jetpacapp/DeepBeliefSDK

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2853 stars · 426 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity abandoned

machine-learning deep-learning computer-vision image-processing sdk machine-learning computer-vision image-processing mobile-development cross-platform cpp image-recognition convolutional-neural-network on-device-inference embedded-vision opencv raspberry-pi legacy ios android linux macos javascript

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jetpacapp/DeepBeliefSDK")