yumeng88's repositories
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
gesture
基于opencv和paddlex的手势识别demo
tensorflow-serving-yolov3
本项目主要对原tensorflow-yolov3版本做了许多细节上的改进,增加了TensorFlow-Serving工程部署,训练了多个数据集，包括Visdrone2019, 安全帽等, 安全帽mAP在98%左右, 推理速度1080上608的尺寸大概25fps.
Yolov5-distillation-train-inference
Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据
yolov5-v4
yolov5第四版
yolov5_prune
yolov5剪枝，支持v2,v3,v4版本的yolov5
yolov5_ROS
ROS使用YOLOv5 run YOLOv5 in ROS
yolov5_transformer
Yolov5 with transformers
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
2020_algorithm_intern_information
2020年的算法实习岗位/校招公司信息表，和常见深度学习基础知识笔记、算法岗面试题答案，及暑期计算机视觉实习面经和总结。
unet-pytorch
这是一个unet-pytorch的源码，可以训练自己的模型
yolov5-1
基于yolov5实现的B站蒙版弹幕效果
detr
End-to-End Object Detection with Transformers
yolov5
YOLOv5 汉化版，保持官方同步更新
yolov5-deepsort-pedestrian-counting
yolov5 + deepsort实现了行人计数功能， 统计摄像头内出现过的总人数，以及对穿越自定义黄线行人计数效果如下
ncnn-android-yolov5
The YOLOv5 object detection android example
fire-detect-yolov4
fire-smoke-detection-dataset and fire-detection-yolov4-5 (with xml annotations)，火灾检测，烟雾检测
PyQt5_YoLoV5_DeepSort
This is a PyQt5 GUI program, which is based on YoloV5 and DeepSort to track person, and give a warning when someone comes to the "dangerous area".
fast-reid
SOTA Re-identification Methods and Toolbox
YOLO-Multi-Backbones-Attention
Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization
yolov5-Social-Distancing
Detecting people using yolov5 model and the people were classified as High, Moderate and Normal based on their distance from one another.
Object-Detection-and-Tracking
YOLO & RCNN Object Detection and Multi-Object Tracking
YOLOV4_MCMOT
Using YOLOV4 as detector for MCMOT.
deep_sort
Simple Online Realtime Tracking with a Deep Association Metric
Fire-Detect-by-YoloV5
火灾检测，浓烟检测，吸烟检测，持续更新中~欢迎star与提出指导~~请查看原文：https://blog.csdn.net/qq_46098574/article/details/107334954
FairMOT
A simple baseline for one-shot multi-object tracking