chentyjpm

MobileNetSSD_Demo_AndroidNCNN

InsightFaceRecognition_Demo_AndroidNCNN

InsightFaceRecognition_Demo_AndroidNCNN

person_detection_lite

Light-weight model with NCNN inference for person/pedestrian detection.

caffe-int8-convert-tools

Generate a quantization parameter file for ncnn framework int8 inference

CasiaLabeler

开箱即用，支持windows, ubuntu和mac

centerface

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)

gstreamill

encoder with hls output based on gstreamer.

HyperFT

移动端快速视频人脸跟踪-移动端150FPS+

insightface

Face Analysis Project on MXNet

LFFD-with-ncnn

A C++ API of the LFFD with ncnn

libqrencode

A fast and compact QR Code encoding library

MegFlow

Efficient ML solutions for long-tailed demands.

mt7601u-ap

AP driver for MT7601U dongles

nanodet

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8mb and run 97FPS on cellphone🔥

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn-android-yolov5

The YOLOv5 object detection android example

ncnn_Android_MoveNet

Android MoveNet pose estimation by ncnn

netron

Visualizer for neural network, deep learning and machine learning models

nnie

重构海思sample中的NNIE模块

node-onvif

The node-onvif is a Node.js module which allows you to communicate with the network camera which supports the ONVIF specifications.

Note-Station-to-markdown

The cross-patform script that converts notes from Synology Note Station to markdown files

Peppa_Pig_Face_Engine

A simple face detect and aligment method, it is easy and stable

ShuffleNet-Series

Ultra-Light-Fast-Generic-Face-Detector-1MB

一款超轻量级通用人脸检测模型（模型文件大小仅1MB，320x240输入下计算量仅90MFlops）适用于边缘计算设备、低算力设备以及PC

UVCCamera

library and sample to access to UVC web camera on non-rooted Android device

yolov7-mask-ncnn

c++ version of yolov7-mask with ncnn

ZLMediaKit

A lightweight RTSP/RTMP/HTTP/HLS/HTTP-FLV/WebSocket-FLV/GB28181 server and client framework based on C++11

ZLMediaKit_NVR_UI

ZQCNN

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型