360AILAB-NLP / 360LayoutAnalysis
360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute
☆278Updated 7 months ago
Alternatives and similar repositories for 360LayoutAnalysis:
Users that are interested in 360LayoutAnalysis are comparing it to the libraries listed below
- Analysis of Chinese and English layouts 中英文版面分析☆201Updated 3 weeks ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆91Updated 5 months ago
- 文档方向分类☆216Updated 5 months ago
- 基于序列表格识别算法推理库,集成PP-Structure和modelscope等表格识别算法。☆274Updated 2 weeks ago
- A High-efficiency Open-source Toolkit for Table-to-Latex Task☆231Updated 4 months ago
- A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.☆210Updated 11 months ago
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆300Updated 8 months ago
- 中文原生检索增强生成测评基准☆115Updated last year
- ☆63Updated 7 months ago
- [ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"☆223Updated last week
- CDLA: A Chinese document layout analysis (CDLA) dataset☆261Updated 3 years ago
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆55Updated 5 months ago
- ☆322Updated 10 months ago
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆46Updated 10 months ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题: 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆44Updated 7 months ago
- 检测和提取各种场景图片中的表格区域,并纠正透视和旋转问题 Detect and extract table regions from images in various scenarios, and correct perspective and rotation i…☆80Updated 4 months ago
- ☆55Updated 2 months ago
- 【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析,按人类阅读顺序进行排序。☆130Updated last year
- 大模型预训练中文语料清洗及质量评估 Large model pre-training corpus cleaning☆57Updated 9 months ago
- 探索 LLM 在法律行业的应用潜力☆87Updated 4 months ago
- SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding☆223Updated last year
- gpt_server是一个用于生产级部署LLMs或Embedding的开源框架。☆167Updated last week
- 📝 针对文档类图像做内容提取,将文档类图像一比一输出到Word或者Txt中,便于进一步使用或处理。后续计划支持输入PDF/图像,输出对应json格式、Txt格式、Word格式和Markdown格式。☆191Updated 5 months ago
- 中文版面检测(Chinese layout detection),yolov8 is used to detect the layout of Chinese document images。☆59Updated last year
- GraphRAG的应用实例,项目特点在于提供了替换OpenAI模型的方法,并通过修改原有提示和切分文档的方法,提高了GraphRAG处理中文内容的能力。☆139Updated 5 months ago
- 基于大语言模型的检索增强生成RAG示例☆142Updated 4 months ago
- 通过浏览器渲染生成表格图像☆214Updated last year
- 语言模型中文认知能力分析☆236Updated last year
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆241Updated 4 months ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆144Updated 10 months ago