NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #2559 most downloaded on PyPI
A cross platform OCR Library based on OnnxRuntime.
Last release 2 years ago
no release in 18 months
Release timing varies
gaps range from 8 days to 3 months
Some releases are documented
notes for 21 of the last 60 stable releases
2 versions withdrawn
withdrawn after publishing
4 years old
86 releases · first in 2022
One column per quarter.
Support det mean and std config
常规更新,去掉无效代码
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.4.3...v1.4.4
优化单字符坐标及返回单字符置信度 by @jesse01 in https://github.com/RapidAI/RapidOCR/pull/293
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.4.2...v1.4.3
add extras_require by @hbh112233abc in https://github.com/RapidAI/RapidOCR/pull/281
主要修复issue #288 问题
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.4.1...v1.4.2
Update README_zh.md by @Decem-Y in https://github.com/RapidAI/RapidOCR/pull/268
中文版(by @Joker1212 ):
Char rec(单字识别) (#254)。支持返回单字坐标,汉字返回单字的坐标,英文返回单词级别坐标。 大概原理是基于文本行长度和文字多少来分割出单字坐标的,泛化性比较有限。
Char rec(单字识别) (#254)。支持返回单字坐标,汉字返回单字的坐标,英文返回单词级别坐标。 大概原理是基于文本行长度和文字多少来分割出单字坐标的,泛化性比较有限。
主要借鉴PP-Structure和fanqie03/char-detection
示例如下:
当输入图像最大边大于max_side_len时,会将该图像最大边等比缩放到max_side_len(默认2000px),另一边按照宽高比等比缩放
max_side_len时,会将该图像最大边等比缩放到max_side_len(默认2000px),另一边按照宽高比等比缩放min_side_len时,会将该图像最小边放大到min_side_len(默认30px),另一边按照宽高比缩放*(python)* Fixed issue #202 and add Shapely version limited
*(python)* Restrict dependent package version, especially numpy versions
*(rapidocr_onnxruntime)* Fix EP_list parameter error
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.21...v1.3.22
*(rapidocr_onnxruntime)* Fix dml not work issue
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.20...v1.3.21
*(rapidocr_onnxruntime)* Optimize prompt when using DirctML
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.19...v1.3.20
fix(config): Make ONNX Runtime DirectML an optional configuration for better compatibility by @ccddos in https://github.com/RapidAI/RapidOCR/pull/178
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.18...v1.3.19
feat(cli): Support GPU acceleration via ONNX Runtime DirectML on Windows by @ccddos in https://github.com/RapidAI/RapidOCR/pull/176
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.17...v1.3.18
Bug fix for converting error when processing bitmap image. by @HAL9000COM in https://github.com/RapidAI/RapidOCR/pull/171
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.15...v1.3.17
Nothing published for this version
See link for details. Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.14...v1.3.15
See link for details.
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.14...v1.3.15
Nothing published for this version
See link for details. Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.12...v1.3.13
See link for details.
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.12...v1.3.13
See link for details. Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.11...v1.3.12
See link for details.
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.11...v1.3.12
add letterbox-like resize function in the python api by @LWQ2EDU in https://github.com/RapidAI/RapidOCR/pull/151
See link for details.
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.10...v1.3.11
Fix get_boxes_img_without_det in the python api by @AuroraWright in https://github.com/RapidAI/RapidOCR/pull/150
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.9...v1.3.10
Optim main function by @SWHL in https://github.com/RapidAI/RapidOCR/pull/137
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.3.8...v1.3.9
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
整合PaddleOCR v4模型到rapidocr系列包中,可直接pip install rapidocr_onnxruntime使用。
rapidocr系列包中,可直接pip install rapidocr_onnxruntime使用。rapidocr series package, which can be directly used by pip install rapidocr_onnxruntime.Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
已经对这部分功能做了拆分,详情参见:RapidStructure
Full Changelog: https://github.com/RapidAI/RapidOCR/compare/v1.1.0...1.2.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Your coding agent can read these notes before it upgrades. Set up the MCP server →