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

A Comprehensive Benchmark for Document Parsing and Evaluation

OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.

stock股票.获取股票数据,计算股票指标,筹码分布,识别股票形态,综合选股,选股策略,股票验证回测,股票自动交易,支持PC及移动设备。

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

CDLA: A Chinese document layout analysis (CDLA) dataset

Baichuan-Omni: Towards Capable Open-source Omni-modal LLM 🌊

【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

卡证和文档检测和矫正

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.

OCR/OCSR on handwritting ⏣/chemical-structural-formulas with YOLO & CRNN models.

PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!

MTL-TabNet: Multi-task Learning based Model for Image-based Table Recognition

常见计算机视觉标注格式相互转换

A lightweight Python library for simulating Chinese handwriting

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

OCR Document image deformation correction.复现阿里OCR皱巴巴文档图像形变矫正

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

end2end layout analysis based seq2seq

cnn-selfattention-ctc ocr tensorflow1.x

高性能编程 笔记

TensorRT ONNX Plugin、Inference、Compile

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).