# tensorflow/tfjs-models

Pretrained models for TensorFlow.js

Repository: https://github.com/tensorflow/tfjs-models
Canonical: https://ross.abutalabs.com/products/tfjs-models
Homepage: https://js.tensorflow.org
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-06-23T19:24:12+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 8, longevity 100
- inputs: {"age_days": 3074, "days_push": 71, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14793, forks 4374 (observed 2026-08-28T04:11:07.698666+00:00)

## What it is
A collection of pre-trained machine learning models ported to TensorFlow.js, published as npm packages for use in JavaScript projects. Models cover image classification, object detection, pose and hand tracking, and more, with APIs designed to hide tensor complexity from non-ML experts.

## Use cases
- classify images in the browser
- detect human pose from webcam video
- track hand movements in real time
- detect objects in images with coco-ssd
- run pretrained ML models in Node.js
- fine-tune models with transfer learning in JavaScript

## When to choose
- you need out-of-the-box ML inference in a browser or Node.js app
- you want pretrained models without ML expertise
- you're building interactive webcam or media experiences with TensorFlow.js

## When to avoid
- you need to train models from scratch in Python
- you require server-side GPU-heavy inference at scale
- you need a model not included in the repository

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, nlp, speech-recognition
- domain: machine-learning, deep-learning, computer-vision, web-development, frontend
- platform: browser
- tags: tensorflowjs, pretrained-models, pose-detection, object-detection, image-classification, transfer-learning, npm-packages, nodejs, javascript, web

## Member repositories
- tensorflow/tfjs-models (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.698666+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 2026-08-29T17:07:09.591656+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/tfjs-models (fetched 2026-08-28T04:11:07.698666+00:00, sha f3be73905d6d)
  - homepage: https://js.tensorflow.org (fetched 2026-08-29T08:05:41.444695+00:00, sha ff013fdcc87d)
  - site_page: https://www.tensorflow.org/install (fetched 2026-08-29T08:05:41.454463+00:00, sha 584a762da891)
  - site_page: https://www.tensorflow.org/tfx/api_docs (fetched 2026-08-29T08:05:41.459606+00:00, sha 6977825696fe)
  - site_page: https://www.tensorflow.org/about (fetched 2026-08-29T08:05:41.464866+00:00, sha 817250744d91)
  - site_page: https://www.tensorflow.org/about/case-studies (fetched 2026-08-29T08:05:41.466937+00:00, sha e6701029eec0)
  - site_page: https://www.tensorflow.org/about/bib (fetched 2026-08-29T08:05:41.468898+00:00, sha 5ca8943386b9)
  - site_page: https://www.tensorflow.org/community/contribute (fetched 2026-08-29T08:05:41.462390+00:00, sha 77d394fa76e7)
- Data as of 2026-08-30T08:39:29.467469+00:00.