Metadata-Version: 2.1
Name: openpifpaf
Version: 0.12.8
Summary: PifPaf: Composite Fields for Human Pose Estimation
Home-page: https://github.com/openpifpaf/openpifpaf
Author: Sven Kreiss
Author-email: research@svenkreiss.com
License: GNU AGPLv3
Platform: UNKNOWN
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: importlib-metadata (!=3.8.0)
Requires-Dist: numpy (>=1.16)
Requires-Dist: pysparkling
Requires-Dist: python-json-logger
Requires-Dist: scipy
Requires-Dist: torch (>=1.7.1)
Requires-Dist: torchvision (>=0.8.2)
Requires-Dist: pillow
Requires-Dist: dataclasses ; python_version < "3.7"
Provides-Extra: coreml
Requires-Dist: coremltools (>=4.1) ; extra == 'coreml'
Provides-Extra: dev
Requires-Dist: cython ; extra == 'dev'
Requires-Dist: flameprof ; extra == 'dev'
Requires-Dist: jupyter-book (>=0.9.1) ; extra == 'dev'
Requires-Dist: matplotlib (>=3.3) ; extra == 'dev'
Requires-Dist: nbdime ; extra == 'dev'
Requires-Dist: nbstripout ; extra == 'dev'
Requires-Dist: sphinx-book-theme ; extra == 'dev'
Requires-Dist: wheel ; extra == 'dev'
Provides-Extra: onnx
Requires-Dist: onnx ; extra == 'onnx'
Requires-Dist: onnxruntime ; extra == 'onnx'
Requires-Dist: onnx-simplifier (>=0.2.9) ; extra == 'onnx'
Provides-Extra: test
Requires-Dist: nbconvert ; extra == 'test'
Requires-Dist: nbval ; extra == 'test'
Requires-Dist: onnx ; extra == 'test'
Requires-Dist: onnxruntime ; extra == 'test'
Requires-Dist: onnx-simplifier (>=0.2.9) ; extra == 'test'
Requires-Dist: pylint ; extra == 'test'
Requires-Dist: pycodestyle ; extra == 'test'
Requires-Dist: pytest ; extra == 'test'
Requires-Dist: opencv-python ; extra == 'test'
Requires-Dist: thop ; extra == 'test'
Provides-Extra: train
Requires-Dist: matplotlib (>=3.3) ; extra == 'train'
Requires-Dist: pycocotools (>=2.0.1) ; extra == 'train'

# openpifpaf

Continuously tested on Linux, MacOS and Windows:
[![Tests](https://github.com/openpifpaf/openpifpaf/workflows/Tests/badge.svg?branch=main)](https://github.com/openpifpaf/openpifpaf/actions?query=workflow%3ATests)
[![deploy-guide](https://github.com/openpifpaf/openpifpaf/workflows/deploy-guide/badge.svg)](https://github.com/openpifpaf/openpifpaf/actions?query=workflow%3Adeploy-guide)
[![Downloads](https://pepy.tech/badge/openpifpaf)](https://pepy.tech/project/openpifpaf)
<br />
[__New__ 2021 paper](https://arxiv.org/abs/2103.02440):

> __OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association__<br />
> _[Sven Kreiss](https://www.svenkreiss.com), [Lorenzo Bertoni](https://scholar.google.com/citations?user=f-4YHeMAAAAJ&hl=en), [Alexandre Alahi](https://scholar.google.com/citations?user=UIhXQ64AAAAJ&hl=en)_, 2021.
>
> Many image-based perception tasks can be formulated as detecting, associating
> and tracking semantic keypoints, e.g., human body pose estimation and tracking.
> In this work, we present a general framework that jointly detects and forms
> spatio-temporal keypoint associations in a single stage, making this the first
> real-time pose detection and tracking algorithm. We present a generic neural
> network architecture that uses Composite Fields to detect and construct a
> spatio-temporal pose which is a single, connected graph whose nodes are the
> semantic keypoints (e.g., a person's body joints) in multiple frames. For the
> temporal associations, we introduce the Temporal Composite Association Field
> (TCAF) which requires an extended network architecture and training method
> beyond previous Composite Fields. Our experiments show competitive accuracy
> while being an order of magnitude faster on multiple publicly available datasets
> such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show
> that our method generalizes to any class of semantic keypoints such as car and
> animal parts to provide a holistic perception framework that is well suited for
> urban mobility such as self-driving cars and delivery robots.

Previous [CVPR 2019 paper](http://openaccess.thecvf.com/content_CVPR_2019/html/Kreiss_PifPaf_Composite_Fields_for_Human_Pose_Estimation_CVPR_2019_paper.html).


# Example

![example image with overlaid pose predictions](https://github.com/openpifpaf/openpifpaf/raw/main/docs/coco/000000081988.jpg.predictions.jpeg)

Image credit: "[Learning to surf](https://www.flickr.com/photos/fotologic/6038911779/in/photostream/)" by fotologic which is licensed under [CC-BY-2.0].<br />
Created with:
```sh
pip3 install openpifpaf matplotlib
python3 -m openpifpaf.predict docs/coco/000000081988.jpg --image-min-dpi=200 --show-file-extension=jpeg --image-output
```


# [Guide](https://openpifpaf.github.io/intro.html)

Continue to our __[OpenPifPaf Guide](https://openpifpaf.github.io/intro.html)__.

For developers, there is also the
__[DEV Guide](https://openpifpaf.github.io/dev/intro.html)__
which is the same guide but based on the latest code in the `main` branch.


[CC-BY-2.0]: https://creativecommons.org/licenses/by/2.0/


# Commercial License

This software is available for licensing via the EPFL Technology Transfer
Office (https://tto.epfl.ch/, info.tto@epfl.ch).


