目录
yolo系列汇总:
关于batch normalization的理解:
各类归一化方法的总结及代码:
YJango的卷积神经网络介绍:
目标检测SSD讲解:
关于AP PR曲线计算的理解(内附代码,生肉,英文):
解释了yolov3的forward和anchor box相关内容
关于数据增强的奇淫技巧:
一篇超级全的数据增强博客:
yolov3 pytorch教程:
标注工具汇总:
github上7k星的pytorch教程(对不起,现在已经8k星了):
github上2w+星的tensorflow教程:
经典论文原文及其中文对照翻译:
分割线 -------------------------------------
数据增强代码:
手写数字识别博客:
keras搭建cnn实现手写数字识别:
关于残差网络的解析:
pytorch官方教程翻译:
HyperLPR:深度学习高性能车牌识别
服装开源数据集(6w测试集1w数据集):
服装识别开源实例(看到新的会再补充,这部分最近有可能会关注一下):
损失函数各类交叉熵讲解(从信息量和熵来推导,浅显易懂)
交通灯数据集:
模型可视化工具(支持多种主流框架):
CVPR2019论文:
SSD讲解:
一文搞懂faster-rcnn:
模型转化工具(支持TF,Keras,Pytorch,MXNet多种主流框架):
AI学习资料整理:
CVPR2019 | 29篇目标检测相关论文汇总(部分含源码)
边缘检测论文集合(含代码):
基于yolov3和crnn的ocr识别:
Python-Opencv入门:
Pytorch代码调试利器,自动print Tensor信息:
coco2014数据集下载地址:
车道线检测论文及代码汇总:
模型所需计算力统计工具pytorch-OpCounter:
CNN模型解读合集:
李宏毅机器学习在线阅读笔记:
微软亚洲研究院开源项目:
交通标志数据集Mapillary Traffic Sign Dataset:
Pytorch中文教程:
Torchcv 基于Pytorch的开源CV框架:
LFFD 一个轻量级的检测器(人脸/人头/行人/车牌/车辆):
高斯YOLOv3:使用定位不确定性进行自动驾驶的精确快速目标检测器:
PAN 一个快速的文本检测算法:
1MB轻量级人脸带关键点检测算法:
目标检测数据集转换工具:
YOLO系列资料整合:
一个RCNN系列讲解超级棒的博客:
Pytorch官方出品的一本深度学习的书:
新鲜开源ASFF,一个贼吊的目标检测器:
Pytorch2Tensorrt的python API:
ICCV2019辅助驾驶资料汇总:
YOLO的各种变种:
Pytorch训练加速123--如何给cpu数据读取加速:
基于GAN的黄种人人脸生成器:
Anchor Free论文合集:
CrowdHuman+Double Anchor:强强联合,推动密集行人检测技术落地:
首个使用 NAS 设计的 GCN,达到动作识别SOTA:
NVIDIA AI TOT团队的实时人体姿态估计:
基于CenterNet魔改的姿态估计CenterPose:
YOLACT++ 开源实时实例分割网络:
UCF-Crime Dataset:
零售商品检测的基准:密集目标检测的强大baseline:
vedaseg:A semantic segmentation toolbox in pytorch:
何凯明新作,视频理解代码开源:
一个暴力事件检测的数据集:
关于yolov1讲的比较清楚的博客:
https://blog.csdn.net/hrsstudy/article/details/70305791
关于yolov1原理解释的幻灯片:
https://docs.google.com/presentation/d/1aeRvtKG21KHdD5lg6Hgyhx5rPq_ZOsGjG5rJ1HP7BbA/pub?start=false&loop=false&delayms=3000#slide=id.g137784ab86_4_1509
关于anchor box讲的比较清楚的博客:
https://blog.csdn.net/zijin0802034/article/details/77685438
关于yolov2讲的比较清楚的博客:
https://blog.csdn.net/zijin0802034/article/details/77097894
关于yolov3的部分解读:
https://xmfbit.github.io/2018/04/01/paper-yolov3/
https://www.cnblogs.com/guoyaohua/p/8724433.html
https://blog.csdn.net/liuxiao214/article/details/81037416
https://zhuanlan.zhihu.com/p/27642620
https://zhuanlan.zhihu.com/p/33544892
https://github.com/rafaelpadilla/Object-Detection-Metrics#create-the-ground-truth-files
解释了源码yolo_layer.c line195~237,待验证):
https://blog.csdn.net/weixin_41015185/article/details/84189515
https://www.zhihu.com/question/35339639
https://blog.csdn.net/daniaokuye/article/details/78535879
https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
https://zhuanlan.zhihu.com/p/36899263
https://github.com/ayooshkathuria/YOLO_v3_tutorial_from_scratch
https://blog.csdn.net/chaipp0607/article/details/79036312
https://github.com/yunjey/pytorch-tutorial
https://github.com/aymericdamien/TensorFlow-Examples
https://ptorch.com/docs/8/
https://github.com/jiajunhua/SnailTyan-deep-learning-papers-translation
github.com/aleju/imgaug
https://blog.csdn.net/qq_33000225/article/details/73123880
https://www.jianshu.com/p/b22e708a3f37
https://blog.csdn.net/rogerchen1983/article/details/79353972
https://mp.weixin.qq.com/s?__biz=Mzg5NzAxMDgwNg==&mid=2247484041&idx=1&sn=a3580ff29d34556a3eb26ddba8b01e29&chksm=c0791f90f70e9686fb7afec2a3f5c3aeb2694fd054c7a45fb51829e9e85c7aa5c2b0580bc3be&mpshare=1&scene=23&srcid=0109XWDDUIVRlU1lezhBKF4t#rd
https://github.com/zeusees/HyperLPR
https://github.com/zalandoresearch/fashion-mnist/tree/master/data/fashion
https://github.com/KaiJin1995/fashionAI2018/tree/master
https://www.jianshu.com/p/47172eb86b39
https://blog.csdn.net/red_stone1/article/details/80735068
博世小交通灯数据集(用于深度学习的小型交通灯数据集):
https://hci.iwr.uni-heidelberg.de/node/6132
LaRa交通灯识别(巴黎交通灯数据集):
http://www.lara.prd.fr/benchmarks/trafficlightsrecognition
WPI数据集(交通灯/行人/车道检测数据集):
http://computing.wpi.edu/dataset.html
交通信号灯/交通指示牌数据集:
