A high-throughput and memory-efficient inference and serving engine for LLMs

Pose-driven Deep Convolutional Model for Person Re-identification

Tracker with reidentification

支持yolov8 Reid行人重识别，支持训练和检测

学习过程中一些自己做的小工具

This repository has been deprecated. Suggest to use edgeai-mmdetection in https://github.com/TexasInstruments/edgeai-tensorlab

Real-time multi-camera multi-object tracker using YOLO varients

This is the pytorch implementation and dataset of the ICCV2019 paper "Pose-Guided Feature Alignment for Occluded Person Re-identification"

Add keypoint detection branch based on YOLOv10, and retain Dual Label Assignments

Human Pose Estimation using YOLOv9

⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

📊 Benchmark multiple object trackers (MOT) in Python

A python implementation of Multiple Object Tracking(MOT) evaluation toolkit(2D)

AlphaPose_yolovx include yolov3, yolov4, yolov5.

[CVPR2022] DanceTrack: Multiple Object Tracking in Uniform Appearance and Diverse Motion

Torchreid: Deep learning person re-identification in PyTorch.

一些关于目标检测的脚本和改进思路代码，详细请看readme.md

Joint Detection and Identification Feature Learning for Person Search

PoseFlow: Efficient Online Pose Tracking (BMVC'18)

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

AlphaPose Implementation in Pytorch along with the pre-trained weights

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

Effortless data labeling with AI support from Segment Anything and other awesome models.

[AAAI2024]Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking