2a258bb9c180cdbe8d1761e/lightning_pose-1.3.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "195cc7618e9421b66686ca7feb33d1eda8bf2313ab0ce40f12c5a533119741eb",
"md5": "1fcc208559f0ffce4d3450e95adba875",
"sha256": "4ee358d8a4bc6fdf378a911a331104a78f4154c50a85e57b3e779256e43fa9a1"
},
"downloads": -1,
"filename": "lightning-pose-1.3.1.tar.gz",
"has_sig": false,
"md5_digest": "1fcc208559f0ffce4d3450e95adba875",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 10110499,
"upload_time": "2024-04-17T16:51:22",
"upload_time_iso_8601": "2024-04-17T16:51:22.426961Z",
"url": "https://files.pythonhosted.org/packages/19/5c/c7618e9421b66686ca7feb33d1eda8bf2313ab0ce40f12c5a533119741eb/lightning-pose-1.3.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-17 16:51:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "danbider",
"github_project": "lightning-pose",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "lightning-pose"
}