{"id":13516166,"url":"https://github.com/crespum/edge-ai","last_synced_at":"2025-03-31T05:31:20.651Z","repository":{"id":38816037,"uuid":"142336474","full_name":"crespum/edge-ai","owner":"crespum","description":"A curated list of resources for embedded AI","archived":false,"fork":false,"pushed_at":"2024-05-21T06:52:59.000Z","size":72,"stargazers_count":311,"open_issues_count":1,"forks_count":38,"subscribers_count":27,"default_branch":"master","last_synced_at":"2024-05-21T08:03:52.778Z","etag":null,"topics":["artificial-intelligence","awesome-list","edge-computing","embedded"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/crespum.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-07-25T18:05:37.000Z","updated_at":"2024-05-29T02:41:27.964Z","dependencies_parsed_at":"2024-05-29T02:41:26.811Z","dependency_job_id":"27f3fb7b-c5c1-4237-8cfb-1b1beec87e15","html_url":"https://github.com/crespum/edge-ai","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crespum%2Fedge-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crespum%2Fedge-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crespum%2Fedge-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/crespum%2Fedge-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/crespum","download_url":"https://codeload.github.com/crespum/edge-ai/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246350950,"owners_count":20763230,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","awesome-list","edge-computing","embedded"],"created_at":"2024-08-01T05:01:19.712Z","updated_at":"2025-03-31T05:31:20.641Z","avatar_url":"https://github.com/crespum.png","language":null,"readme":"# AI at the edge\n\nA curated list of hardware, software, frameworks and other resources for Artificial Intelligence at the edge. Inspired by [awesome-dataviz](https://github.com/fasouto/awesome-dataviz).\n\n\n## Contents\n- [Hardware](#hardware)\n- [Software](#software)\n- [Frameworks](#frameworks)\n- [Contributing](#other-interesting-resources)\n- [License](#license)\n\n# Hardware\n- [OpenMV](http://docs.openmv.io) - A camera that runs with MicroPython on ARM Cortex M6/M7 and great support for computer vision algorithms. Now with [support for Tensorflow Lite too](https://openmv.io/blogs/news/tensorflow-lite-and-person-detection).\n- [JeVois](http://jevois.org/) - A TensorFlow-enabled camera module.\n- [Edge TPU](https://cloud.google.com/edge-tpu/) - Google’s purpose-built ASIC designed to run inference at the edge.\n- [Movidius](https://www.movidius.com) - Intel's family of SoCs designed specifically for low power on-device computer vision and neural network applications.\n    - [UP AI Edge](https://up-shop.org/25-up-ai-edge) - Line of products based on Intel Movidius VPUs (including Myriad 2 and Myriad X) and Intel Cyclone FPGAs.\n    - [DepthAI](https://www.crowdsupply.com/luxonis/depthai) - An embedded platform for combining Depth and AI, built around Myriad X\n- [NVIDIA Jetson](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/) - High-performance embedded system-on-module to unlock deep learning, computer vision, GPU computing, and graphics in network-constrained environments.\n    - Jetson TX1\n    - Jetson TX2\n    - Jetson Nano\n- [Artificial Intelligence Radio - Transceiver (AIR-T)](https://www.crowdsupply.com/deepwave-digital/air-t) - High-performance SDR seamlessly integrated with state-of-the-art deep learning hardware.\n- [Kendryte K210](https://canaan.io/product/kendryteai) - Dual-core, RISC-V chip with convolutional neural network acceleration using 64 KLUs (Kendryte Arithmetic Logic Unit).\n    - [Sipeed M1](http://en.dan.sipeed.com/) - Based on the Kendryte K210, the module adds WiFi connectivity and an external flash memory.