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

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

Image, GIF and Video enlarger/upscaler(super-resolution) achieved with Waifu2x, SRMD, RealSR, Anime4K and ACNet.

Deep Learning API and Server in C++11 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.

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

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥

waifu2x converter ncnn version, runs fast on intel / amd / nvidia GPU with vulkan

face detection

AoE (AI on Edge，终端智能，边缘计算) 是一个终端侧AI集成运行时环境 (IRE)，帮助开发者提升效率。

基于Retinaface车牌检测,全新模型仅1.8MB.

Generate a quantization parameter file for ncnn framework int8 inference

基于ncnn框架搭建win及android端的MTCNN人脸检测工程

🍅 Ncnn deployment on mobile,support:YOLOv5s,YOLOv4-tiny,MobileNetV2-YOLOv3-nano,Simple-Pose,Yolact,ChineseOCR-lite,ENet,Landmark106,DBFace,MBNv2-FCN,MBNv3-Seg-small and NanoDet on camera.

全平台实时人脸检测和姿态估计Realtime Face Detection and Head pose estimation on Windows、Ubuntu、Mac、Android and iOS

PFLD pytorch Implementation

RealSR super resolution implemented with ncnn library

基于insightface训练mobilefacenet的相关步骤及ncnn转换流程

加入关键点的darknet训练框架，轻量级的人脸检测，支持ncnn推理

implementation of ncnn's mobileFacenet

SRMD super resolution implemented with ncnn library

yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测（包含关键点）

Darknet2ncnn converts the darknet model to the ncnn model

DAIN, Depth-Aware Video Frame Interpolation implemented with ncnn library

YOLOv5 C++ Implementation on Android using NCNN framework

benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.

😎 A Collection of Awesome NCNN-based Projects

simple android demo.mobilefacenet.ncnn