# microsoft/human-pose-estimation.pytorch

The project is an official implement of our ECCV2018 paper  "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

Repository: https://github.com/microsoft/human-pose-estimation.pytorch
Canonical: https://ross.abutalabs.com/products/human-pose-estimationpytorch
Language: Python
License: MIT
License Family: permissive
Topics: human-pose-estimation, deep-learning, coco-keypoints-detection, mpii-dataset, mscoco-keypoint
Archived: true
Last push: 2022-11-28T19:11:04+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2954, "days_push": 1374, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3008, forks 596 (observed 2026-08-28T04:07:37.709890+00:00)

## What it is
Official PyTorch implementation of the ECCV 2018 paper 'Simple Baselines for Human Pose Estimation and Tracking' from Microsoft. It provides ResNet-based models for human keypoint detection on COCO and MPII benchmarks with pretrained weights for research.

## Use cases
- detect human body keypoints in images
- estimate human pose from photos
- run 2D pose estimation on COCO dataset
- evaluate keypoint detection models on MPII
- reproduce simple baseline pose estimation results
- build pose tracking pipelines for multi-person videos

## When to choose
- you need a well-tested reference implementation of the Simple Baseline pose estimation method
- you want pretrained ResNet models for COCO or MPII keypoint detection
- you are benchmarking new pose estimation ideas against a simple strong baseline

## When to avoid
- you need real-time pose estimation on edge devices
- you want 3D pose estimation rather than 2D keypoints
- you need actively maintained code with recent framework support

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python
- tags: human-pose-estimation, keypoint-detection, pytorch, coco, mpii, resnet, eccv2018, pose-tracking, linux, gpu

## Member repositories
- microsoft/human-pose-estimation.pytorch (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.709890+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 2026-08-29T18:47:23.524712+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/human-pose-estimation.pytorch (fetched 2026-08-28T04:07:37.709890+00:00, sha b6626375e40c)
- Data as of 2026-08-30T08:39:29.467469+00:00.