https://github.com/ytzhao/Robotics/wiki/TS-and-TL-Dataset
https://github.com/lutzroeder/Netron
https://github.com/extreme-assistant/cvpr2019
https://blog.csdn.net/qianqing13579/article/details/82106664
https://zhuanlan.zhihu.com/p/31426458
https://github.com/Microsoft/MMdnn
https://mp.weixin.qq.com/s?__biz=Mzg5NzAxMDgwNg==&mid=2247484212&idx=1&sn=18de3f24ff47ff0e096c38ce90a8d95d&chksm=c0791e2df70e973b03a0496ac045974f581bade3a05aa1416104b5556a515acf0ee07a1c3554&mpshare=1&scene=23&srcid=#rd
https://mp.weixin.qq.com/s?__biz=MzI5MDUyMDIxNA==&mid=2247488715&idx=1&sn=e5cb3e73e0a15aa88155bb3807f28121&chksm=ec1ff932db687024dd482e169355b9e37c3c3c4041263634b2a37c0a0f3408b961d3ed1fe4b3&mpshare=1&scene=23&srcid=#rd
https://mp.weixin.qq.com/s?__biz=Mzg5ODAzMTkyMg==&mid=2247485964&idx=1&sn=e87ee7dc9f05c105f555e1e768e5756b&chksm=c0698251f71e0b4786ccf8e91b4c6c888982916063a70c23b78aed5d42ace9ef53c6caa593e7&mpshare=1&scene=23&srcid=#rd
https://github.com/chineseocr/chineseocr
http://www.1zlab.com/article/opencv-face-detection/
https://github.com/zasdfgbnm/TorchSnooper
国外:https://blog.csdn.net/u013249853/article/details/84924808
国内:https://blog.csdn.net/weixin_43599336/article/details/86539042
https://github.com/amusi/awesome-lane-detection
https://github.com/Lyken17/pytorch-OpCounter
https://zhuanlan.zhihu.com/p/65564209
https://datawhalechina.github.io/leeml-notes
https://mp.weixin.qq.com/s/EDDeWQdfEeh8tISMpPOsCQ
https://www.mapillary.com/dataset/trafficsign
https://pytorch.apachecn.org/
https://github.com/donnyyou/torchcv
原版:https://github.com/YonghaoHe/A-Light-and-Fast-Face-Detector-for-Edge-Devices
Pytorch版:https://github.com/becauseofAI/lffd-pytorch
https://github.com/jwchoi384/Gaussian_YOLOv3
https://github.com/WenmuZhou/PAN.pytorch
https://github.com/biubug6/Face-Detector-1MB-with-landmark?tdsourcetag=s_pctim_aiomsg
https://github.com/spytensor/prepare_detection_dataset
https://github.com/Bubble-water/YOLO-Summary
http://www.telesens.co/2018/03/11/object-detection-and-classification-using-r-cnns/
https://zhuanlan.zhihu.com/p/93116220
https://github.com/ruinmessi/ASFF
https://github.com/NVIDIA-AI-IOT/torch2trt
https://mp.weixin.qq.com/s/PFPGX4dDtj_1A4nvtBNFRA
ASFF: Learning Spatial Fusion for Single-Shot Object Detection
https://github.com/ruinmessi/ASFF
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
https://github.com/Zzh-tju/DIoU-darknet
Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
https://github.com/jwchoi384/Gaussian_YOLOv3
PRN: Enriching Variety of Layer-wise Learning Information by Gradient Combination
https://github.com/WongKinYiu/PartialResidualNetworks
一个更优秀的backbone:Cross Stage Partial Networks
https://github.com/WongKinYiu/CrossStagePartialNetworks
彩蛋:Centernet也可以用Darknet实现
https://github.com/CaoWGG/CenterNet-darknet
针对CPU到GPU的张量迁移工具:
https://zhuanlan.zhihu.com/p/82666665
给训练踩踩油门 —— Pytorch 加速数据读取:
https://zhuanlan.zhihu.com/p/80695364
在深度学习中喂饱gpu:
https://zhuanlan.zhihu.com/p/77633542
https://github.com/a312863063/seeprettyface-generator-yellow
https://github.com/VCBE123/AnchorFreeDetection
https://zhuanlan.zhihu.com/p/95253096
https://github.com/xiaoiker/GCN-NAS
https://github.com/NVIDIA-AI-IOT/trt_pose
https://github.com/tensorboy/centerpose
https://github.com/dbolya/yolact
https://webpages.uncc.edu/cchen62/dataset.html
https://github.com/ParallelDots/generic-sku-detection-benchmark
https://zhuanlan.zhihu.com/p/98561946
https://github.com/facebookresearch/SlowFast?tdsourcetag=s_pctim_aiomsg
https://github.com/ZHEQIUSHUI/Violence-Recognition-Dataset
https://github.com/Mingtzge/2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement
https://aijishu.com/a/1060000000091759?from=timeline&isappinstalled=0
https://github.com/ouyanghuiyu/chineseocr_lite
http://www.socsci.ru.nl:8180/RaFD2/RaFD?p=main