# DeepLearningKit/DeepLearningKit

Open Source Deep Learning Framework for Apple's iOS, OS X and tvOS -

Repository: https://github.com/DeepLearningKit/DeepLearningKit
Canonical: https://ross.abutalabs.com/products/deeplearningkit
Homepage: http://deeplearningkit.org
Language: Swift
License: Apache-2.0
License Family: permissive
Last push: 2016-07-13T16:46:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3903, "days_push": 3703, "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 1059, forks 134 (observed 2026-08-28T04:03:25.608640+00:00)

## What it is
DeepLearningKit is an open-source deep learning framework for Apple's iOS, OS X and tvOS, written in Swift and using Metal for GPU-accelerated on-device inference. It supports running pre-trained deep convolutional neural networks (e.g. Caffe-trained models) for tasks like image recognition.

## Use cases
- run pre-trained deep learning models on iphone or ipad
- image recognition on ios with gpu acceleration
- use caffe-trained cnn models on apple devices
- on-device deep learning inference on mac
- run neural networks on apple tv

## When to choose
- you need GPU-accelerated CNN inference on iOS, macOS or tvOS with Swift
- you want to run Caffe-trained models on Apple devices without a server

## When to avoid
- you need training, not just inference
- you need modern framework support like Core ML, TensorFlow or PyTorch
- you need active maintenance or recent iOS support - the project has not been updated since 2016

## Facets
- artifact type: framework
- maturity: abandoned
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: deep-learning, machine-learning, mobile-development, apple-ecosystem, computer-vision
- platform: -
- tags: metal, tvos, caffe-models, on-device-inference, gpu-acceleration, ios, macos, swift, gpu

## Member repositories
- DeepLearningKit/DeepLearningKit (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:25.608640+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 2026-08-30T06:57:05.301027+00:00, confidence not recorded.
  - readme: https://github.com/DeepLearningKit/DeepLearningKit (fetched 2026-08-28T04:03:25.608640+00:00, sha e7fc5f5518d7)
  - homepage: http://deeplearningkit.org (fetched 2026-08-29T12:58:52.161826+00:00, sha 80fd210816b8)
  - site_page: https://deeplearningkit.org/about (fetched 2026-08-29T12:58:52.171175+00:00, sha f7720782c98f)
- Data as of 2026-08-30T08:39:29.467469+00:00.