An efficient C++17 GPU numerical computing library with Python-like syntax

YOLOv5 on Orin DLA

C++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow

Sample projects for TensorRT in C++

Simple samples for TensorRT programming

ONNX-TensorRT: TensorRT backend for ONNX

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …

⚡ 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 …

Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process

⚡ 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+

PyTorch Neural Network eXchange

Mobile Detection Benchmark

PP-PicoDet for Jetson Nano

边缘设备端算法部署模板框架（包括海思SS928、Hi3519 DV500；瑞芯微rv1126、rk588、比特大陆BM1684X）,部署项目包括yolov5、picodet、MNIST，包括优化加速教程

Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.

face_detection_paper_code

开源配合型人脸活体检测 Open Source Face Anti-spoofing

face detection

The YOLOv5 object detection android example

ncnn example: mask detection: anticonv face detection: retinaface&&mtcnn&&centerface, track: iou tracking, landmark: zqcnn, recognize: mobilefacenet classifier: mobilenet object detecter: mobilenetssd

Light-LPR is an open source project aimed at license plate recognition that can run on embedded devices, mobile phones, and x86 platforms. It aims to support license plate recognition in various sc…

High Performance Chinese License Plate Recognition Framework.

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

Mobile-LPR 是一个面向移动端的准商业级车牌识别库，以NCNN作为推理后端，使用DNN作为算法核心，支持多种车牌检测算法，支持车牌识别和车牌颜色识别。

ncnn android benchmark app

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

ncnn android nanodet lightweight object detection