{"id":31965514,"url":"https://github.com/umitkacar/ai-edge-computing-tiny-embedded","last_synced_at":"2025-10-14T17:55:50.770Z","repository":{"id":158690224,"uuid":"336525398","full_name":"umitkacar/ai-edge-computing-tiny-embedded","owner":"umitkacar","description":null,"archived":false,"fork":false,"pushed_at":"2024-06-26T19:45:29.000Z","size":296,"stargazers_count":11,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-06-27T23:21:35.181Z","etag":null,"topics":["ai","android","coreml","edge-computing","embedded","embedded-systems","gpu-computing","ios","jetson-nano","machine-learning","mcu","mobile","ncnn","onnx","onnxruntime","tensorrt","tensorrt-inference","tiny","tinyml","yolo"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/umitkacar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-02-06T11:49:23.000Z","updated_at":"2024-06-26T19:45:32.000Z","dependencies_parsed_at":"2024-01-03T13:28:52.302Z","dependency_job_id":"331802c4-d858-434b-971a-983fdc6d3343","html_url":"https://github.com/umitkacar/ai-edge-computing-tiny-embedded","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/umitkacar/ai-edge-computing-tiny-embedded","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/umitkacar%2Fai-edge-computing-tiny-embedded","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/umitkacar%2Fai-edge-computing-tiny-embedded/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/umitkacar%2Fai-edge-computing-tiny-embedded/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/umitkacar%2Fai-edge-computing-tiny-embedded/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/umitkacar","download_url":"https://codeload.github.com/umitkacar/ai-edge-computing-tiny-embedded/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/umitkacar%2Fai-edge-computing-tiny-embedded/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279020016,"owners_count":26086807,"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","status":"online","status_checked_at":"2025-10-14T02:00:06.444Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["ai","android","coreml","edge-computing","embedded","embedded-systems","gpu-computing","ios","jetson-nano","machine-learning","mcu","mobile","ncnn","onnx","onnxruntime","tensorrt","tensorrt-inference","tiny","tinyml","yolo"],"created_at":"2025-10-14T17:54:55.215Z","updated_at":"2025-10-14T17:55:50.757Z","avatar_url":"https://github.com/umitkacar.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI - Edge Computing\n\n## OBJECT DETECTION WITH LLMs\n\n- https://blog.roboflow.com/fine-tune-florence-2-object-detection/\n\n## Onnxruntime\n\n- https://leimao.github.io/blog/ONNX-Runtime-CPP-Inference/\n- https://github.com/cassiebreviu/cpp-onnxruntime-resnet-console-app\n- https://github.com/k2-gc/onnxruntime-cpp-example\n- https://github.com/Rohithkvsp/OnnxRuntimeAndorid\n- https://github.com/ifzhang/ByteTrack/blob/main/deploy/ONNXRuntime/onnx_inference.py\n- https://huggingface.co/models?sort=trending\u0026search=onnx\n- https://neuml.github.io/txtai/pipeline/train/hfonnx/\n- https://docs.ultralytics.com/modes/export/#arguments\n\n### YOLO -NAS\n- https://github.com/jason-li-831202/YOLO-NAS-onnxruntime\n\n### QUANTIZATION\n- https://github.com/microsoft/onnxruntime/tree/main/onnxruntime/python/tools/quantization\n- https://onnxruntime.ai/docs/performance/model-optimizations/float16.html\n- https://github.com/microsoft/onnxruntime-inference-examples/tree/main/quantization\n\n### YOLO - TENSORRT - POSE - DETECT - SEGMENT\n\n- https://www.youtube.com/watch?v=Z0n5aLmcRHQ\n- https://github.com/cyrusbehr/YOLOv8-TensorRT-CPP\n- https://github.com/cyrusbehr/tensorrt-cpp-api\n- https://github.com/mattiasbax/yolo-pose_cpp\n- https://github.com/triple-Mu/YOLOv8-TensorRT (Python + C++ + TensorRT)\n- https://github.com/NVIDIA/TensorRT/tree/main/samples/trtexec\n\n### YOLO - POSE - DETECT - SEGMENT - CLASSIFY\n- https://github.com/FourierMourier/yolov8-onnx-cpp/tree/main (Python + C++)\n- https://github.com/mallumoSK/yolov8/blob/master/yolo/YoloPose.cpp\n- https://github.com/triple-Mu/YOLOv8-TensorRT/blob/main/csrc/pose/normal/main.cpp\n- https://github.com/Amyheart/yolo-onnxruntime-cpp\n- https://github.com/UNeedCryDear/yolov8-opencv-onnxruntime-cpp\n- https://github.com/ultralytics/ultralytics/tree/main/examples/YOLOv8-ONNXRuntime-CPP\n- https://github.com/hpc203/yolov6-opencv-onnxruntime/tree/main\n- https://github.com/hpc203/yolov5_pose_opencv\n- https://github.com/ultralytics/ultralytics/issues/1852\n\n### FIXED BUGS\n- https://github.com/ultralytics/yolov5/issues/916\n- https://zhuanlan.zhihu.com/p/466677699\n- https://github.com/hpc203?tab=repositories\n- https://velog.io/@dnchoi/ONNX-runtime-install\n\n### DOCUMENT