# jetpacapp/DeepBeliefSDK

The SDK for Jetpac's iOS Deep Belief image recognition framework

Repository: https://github.com/jetpacapp/DeepBeliefSDK
Canonical: https://ross.abutalabs.com/products/deepbeliefsdk
Language: JavaScript
License: NOASSERTION
License Family: other
Last push: 2019-11-06T19:25:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4536, "days_push": 2492, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2853, forks 426 (observed 2026-08-28T04:07:25.726917+00:00)

## What it is
Jetpac's Deep Belief SDK, a cross-platform image recognition framework implementing the AlexNet convolutional neural network architecture, optimized to run on mobile and embedded devices like iPhone, Android, Raspberry Pi, and Beaglebone. It provides libraries and examples for running local, low-power image classification in under 300ms on devices like the iPhone 5S.

## Use cases
- classify images on an iPhone without a server
- run a convolutional neural network on a Raspberry Pi
- add object recognition to an Android app
- do live camera object tagging on mobile
- integrate deep learning image recognition with OpenCV
- run image classification on a Beaglebone Black

## When to choose
- you need on-device image recognition on old mobile or embedded hardware with no cloud dependency
- you are maintaining a legacy project already built on this SDK
- you want a lightweight C-based CNN runtime for very constrained devices

## When to avoid
- you are starting a new project - modern frameworks like TensorFlow Lite or Core ML are far more accurate and actively maintained
- you need state-of-the-art model accuracy
- you need official support, updates, or a clear license

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing, sdk
- domain: machine-learning, computer-vision, image-processing, mobile-development, cross-platform
- platform: cpp
- tags: image-recognition, convolutional-neural-network, on-device-inference, embedded-vision, opencv, raspberry-pi, legacy, ios, android, linux, macos, javascript

## Member repositories
- jetpacapp/DeepBeliefSDK (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:25.726917+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 2026-08-29T18:48:31.014044+00:00, confidence not recorded.
  - readme: https://github.com/jetpacapp/DeepBeliefSDK (fetched 2026-08-28T04:07:25.726917+00:00, sha 7ab3e7ea8f53)
- Data as of 2026-08-30T08:39:29.467469+00:00.