Wangweilai1

across

Across the Great Wall we can reach every corner in the world

C-Learning-

学习C#的练习项目

C-OCR

C-OCR是携程自研的OCR项目，主要包括身份证、护照、火车票、签证等旅游相关证件、材料的识别。 项目包含4个部分，拒识、检测、识别、后处理。

Chinese_OCR_CNN-RNN-CTC

中文手写汉字识别

Deep-Learning

DeepClassfiy

EATEN

EATEN: Entity-aware Attention for Single Shot Visual Text Extraction

EyeTrack

图像拼接

EyeTracking

眼动数据图像拼接

fine-tuning

Close-Domain fine-tuning for table detection

hed

code for Holistically-Nested Edge Detection

HelloGitHub

:octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

Image_Segmentation

pytorch Implementation of U-Net, R2U-Net, Attention U-Net, Attention R2U-Net.

labelme2coco

A lightweight package for converting your labelme annotations into COCO object detection format.

learnopencv

Learn OpenCV : C++ and Python Examples

LovaszSoftmax

Code for the Lovász-Softmax loss (CVPR 2018)

MobileNet-v2-caffe

MobileNet-v2 experimental network description for caffe

MVision

机器人视觉 无人驾驶 视觉SLAM ORB LSD SVO DSO 深度学习目标检测yolov3 行为检测 opencv PCL 双目视觉

OCR_DataSet

收集并整理有关OCR的数据集并统一标注格式，以便实验需要

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

PMTD

Pyramid Mask Text Detector designed by SenseTime Video Intelligence Research team.

PSENet

Python-Spider

豆瓣电影top250、斗鱼爬取json数据以及爬取美女图片、淘宝、有缘、CrawlSpider爬取红娘网相亲人的部分基本信息以及红娘网分布式爬取和存储redis、爬虫小demo、Selenium、爬取多点、django开发接口、爬取有缘网信息、模拟知乎登录、模拟github登录、模拟图虫网登录、爬取多点商城整站数据、爬取微信公众号历史文章、爬取微信群或者微信好友分享的文章、itchat监听指定微信公众号分享的文章

pytorch-groupnorm

Group Normalization in PyTorch

RepPoints

Represent Visual Objects by Point Sets

senet.pytorch

PyTorch implementation of SENet

TensorExpand

集成包

tf_ctpn

Tensorflow CTPN

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

yolov7-opencv-onnxrun-cpp-py

分别使用OpenCV、ONNXRuntime部署YOLOV7目标检测，一共包含14个onnx模型，依然是包含C++和Python两个版本的程序