\n    - [M5StickV](https://docs.m5stack.com/#/en/core/m5stickv) - AIoT(AI+IoT) Camera powered by Kendryte K210\n    - [UNIT-V](https://docs.m5stack.com/#/en/unit/unitv) - AI Camera powered by Kendryte K210 (lower-end M5StickV)\n- [Kendryte K510](https://canaan.io/product/kendryteai) - Tri-core RISC-V processor clocked with AI accelerators.\n- [GreenWaves GAP8](https://greenwaves-technologies.com/gap8_mcu_ai/) - RISC-V-based chip with hardware acceleration for convolutional operations.\n- [GreenWaves GAP9](https://greenwaves-technologies.com/gap9_processor/) - RISC-V-based chip primarily focused on AI-centric audio processing.\n- [Ultra96](https://www.96boards.ai/products/ultra96/) - Embedded development platform featuring a Xilinx UltraScale+ MPSoC FPGA.\n- [Apollo3 Blue](https://www.sparkfun.com/products/15170) - SparkFun Edge Development Board powered by a Cortex M4 from Ambiq Micro.\n- [Google Coral](https://coral.ai/) - Platform of hardware components and software tools for local AI products based on Google Edge TPU coprocessor.\n    - Dev boards\n    - USB Accelerators\n    - PCIe / M.2 modules\n- [Gyrfalcon Technology Lighspeeur](https://www.gyrfalcontech.ai/solutions/) - Family of chips optimized for edge computing.\n- [ARM microNPU](https://www.arm.com/products/silicon-ip-cpu/machine-learning/ethos-u55) - Processors designed to accelerate ML inference (being the first one the Ethos-U55).\n- [Espressif ESP32-S3](https://www.espressif.com/en/products/socs/esp32-s3) - SoC similar to the well-known ESP32 with support for AI acceleration (among many other interesting differences).\n- [Maxim MAX78000](https://www.maximintegrated.com/en/products/microcontrollers/MAX78000.html) - SoC based on a Cortex-M4 that includes a CNN accelerator.\n- [Beagleboard BeagleV](https://beagleboard.org/beaglev) - Open Source RISC-V-based Linux board that includes a Neural Network Engine.\n- [Syntiant TinyML](https://www.syntiant.com/tinyml) - Development kit based on the Syntiant NDP101 Neural Decision Processor and a SAMD21 Cortex-M0+.\n- [STM32N6](https://www.st.com/en/microcontrollers-microprocessors/stm32n6-series.html) - Arm Cortex-M55 running at 800MHz that embeds an neural processing unit (NPU).\n- [Grove Vision AI Module V2](https://www.seeedstudio.com/Grove-Vision-AI-Module-V2-p-5851.html) - Arm Cortex-M55 and Ethos U-55 neural processing unit (NPU).\n- [Arduino Nicla Voice](https://docs.arduino.cc/hardware/nicla-voice) - Soc based on Arm Cortex-M4 nRF52832 and includes the Syntiant NDP120 Neural Decision Processor \n\n# Software\n- [TensorFlow Lite](https://www.tensorflow.org/lite/) - Lightweight solution for mobile and embedded devices which enables on-device machine learning inference with low latency and a small binary size.\n- [TensorFlow Lite for Microcontrollers](https://www.tensorflow.org/lite/microcontrollers) - Port of TF Lite for microcontrollers and other devices with only kilobytes of memory. Born from a [merge with uTensor](https://os.mbed.com/blog/entry/uTensor-and-Tensor-Flow-Announcement/).\n- [Embedded Learning Library (ELL)](https://github.com/Microsoft/ELL) - Microsoft's library to deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers.\n- [uTensor](https://github.com/uTensor/uTensor) - AI inference library based on mbed (an RTOS for ARM chipsets) and TensorFlow.\n- [CMSIS NN](https://arm-software.github.io/CMSIS_5/NN/html/index.html) - A collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Cortex-M processor cores.\n- [ARM Compute Library](https://developer.arm.com/technologies/compute-library) - Set of optimized functions for image processing, computer vision, and machine learning.\n- [Qualcomm Neural Processing SDK for AI](https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk) - Libraries to developers run NN models on Snapdragon mobile platforms taking advantage of the CPU, GPU and/or DSP.\n- [ST X-CUBE-AI](https://www.st.com/en/embedded-software/x-cube-ai.html) - Toolkit for generating NN optimiezed for STM32 MCUs.\n- [ST NanoEdgeAIStudio](https://www.st.com/content/st_com/en/campaigns/nanoedgeaistudio.html) - Tool that generates a model to be loaded into an STM32 MCU.\n- [Neural Network on Microcontroller (NNoM)](https://github.com/majianjia/nnom) - Higher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN.\n- [nncase](https://github.com/kendryte/nncase) - Open deep learning compiler stack for Kendryte K210 AI accelerator.\n- [deepC](https://github.com/ai-techsystems/dnnCompiler) - Deep learning compiler and inference framework targeted to embedded platform.\n- [uTVM](https://tvm.apache.org/2020/06/04/tinyml-how-tvm-is-taming-tiny) - *MicroTVM* is an open source tool to optimize tensor programs.\n- [Edge Impulse](https://edgeimpulse.com/) - Interactive platform to generate models that can run in microcontrollers. They are also quite active on social netwoks talking about recent news on EdgeAI/TinyML.\n- [Qeexo AutoML](https://qeexo.com/ml-platform/) - Interactive platform to generate AI models targetted to microcontrollers.\n- [mlpack](https://www.mlpack.org) - C++ 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. \n- [AIfES](https://github.com/Fraunhofer-IMS/AIfES_for_Arduino) - platform-independent and standalone AI software framework optimized for embedded systems.\n- [onnx2c](https://github.com/kraiskil/onnx2c) - ONNX to C compiler targeting \"Tiny ML\".\n- [Imagimob](https://www.imagimob.com/) - They offer a toolset (DEEPCRAFT) aimed at developing ML models for embedded devices.\n- [emlearn](https://github.com/emlearn/emlearn) - ML inference engine for microcontrollers and embedded devices.\n\n# Other interesting resources\n- [Benchmarking Edge Computing (May 2019)](https://medium.com/@aallan/benchmarking-edge-computing-ce3f13942245)\n- [Hardware benchmark for edge AI on cubesats - Open Source Cubesat Workshop 2018](https://github.com/crespum/oscw18-edge-ai)\n- [Why Machine Learning on The Edge?](https://towardsdatascience.com/why-machine-learning-on-the-edge-92fac32105e6)\n- [Tutorial: Low Power Deep Learning on the OpenMV Cam](https://community.arm.com/innovation/b/blog/posts/low-power-deep-learning-on-openmv-cam)\n- [TinyML: Machine Learning with TensorFlow on Arduino and Ultra-Low Power Micro-Controllers](http://shop.oreilly.com/product/0636920254508.do) - O'Reilly book written by Pete Warden, Daniel Situnayake.\n- [tinyML Summit](https://www.tinymlsummit.org/) - Annual conference and monthly meetup celebrated in California, USA. Talks and slides are usually [available from the website](https://www.tinymlsummit.org/#meetups).\n- [TinyML Papers and Projects](https://github.com/gigwegbe/tinyml-papers-and-projects) - Compilation of the most recent paper's and projects in the TinyML/EdgeAI field.\n- [MinUn](https://github.com/ShikharJ/MinUn) - Accurate ML Inference on Microcontrollers.\n\n# Contributing\n- Please check for duplicates first.\n- Keep descriptions short, simple and unbiased.\n- Please make an individual commit for each suggestion.\n- Add a new category if needed.\n\nThanks for your suggestions!\n\n# License\n[![CC0](https://licensebuttons.net/p/zero/1.0/88x31.png)](https://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, [Xabi Crespo](https://crespum.eu/) has waived all copyright and related or neighboring rights to this work.\n","funding_links":[],"categories":["Technical","Others","**Other Insightful Lists**","Other Lists","Networks"],"sub_categories":["TeX Lists"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrespum%2Fedge-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcrespum%2Fedge-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcrespum%2Fedge-ai/lists"}