edge-ai

Edge AI resources

A curated collection of resources and hardware components for deploying artificial intelligence at the edge in embedded devices

A curated list of resources for embedded AI

GitHub

371 stars
25 watching
43 forks
last commit: almost 2 years ago
Linked from 1 awesome list

artificial-intelligenceawesome-listedge-computingembedded

Hardware

OpenMVA camera that runs with MicroPython on ARM Cortex M6/M7 and great support for computer vision algorithms. Now with
JeVoisA TensorFlow-enabled camera module
Edge TPUGoogle’s purpose-built ASIC designed to run inference at the edge
MovidiusIntel's family of SoCs designed specifically for low power on-device computer vision and neural network applications

Hardware / Movidius

UP AI EdgeLine of products based on Intel Movidius VPUs (including Myriad 2 and Myriad X) and Intel Cyclone FPGAs
DepthAIAn embedded platform for combining Depth and AI, built around Myriad X

Hardware

NVIDIA JetsonHigh-performance embedded system-on-module to unlock deep learning, computer vision, GPU computing, and graphics in network-constrained environments
Artificial Intelligence Radio - Transceiver (AIR-T)High-performance SDR seamlessly integrated with state-of-the-art deep learning hardware
Kendryte K210Dual-core, RISC-V chip with convolutional neural network acceleration using 64 KLUs (Kendryte Arithmetic Logic Unit)

Hardware / Kendryte K210

Sipeed M1Based on the Kendryte K210, the module adds WiFi connectivity and an external flash memory
M5StickVAIoT(AI+IoT) Camera powered by Kendryte K210
UNIT-VAI Camera powered by Kendryte K210 (lower-end M5StickV)

Hardware

Kendryte K510Tri-core RISC-V processor clocked with AI accelerators
GreenWaves GAP8RISC-V-based chip with hardware acceleration for convolutional operations
GreenWaves GAP9RISC-V-based chip primarily focused on AI-centric audio processing
Ultra96Embedded development platform featuring a Xilinx UltraScale+ MPSoC FPGA
Apollo3 BlueSparkFun Edge Development Board powered by a Cortex M4 from Ambiq Micro
Google CoralPlatform of hardware components and software tools for local AI products based on Google Edge TPU coprocessor
Gyrfalcon Technology LighspeeurFamily of chips optimized for edge computing
ARM microNPUProcessors designed to accelerate ML inference (being the first one the Ethos-U55)
Espressif ESP32-S3SoC similar to the well-known ESP32 with support for AI acceleration (among many other interesting differences)
Maxim MAX78000SoC based on a Cortex-M4 that includes a CNN accelerator
Beagleboard BeagleVOpen Source RISC-V-based Linux board that includes a Neural Network Engine
Syntiant TinyMLDevelopment kit based on the Syntiant NDP101 Neural Decision Processor and a SAMD21 Cortex-M0+

Software

TensorFlow LiteLightweight solution for mobile and embedded devices which enables on-device machine learning inference with low latency and a small binary size
TensorFlow Lite for MicrocontrollersPort of TF Lite for microcontrollers and other devices with only kilobytes of memory. Born from a
Embedded Learning Library (ELL)2,288over 2 years agoMicrosoft's library to deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers
uTensor1,742almost 2 years agoAI inference library based on mbed (an RTOS for ARM chipsets) and TensorFlow
CMSIS NNA collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Cortex-M processor cores
ARM Compute LibrarySet of optimized functions for image processing, computer vision, and machine learning
Qualcomm Neural Processing SDK for AILibraries to developers run NN models on Snapdragon mobile platforms taking advantage of the CPU, GPU and/or DSP
ST X-CUBE-AIToolkit for generating NN optimiezed for STM32 MCUs
ST NanoEdgeAIStudioTool that generates a model to be loaded into an STM32 MCU
Neural Network on Microcontroller (NNoM)965over 2 years agoHigher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN
nncase757almost 2 years agoOpen deep learning compiler stack for Kendryte K210 AI accelerator
deepC568almost 4 years agoDeep learning compiler and inference framework targeted to embedded platform
uTVMis an open source tool to optimize tensor programs
Edge ImpulseInteractive platform to generate models that can run in microcontrollers. They are also quite active on social netwoks talking about recent news on EdgeAI/TinyML
Qeexo AutoMLInteractive platform to generate AI models targetted to microcontrollers
mlpackC++ header-only fast machine learning library that focuses on lightweight deployment. It has a wide variety of machine learning algorithms with the possibility to realize on-device learning on MPUs
AIfES225over 2 years agoplatform-independent and standalone AI software framework optimized for embedded systems
onnx2c234almost 2 years agoONNX to C compiler targeting "Tiny ML"

Other interesting resources

Benchmarking Edge Computing (May 2019)
Hardware benchmark for edge AI on cubesats - Open Source Cubesat Workshop 201812about 8 years ago
Why Machine Learning on The Edge?
Tutorial: Low Power Deep Learning on the OpenMV Cam
TinyML: Machine Learning with TensorFlow on Arduino and Ultra-Low Power Micro-ControllersO'Reilly book written by Pete Warden, Daniel Situnayake
tinyML SummitAnnual conference and monthly meetup celebrated in California, USA. Talks and slides are usually
TinyML Papers and Projects778almost 2 years agoCompilation of the most recent paper's and projects in the TinyML/EdgeAI field
MinUn0over 3 years agoAccurate ML Inference on Microcontrollers

Backlinks from these awesome lists:

More related projects: