Z,J Hu's starred repositories
Ultralight-SimplePose
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
License-Plate-Detector
基于Yolov5车牌检测,更快更准.
UnrealPerson
[CVPR-2021] UnrealPerson: An adaptive pipeline for costless person re-identification
PyTorch-Networks
Pytorch implementation of cnn network
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
2021AICITY_Code_From_Top_Teams
The code from the top teams in the 2021 AI City Challenge (not in any particular order)
Traffic-Control-Plus-Plus
A project for ticketing automated challan for overspeeding vehicles on a decentralized network, and generating dynamic traffic signal timings based on traffic.
3D-detection-with-monocular-RGB-image
3D detection prediction in Autopilot scene with monocular RGB image. Selected Faster RCNN as basemodel and ResNet as backbone with Python.
AICIty-reID-2020
:red_car: The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)
algorithm-base
一位酷爱做饭的程序员,立志用动画将算法说的通俗易懂。我的面试网站 www.chengxuchu.com
ElanGuard_Public
(Academia Sinica / Computer Vision / Deep Learning) Object Detection, Person Reid, Face Reid
AlignedReID-Re-Production-Pytorch
Reproduce AlignedReID: Surpassing Human-Level Performance in Person Re-Identification, using Pytorch.
yolov5_tensorrt_int8
TensorRT int8 量化部署 yolov5s 模型,实测3.3ms一帧!
Image-processing-algorithm
paper implement
AlignedReID
Alignedreid++: Dynamically Matching Local Information for Person Re-Identification.