-
South China University of Technology
- Guangzhou, Guangdong Province, China
Stars
A curated list of resources for Document Understanding (DU) topic
Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).
gztangde / gector
Forked from grammarly/gectorOfficial implementation of the paper “GECToR – Grammatical Error Correction: Tag, Not Rewrite” // Published on BEA15 Workshop (co-located with ACL 2020) https://www.aclweb.org/anthology/2020.bea-1.…
本工程基于云开放平台API构建图像效果增强Android应用,主要提供图像去雾、清晰度增强、黑白图像上色等多种图像效果增强的服务
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[email protected] 版权所有,违权必究 Tan 2018.06
深度学习面试宝典(含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向)
Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
由图灵的猫开发,基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化
TIANCHI 天池 “数字人体”视觉挑战赛——宫颈癌风险智能诊断 算法赛道 LLLLC队代码 4/2359
TIANCHI 天池 "数字人体"视觉挑战赛——宫颈癌风险智能诊断 VNNI赛道 LLLLC队 1/2359
2020 DIGIX GLOBAL AI CHALLENGE - Digital Device Image Retrieval - Top2 WEARE队
Data/Code Repository for https://api.semanticscholar.org/CorpusID:218470122
Trained models with fast variant of the "best" LSTM models + legacy models
Tesseract Open Source OCR Engine (main repository)
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"
Simple Cowtransfer Uploader/Downloader in Golang
Synthetic Dataset used in the ICDAR2019 Competition on HArvesting Raw Tables from Infographics (CHART-Infographics)
🇨🇳最全最新中国【省、市、区县、乡镇街道】json,csv,sql数据
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现,也是作为一个算法工程师必会的理论基础知识。
Pytorch implementation for "Decoupled attention network for text recognition".
🐍 py2so is tool to change the .py to .so, you can use it to hide the source code of py [Deprecated]. Please navigate to Py2sec
Learning 2D Morphological Network for Old Document Image Binarization