Skip to main content

Awesome OCR toolkits based on PaddlePaddle(8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embedded and IoT devices)

Project description

English | 简体中文

Chat

简介

PaddleOCR 旨在打造一套丰富、领先、且实用的 OCR 工具库,助力开发者训练出更好的模型,并应用落地。

🚀 社区

PaddleOCR 由 PMC 监督。Issues 和 PRs 将在尽力的基础上进行审查。欲了解 PaddlePaddle 社区的完整概况,请访问 community

⚠️注意:Issues模块仅用来报告程序🐞Bug,其余提问请移步Discussions模块提问。如所提Issue不是Bug,会被移到Discussions模块,敬请谅解。

📣 近期更新(more)

  • 🔥🔥《PaddleOCR 2.9 发布,正式开源文本图像智能分析利器》,文本图像版面解析实现高精度实时预测,低代码全流程开发加速产业应用。集成文本图像矫正、版面区域检测、常规文本检测、印章文本检测、文本识别、表格识别等多功能。6条模型产线一键调用,显著降低开发成本。支持高性能推理、服务化部署和端侧部署等多种部署方式。10月24日(周四)19:00直播为您深度解析最新升级亮点。 报名链接

  • 🔥2024.10.1 添加OCR领域低代码全流程开发能力:

    • 飞桨低代码开发工具PaddleX,依托于PaddleOCR的先进技术,支持了OCR领域的低代码全流程开发能力:

      • 🎨 模型丰富一键调用:将文本图像智能分析、通用OCR、通用版面解析、通用表格识别、公式识别、印章文本识别涉及的17个模型整合为6条模型产线,通过极简的Python API一键调用,快速体验模型效果。此外,同一套API,也支持图像分类、目标检测、图像分割、时序预测等共计200+模型,形成20+单功能模块,方便开发者进行模型组合使用。
      • 🚀提高效率降低门槛:提供基于统一命令图形界面两种方式,实现模型简洁高效的使用、组合与定制。支持高性能推理、服务化部署和端侧部署等多种部署方式。此外,对于各种主流硬件如英伟达GPU、昆仑芯、昇腾、寒武纪和海光等,进行模型开发时,都可以无缝切换
    • 支持文档场景信息抽取v3PP-ChatOCRv3-doc、基于RT-DETR的高精度版面区域检测模型和PicoDet的高效率版面区域检测模型、高精度表格结构识别模型SLANet_Plus、文本图像矫正模型UVDoc、公式识别模型LatexOCR、基于PP-LCNet的文档图像方向分类模型

  • 🔥2024.7 添加 PaddleOCR 算法模型挑战赛冠军方案

🌟 特性

支持多种 OCR 相关前沿算法,在此基础上打造产业级特色模型PP-OCR、PP-Structure和PP-ChatOCR,并打通数据生产、模型训练、压缩、预测部署全流程。

快速开始

🔥 低代码全流程开发

📝 文档

完整文档请移步:docs

📚《动手学 OCR》电子书

🎖 贡献者

⭐️ Star

Star History Chart

许可证书

本项目的发布受 Apache License Version 2.0 许可认证。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

je_paddleocr-2.9.1.tar.gz (2.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

je_paddleocr-2.9.1-py3-none-any.whl (2.4 MB view details)

Uploaded Python 3

File details

Details for the file je_paddleocr-2.9.1.tar.gz.

File metadata

  • Download URL: je_paddleocr-2.9.1.tar.gz
  • Upload date:
  • Size: 2.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for je_paddleocr-2.9.1.tar.gz
Algorithm Hash digest
SHA256 c6fe4e76cc020f772e0f8265c3fa16c18816480f48cabeedc9e367fa3ff661f9
MD5 a875dd32054cc58dde678dba2ea58f80
BLAKE2b-256 63841e3a4189da697c134c9a768e9ed265d1d346c3b1b83cfd93314bdfb154a8

See more details on using hashes here.

Provenance

The following attestation bundles were made for je_paddleocr-2.9.1.tar.gz:

Publisher: python-publish.yml on eritpchy/PaddleOCR

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file je_paddleocr-2.9.1-py3-none-any.whl.

File metadata

  • Download URL: je_paddleocr-2.9.1-py3-none-any.whl
  • Upload date:
  • Size: 2.4 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for je_paddleocr-2.9.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b38b08cade60ea850457ed28213f4519f284660b7c305b7faf20dbb4b6e959b6
MD5 3df286f44231e789dd6fd6fbc0553a8d
BLAKE2b-256 5ffe5331c0061f0a73aa8ebf32c8a7020a45c3f04d68a09ac1e7a2cc4422fac0

See more details on using hashes here.

Provenance

The following attestation bundles were made for je_paddleocr-2.9.1-py3-none-any.whl:

Publisher: python-publish.yml on eritpchy/PaddleOCR

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page