A curated list of awesome embedded programming.

🦜🔗 Build context-aware reasoning applications

State-of-the-art 2D and 3D Face Analysis Project

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

yolov5 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

RK3588上实现车辆车牌检测，并输出4个点的landmark，车牌颜色和车牌识别

License-Plate-Recognition 支持12种车牌检测识别，包含yolov5,yolov7,yolov8车牌检测，车牌矫正，车牌识别等，准确率高达99.5% 还有车牌数据集提供下载

Track vehicles and persons on rk3588 / rk3399pro.

使用ONNXRuntime部署百度飞桨开源PP-Vehicle车辆分析，包含车辆检测，识别车型和车辆颜色，车牌检测，车牌识别5个功能，不依赖PaddlePaddle就能运行，包含C++和Python两个版本的程序

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

PyTorch-->ONNX-->RKNN

Official implementation of Score-CAM in PyTorch

⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is …

Learning to See in the Dark. CVPR 2018

Image Signal Processor

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

tensorflow学习笔记

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

⚡ Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB

Noise Flow: Noise Modeling with Conditional Normalizing Flows

MCUNet: Tiny Deep Learning on IoT Devices

PaddleSlim is an open-source library for deep model compression and architecture search.