Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.

This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

This is a web demo for camera-based PPG sensing (rPPG).

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

An Android app running inference on Depth-Anything and Depth-Anything-V2

Embeddings from sentence-transformers in Android! Supports all-MiniLM-L6-V2, bge-small-en, snowflake-arctic models and more

Object detection inference with Roboflow Train models on NVIDIA Jetson devices.

Approach to implementing distributed training of an ML model: server/device training for iOS.

End-to-end on-device federated learning, "An On-Device Federated Learning System for SMS Spam Classification", IEEE MIT URTC 2022

SponsorMe is a project to help provide access to digital tools for learning, powered by on-device machine learning, innovation and willingness, to those people that have limited access to technology due to demographics, disabilities, economy or other multiple reasons.

Python ML library for person fall detection. Intended for IoT deployments with on-device inference and on-device transfer learning.

This repository is meant to be a playground for mobile deep learning.

Control your computer using hand gestures with AI, using Google's MediaPipe and OAK-D Lite camera.

An Android app where users draw a number and machine learning does the rest

*Resource Efficient Federated Deep Learning for IoT Security Monitoring

#AndroidDevChallenge

As described in "Towards Full On-Tiny-Device Learning: Guided Search for a Randomly Initialized Neural Network"

Rock-Paper-Scissors game, using On-Device MachineLearning.