# open-mmlab/playground

A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

Repository: https://github.com/open-mmlab/playground
Canonical: https://ross.abutalabs.com/products/open-mmlab-playground
Language: Python
License: Apache-2.0
License Family: permissive
Topics: mmdetection, mmpose, mmrotate, sam, mmocr, openmmlab
Last push: 2024-03-29T10:17:22+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 88
- inputs: {"age_days": 1241, "days_push": 887, "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 1236, forks 128 (observed 2026-08-28T04:04:05.086404+00:00)

## What it is
OpenMMLab Playground is a central hub collecting and showcasing community projects that extend OpenMMLab libraries with Segment Anything Model (SAM) and other computer vision features. It provides example code and demos combining detection, segmentation, pose estimation, and OCR tools from the OpenMMLab ecosystem.

## Use cases
- label images automatically with SAM and mmdetection
- segment anything in photos using open-source models
- combine SAM with object detection for annotation
- run pose estimation demos with OpenMMLab
- extract text from images with MMOCR and SAM
- build computer vision apps with OpenMMLab tools

## When to choose
- you already use OpenMMLab libraries and want SAM integrations
- you need reference implementations for detection plus segmentation workflows
- you want community examples for auto-labeling and CV demos

## When to avoid
- you need a production-ready supported product rather than example projects
- you don't use the OpenMMLab ecosystem
- you need a stable API with long-term maintenance guarantees

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, developer-tools
- domain: computer-vision, machine-learning, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: segment-anything, openmmlab, mmdetection, mmpose, mmocr, sam, demo-projects, aigc

## Member repositories
- open-mmlab/playground (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:05.086404+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 2026-08-30T08:22:00.036364+00:00, confidence not recorded.
  - readme: https://github.com/open-mmlab/playground (fetched 2026-08-28T04:04:05.086404+00:00, sha d754f41ad0f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.