dog-qiuqiu

xuehao.ma's repositories

Yolo-Fastest

:zap: 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 the mobile terminal can run up to 178fps+

Language:CNOASSERTION1964 49 72

MobileNet-Yolo

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

Language:CNOASSERTION1692 34 34

Yolo-FastestV2

:zap: 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+

Language:Python781 16 75

FastestDet

:zap: 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 simpler

Language:PythonBSD-3-Clause741 12 38

Ultralight-SimplePose

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

Language:Python275 13 10

simple-rknn2

The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588

Language:C++41 3 1

YOLOv5_NCNN

🍅 移动端部署，支持YOLOv5s、YOLOv4-tiny、MobileNetV2-YOLOv3-nano、Simple-Pose与Yolact模型，支持iOS、Android，使用NCNN框架。

Language:C++12 20

libopencv

Opencv ARM Linux precompiled library

Language:C++BSD-3-Clause11 20

ncnn

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

Language:C++NOASSERTION3 10

darknet

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

Language:CNOASSERTION2 10

dog-qiuqiu

2 20

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Language:C++NOASSERTION2 10

Face-Detector-1MB-with-landmark

1M人脸检测模型(含关键点)

Language:PythonMIT1 10

insightface

Face Analysis Project on MXNet and PyTorch

Language:PythonMIT1 10

YOLOX

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

Language:PythonApache-2.0100