A curated list of awesome embedded programming.
Embedded and mobile deep learning research resources
benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.
Read chapters directly from this repo - do not use GitHub Pages link.
POC visual search with smart glasses and Qdrant Edge.
Culturally-compliant video storage. Embeds searchable text chunks into pixelated media for lightning-fast semantic search. Zero-database, maximum compliance.
Speech Recognition using STM32 and Machine Learning
AcousticsLab is a cross-platform framework for sound and vibration analysis.
World's First NMS-Free YOLOv26n on ESP32-P4. Features end-to-end Int8 QAT and custom C++ optimizations achieving 30% faster inference than the official ESP-DL YOLOv11n (1.7s vs 2.4s).
MicroAI™ is an AI engine that can operate on low power edge and endpoint devices. It can learn the pattern of any and all time series data and can be used to detect anomalies or abnormalities, make one step ahead predictions/forecasts, and calculate the remaining life of entities (whether it is industrial machinery, small devices or the like).
Ultra-lightweight C++ inference engine for BitMamba-2 (1.58-bit SSM). Runs 1B models on consumer CPUs at 50+ tok/s using <700MB RAM. No heavy dependencies.
This is an open source project on the deployment of deep learning to embedded microprocessors. The project establishes a data set for obstacle recognition of blind travel environment, and trains a simplified MoblieNet model in TensorFlow. Finally, the binary file of the model is deployed on the UNCLEO-STM32H7A3ZIT-Q development board to realize …
A list of production-ready models for resource-constrained devices.
🔥 ACM Multimedia Asia 2023 (Tainan, Taiwan) – Grand Challenges
Guide to deploying neural networks in VST plugins, with a specific focus on embedded devices using the Elk Audio OS
MicroAI™ is an AI engine that can operate on low power edge and endpoint devices. It can learn the pattern of any and all time series data and can be used to detect anomalies or abnormalities, make one step ahead predictions/forecasts, and calculate the remaining life of entities (whether it is industrial machinery, small devices or the like).
Measure power consumption of your edge devices without Voltage Throttling!
JUCE Template plugins to use TensorFlow lite for deep learning inference
Swift Package wrapping WhisperCore and whisper.xcframeworks for on-device speech-to-text transcription on iOS.
Add a description, image, and links to the embedded-ai topic page so that developers can more easily learn about it.
To associate your repository with the embedded-ai topic, visit your repo's landing page and select "manage topics."