There are 3 repositories under nanodet topic.
🛠 A lite C++ toolkit of awesome AI models, support ONNXRuntime, MNN. Contains YOLOv5, YOLOv6, YOLOX, YOLOR, FaceDet, HeadSeg, HeadPose, Matting etc. Engine: ONNXRuntime, MNN.
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署,支持Android与iOS。
awesome AI models with NCNN, and how they were converted ✨✨✨
Deploy nanodet, the super fast and lightweight object detection, in your web browser with ncnn and webassembly
用opencv部署nanodet目标检测,包含C++和Python两种版本程序的实现
QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.
Tracking-by-Detection形式のMOT(Multi Object Tracking)について、 DetectionとTrackingの処理を分離して寄せ集めたフレームワーク(Tracking-by-Detection method MOT(Multi Object Tracking) is a framework that separates the processing of Detection and Tracking.)
NanoDet: Tiny Object Detection for TFJS and NodeJS
🍅🍅NanoDet、NanoDet-Plus with ONNXRuntime/MNN/TNN/NCNN C++. (https://github.com/DefTruth/lite.ai.toolkit)
A collection of some awesome public Anchor-Free object detection series projects.
NanoDet for a bare Raspberry Pi 4
NanoDetをGoogle Colaboratory上で訓練しONNX形式のファイルをエクスポートするサンプル(This is a sample to training NanoDet on Google Colaboratory and export a file in ONNX format)
本仓库在OpenVINO推理框架下部署Nanodet检测算法,并重写预处理和后处理部分,具有超高性能!让你在Intel CPU平台上的检测速度起飞! 并基于NNCF和PPQ工具将模型量化(PTQ)至int8精度,推理速度更快!
NanoDet for Jetson Nano
docker images for training, mining and infer for ymir
Some Nanodet trained models
NanoDet with tracking for a bare Raspberry Pi 4 using ncnn.
Nanodet, NanodetPlus, Yolov5, Yolov6, Yolov7, MobileSSD etc. deployment with ncnn/dnn/mnn/SNPE/mace/Torch onto Android
Navigation software for autonomous robot. Real-time object detection using high-performance neural network inference computing framework. To communicate with microcontroller, text-based bluetooth communication. Progress of the roboter is shown on Website: We communicate with the server using websockets https://github.com/cyrillkuettel/rover/
Implemented the prediction inference process of the NANODET model in ONNX format and TFLite format