# apple/turicreate

Turi Create simplifies the development of custom machine learning models.

Repository: https://github.com/apple/turicreate
Canonical: https://ross.abutalabs.com/products/turicreate
Language: C++
License: BSD-3-Clause
License Family: permissive
Topics: machine-learning, deep-learning, python
Archived: true
Last push: 2023-11-01T06:14:06+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3198, "days_push": 1036, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11159, forks 1118 (observed 2026-08-28T04:10:46.269051+00:00)

## What it is
Turi Create is a Python library from Apple that simplifies building custom machine learning models for tasks like image classification, object detection, recommendations, and activity classification. Trained models can be exported to Core ML for deployment in iOS, macOS, watchOS, and tvOS apps.

## Use cases
- train an image classifier without ML expertise
- build a recommender system for my app
- detect objects in images with a few lines of Python
- export a machine learning model to Core ML for iOS
- classify sounds or sensor activity data
- find visually similar images
- stylize images with style transfer

## When to choose
- you want easy, high-level APIs for common ML tasks
- you target Apple platforms and need Core ML export
- you work with images, text, audio, or sensor data on a single machine

## When to avoid
- you need cutting-edge deep learning research features or custom architectures
- you require active development and recent updates
- you need distributed training across clusters

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision, audio-processing, nlp, data-science
- domain: machine-learning, deep-learning, computer-vision, mobile-development, apple-ecosystem
- platform: python
- tags: core-ml, recommender-systems, object-detection, style-transfer, apple, natural-language-processing, macos, linux, ios

## Member repositories
- apple/turicreate (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.269051+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 2026-08-29T17:16:44.283829+00:00, confidence not recorded.
  - readme: https://github.com/apple/turicreate (fetched 2026-08-28T04:10:46.269051+00:00, sha b2439ced6524)
- Data as of 2026-08-30T08:39:29.467469+00:00.