# eldar/pose-tensorflow

Human Pose estimation with TensorFlow framework

Repository: https://github.com/eldar/pose-tensorflow
Canonical: https://ross.abutalabs.com/products/pose-tensorflow
Language: C++
License: LGPL-3.0
License Family: copyleft
Topics: tensorflow, pose-estimation, deep-learning
Last push: 2019-12-07T23:30:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3464, "days_push": 2461, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1141, forks 377 (observed 2026-08-28T04:03:44.577271+00:00)

## What it is
A TensorFlow implementation of the DeeperCut and ArtTrack algorithms for human body pose estimation, supporting both single-person and multi-person pose detection from images. It includes pre-trained models, demo scripts, and training code for research use.

## Use cases
- estimate human body keypoints from images
- detect poses of multiple people in a photo
- run DeeperCut pose estimation model
- track articulated multi-person poses in the wild
- train a custom pose estimation model on MPII or COCO
- reproduce results from the DeeperCut and ArtTrack papers

## When to choose
- you need to reproduce or build on the DeeperCut/ArtTrack research papers
- you want a TensorFlow 1.x-based multi-person pose estimation implementation with pre-trained models
- you are doing academic research on human pose estimation

## When to avoid
- you need a maintained library - the project has not been updated since 2019 and targets old TensorFlow versions
- you want modern pose estimation models like MoveNet, HRNet, or YOLO-pose
- you need production deployment or easy installation - the setup is research-grade with legacy dependencies

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: pose-estimation, tensorflow, deepercut, arttrack, multi-person-pose, human-pose, research-code, linux, gpu

## Member repositories
- eldar/pose-tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.577271+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:35:23.598889+00:00, confidence not recorded.
  - readme: https://github.com/eldar/pose-tensorflow (fetched 2026-08-28T04:03:44.577271+00:00, sha b3aad3f8e7d2)
- Data as of 2026-08-30T08:39:29.467469+00:00.