Yolov5-deepsort-inference. Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中
1.5kYolov5-Deepsort. 最新版本yolov5+deepsort目标检测和追踪，能够显示目标类别，支持5.0版本可训练自己数据集
1.2kYolov5-distillation-train-inference. Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据
227Yolov5-Flask-VUE. 基于Flask+VUE前后端，在阿里云公网WEB端部署YOLOv5目标检测模型
225YOLOv11-DeepSort. YOLOv11 & YOLOv8 + DeepSort
206yolox-deepsort. 基于YoloX目标检测+DeepSort算法实现多目标追踪Baseline
187PaddleX-Flask-VUE-demo. 基于PaddleX+Flask开发后端，基于VUE开发前端应用，做一个AI医疗的WEB应用
180yolov3-vehicle-detection-paddle. vehicle-detection based on yolov3（基于paddle的YOLOv3车辆检测和类型识别）
171yolov5-distillation-5.0. yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s
169yolov5-knowledge-distillation. yolov5目标检测模型的知识蒸馏（基于响应的蒸馏）
115Easy-AnimeGAN. From https://github.com/TachibanaYoshino/AnimeGAN, easier for a demo
108DMD3C. 1st Place on KITTI Depth Completion Leaderboard, Official Code of "[CVPR 2025] Distilling Monocular Foundation Model for Fine-grained Depth Completion"
108play-daxigua-using-Reinforcement-Learning. 用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本
97Flow-Anything. Official implementation of our paper "Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images"
78opencv-pyqt-makeup-software. 基于opencv+pyqt5开发的美颜化妆软件，功能包括：图像锐化、亮睛、红唇、瘦脸、美肤等
76L2M. Official implementation of our ICCV'25 paper "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space"
71MPI-Flow. Official Code of "[ICCV 2023] MPI-Flow: Learning Realistic Optical Flow with Multiplane Images"
64Face-recognition-for-classroom-sign-in. 基于FaceNet的人脸检测+识别的课堂学生签到系统
58PaddleDetection-Pedestrians-Detection-and-Tracking. 中软杯baseline-基于百度飞桨的单/多镜头行人追踪，使用百度飞桨PaddleDetection套件的PP-YOLO+Sort算法开发
55PaddleDetection-Yolov5. 基于Paddlepaddle复现yolov5，支持PaddleDetection接口
42gobang-object-detection-dataset. 北理BIT人工智能大作业，写脚本收集了黑/白棋子检测数据集并提供YOLOv3训练和推理代码
38Paddle-face-detection-and-expression-recognition. 基于Paddle框架的TinyYOLO人脸检测和ResNet表情识别
34Pix2seq-mmdetection. Unofficial implement of "Pix2seq: A Language Modeling Framework for Object Detection" on mmdetection
34Point-Transformer-Pytorch. 基于Pytorch复现Point-Transformer，用于ShapeNet数据集点云分割
33Point-Transformers-with-Quantization. 基于Point Transformers复现点云分割任务，并使用HAQ算法进行自动量化压缩，几乎不影响精度
26FCN-DenseNet. FCN implement with densenet for VOC dataset
25paddlex-vehicle-detection-with-YOLOv3. （车辆检测和车道分割）vehicle detection and lane segmentation based on YOLOv3 with paddlex
22HAQ-for-Mobilenetv3-Quantization. 用于 MobileNetV3 在自定义数据集上的量化，模型压缩90%而精度几乎不受影响，论文：HAQ: Hardware-Aware Automated Quantization with Mixed Precision
20yolov5_export_quant_model. yolov5模型训练后量化代码
19paddleocr-enterprise-entity-recognition. 【中软杯国二开源】基于PaddleOCR和深度学习的企业实体识别
19Easy-Pelee-Detection. A Pelee demo easier for demo（直接跑检测的那种）
17Versailles-text-generation-with-paddlepaddle. 使用Paddlehub实现最近大火的凡尔赛文案自动生成
17play-Pacman-with-gesture-recognition-by-resnet18. 手把手教你用PaddleX训练手势识别模型，并将该模型用于吃豆豆游戏
16pacman-with-paddlepaddle-gesture-control. pacman with paddlepaddle gesture control，手势识别用于吃豆人小游戏
16Hand-gesture-recognition-for-game. 手势识别玩转打飞机小游戏，基于MobileNetV3_Small和pygame
15PyQt5-based-Remote-Medical-System-v1.0. 基于PyQt5开发，使用多线程和Socket通信，北理18级小学期大作业，远程医疗云监控系统
15Awesome-Depth-Completion. 2018-2024 in-depth completion of top papers, open source code summary! (Continuous update)
14PARL-DQN-daxigua. 用parl框架的DQN强化学习算法玩“合成大西瓜”
14BITCS-final-exam-learning-materials-1. 北理工计算机CS期末考试复习资料/历年考题汇总，欢迎PR
13Tianchi-PANDA-rank13. PANDA大场景多对象检测跟踪（初赛检测）开源代码，初赛排名13
13advanced_lane_detection. Advanced lane detection using computer vision
12lane-detection-for-huawei-competition. 2021第三届华为云人工智能大赛 · 无人车挑战杯——车道线检测模块
12pp-yolo-vehcile-detection-and-distance-estimation-for-self-driving. a
11Awesome-datafree-KD. 2019~2021年间Zero-shot/Data-free知识蒸馏的论文合集
11Yolov3-plate-detection. Chinese plate detection（基于YOLOv3的中文车牌检测）
11Play-Tetris-Using-hand-gesture-recognition. 使用手势识别算法玩俄罗斯方块
10RGAL. official code for our IJCV paper "Relation-Guided Adversarial Learning for Data-Free Knowledge Transfer"
10DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06
9Social-safety-distance-detection-with-paddlepaddle. 基于Paddlepaddle的社交行人安全距离检测
9play-daxigua-using-PaddleX. 使用PaddleX在浏览器自动玩合成大西瓜
9BIT-AI-final-exam-papers. 北京理工大学人工智能基础考试卷（目前两套）
9Train-RAFT-from-single-view-images. Official Code (new released) of "[ICCV 2023] MPI-Flow: Learning Realistic Optical Flow with Multiplane Images"
8Star-face-recognition. 基于FaceNet的明星人脸识别
8Nanocrystals-Deep-Learning. A deep learning model for predicting the size and morphology of colloidal nanocrystals (or quantum dots) from synthesis schemes
6Gold-Miner. 汇编大作业，黄金矿工
5CascadeV-Det. Official Code of "[Arxiv 2024] CascadeV-Det: Cascade Point Voting for 3D Object Detection"
5BBAVectors-Oriented-Object-Detection. [WACV2021] Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors
5HeartRate. rppg based hr estimator
4RESNET-tensorflow. resnet on tensorflow
4hello-algorithm. 🌍「算法面试+算法知识」针对小白的算法训练 | 还包括：1、阿里、字节、滴滴 百篇大厂面经汇总 2、千本开源电子书 3、百张思维导图 （右侧来个 star 吧 🌹，English version supported）
4