ONNXRUNTIME\n- https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html\n- https://onnxruntime.ai/docs/api/python/on_device_training/training_artifacts.html\n- https://pytorch.org/tutorials/beginner/onnx/onnx_registry_tutorial.html\n- https://github.com/NVIDIA/TensorRT/tree/main/samples/trtexec\n\n### ONNXRUNTIME compatibility (ONNX, OPSET, TensorRT, CUDA, CUDNN)\n- https://onnxruntime.ai/docs/reference/compatibility.html\n- https://github.com/onnx/onnx/blob/main/docs/Versioning.md\n- https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html\n  \n## TENSORRT\n- https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html#requirements\n- https://gitee.com/arnoldfychen/onnxruntime/blob/master/docs/execution_providers/TensorRT-ExecutionProvider.md#specify-tensorrt-engine-cache-path\n\n## FASTDEPLOY\n- https://github.com/PaddlePaddle/FastDeploy\n- https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/en/build_and_install/download_prebuilt_libraries.md\n\n## DEEPSPARSE - SPARSEML\n- https://neuralmagic.com/blog/benchmark-yolov5-on-cpus-with-deepsparse/\n- https://github.com/neuralmagic/sparseml/tree/main\n- https://github.com/neuralmagic/deepsparse\n  \n## MCU\n- [MCU](https://mcunet.mit.edu/)\n- [MCU-Net](https://github.com/mit-han-lab/mcunet)\n\n## COMPRESSION\n- https://github.com/AlgoHunt/VQRF\n\n## OPENCV\n- [openCV C++](https://www.youtube.com/playlist?list=PLUTbi0GOQwghR9db9p6yHqwvzc989q_mu)\n- [Build-OpenCV-C++](https://gist.github.com/raulqf/f42c718a658cddc16f9df07ecc627be7)\n\n## MACE\n- [mace](https://github.com/xiaomi/mace)\n\n## NCNN\n- https://github.com/wkt/YoloMobile\n- [ncnn](https://github.com/Tencent/ncnn)\n- [nccn c++](https://github.com/Tencent/ncnn/blob/master/docs/how-to-use-and-FAQ/use-ncnn-with-alexnet.md)\n- [convert model](https://convertmodel.com/)\n- [awesome-ncnn-collection](https://github.com/umitkacar/awesome-ncnn-collection)\n\n## COREML \n- https://github.com/tucan9389/SemanticSegmentation-CoreML\n- https://github.com/john-rocky/CoreML-Models#u2net\n- https://github.com/likedan/Awesome-CoreML-Models\n- https://github.com/SwiftBrain/awesome-CoreML-models\n- https://github.com/PeterL1n/RobustVideoMatting\n- https://coremltools.readme.io/docs/pytorch-conversion\n- https://github.com/hollance/CoreMLHelpers\n- https://developer.apple.com/machine-learning/api/\n- https://github.com/vladimir-chernykh/coreml-performance\n\n#### CoreML - Stable Diffusion\n- https://github.com/apple/ml-4m/\n- https://github.com/apple/ml-stable-diffusion\n- https://huggingface.co/stabilityai/stable-diffusion-2-base [1]\n- https://github.com/Stability-AI/stablediffusion [1]\n- https://huggingface.co/CompVis/stable-diffusion-v1-4 [2]\n- https://github.com/runwayml/stable-diffusion\n- https://github.com/AUTOMATIC1111/stable-diffusion-webui\n\n### Performance Tool\n- [Performance Inference Time IOS](https://github.com/vladimir-chernykh/coreml-performance)\n\n## LIGHTWEIGHT DETECTOR\n- [PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices ](https://arxiv.org/pdf/2111.00902.pdf)\n- [EtinyNet](https://github.com/aztc/EtinyNet)\n- \u003cimg src=\"./tinyML.png\" alt=\"tinyML\" width=\"640\"\u003e\n\n## TVM\n- https://github.com/apache/tvm\n  \n## LLVM\n- https://github.com/llvm/llvm-project\n\n## ARM-NN\n- https://github.com/ARM-software/armnn\n- https://www.youtube.com/watch?v=QuNOaFLobSg\n\n## CMSIS-NN\n- https://github.com/ARM-software/CMSIS_5\n\n## RISC-V\n\n## ARM\n\n## OpenCL\n\n## Vulkan\n\n## Cuda\n\n## Metal\n\n## XNNPack\n- https://github.com/google/XNNPACK\n\n## Samsung ONE (On-device Neural Engine)\n- https://github.com/Samsung/ONE\n\n## COMPANY\n\n- https://www.deeplite.ai/\n  \nTo provide an AI-Driven Optimizer to make Deep Neural Networks:\n- faster, \n- smaller,\n- energy-efficient \n- from cloud to edge computing\n- without compromising accuracy\n\n## PAPER\n\n- [Deep Learning With Edge Computing: A Review](https://www.cs.ucr.edu/~jiasi/pub/deep_edge_review.pdf)\n\n- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://arxiv.org/pdf/1907.08349.pdf)\n\n- [Machine Learning at the Network Edge: A Survey](https://arxiv.org/pdf/1908.00080.pdf)\n\n- [EtinyNet: Extremely Tiny Network for TinyML](https://ojs.aaai.org/index.php/AAAI/article/download/20387/version/18684/20146)\n\n- [An Ultra-low Power TinyML System for Real-time Visual Processing at Edge](https://arxiv.org/pdf/2207.04663.pdf)\n\n- [Awesome - Embedded and mobile deep learning](https://github.com/csarron/awesome-emdl/blob/master/README.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fumitkacar%2Fai-edge-computing-tiny-embedded","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fumitkacar%2Fai-edge-computing-tiny-embedded","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fumitkacar%2Fai-edge-computing-tiny-embedded/lists"}