opendatalab/MinerU

Issues

• layout.pdf结果和layout模型结果不一致

  #590 opened 2 days ago by Schumpeterx
  3

• magic-pdf -p demo1.pdf Illegal instruction

  #591 opened 2 days ago by Joyouspeng
  0

• 分页并行以及模块化处理

  #570 opened 5 days ago by QIN2DIM
  12

• 能否在版本发布时候，同时发布更新一个相应版本的docker镜像呢？

  #583 opened 3 days ago by DreamTeamWangbowen
  5

• 【求更新】UniMERNet已更新，期望更新。

  #589 opened 2 days ago by CocoaML
  1

• 解析后的markdown中的标题，没有区分一级标题，二级标题，三级标题，都是一样的

  #506 opened 15 days ago by wzhiqing
  2

• 能提供远程IP地址+API key使用的功能吗？

  #585 opened 3 days ago by llity
  2

• pdf中的表格识别，怎么将表格解析为纯文本而不是图片的形式存放在pdf解析生成的md文件中？

  #531 opened 10 days ago by SuperDZ
  3

• Unable to handle large files

  #576 opened 4 days ago by Sg4Dylan
  3

• pdf解析时报“pymupdf.mupdf.FzErrorSyntax: code=8: syntax error in object (58 0 R)”

  #572 opened 4 days ago by liy-a
  3

• 求助docker相关

  #575 opened 4 days ago by meng0423
  2

• 安装版本为0.6.1 而不是0.7.1

  #556 opened 8 days ago by James-Dao
  33

• 模型预加载参数错误，大佬救命🆘🆘🆘

  #571 opened 4 days ago by FHhui
  3

• 整体的识别进度显示，完成多少页转换。

  #541 opened 9 days ago by TastSong
  2

• 正文中的段落有时候被丢掉了。

  #569 opened 6 days ago by wooemans
  3

• ocr解析pdf，部分pdf会出现乱码问题

  #558 opened 7 days ago by stormchen-cell
  4

• 如何输出bbox框选不同元素的pdf

  #566 opened 6 days ago by jujulovesstudying
  1

• 内网离线运行总是提示发送request失败，里面是有什么依赖要手动下载吗？

  #565 opened 6 days ago by DreamTeamWangbowen
  0

• 报错torch版本和cuda版本不匹配

  #563 opened 6 days ago by ynzm233
  2

• 解析PDF得到的content_list中标题只有一级

  #562 opened 7 days ago by littlexiaoyou
  1

• 对于整个页面大部分为空白，只有几个字符的PDF页面， 无法识别

  #559 opened 7 days ago by coocoocooee
  6

• MinerU和marker解析pdf能力对比

  #551 opened 8 days ago by Sakura4036
  5

• 推理显存占用很高

  #561 opened 7 days ago by pandaominggz
  0

• Table caption recognize error | 表格标题识别错误

  #539 opened 10 days ago by Schumpeterx
  2

• 是否可以将所有模型统一转换为onnx版本，这样可以大大减少工程依赖而且可以降低系统复杂度

  #557 opened 7 days ago by ConleyKong
  0

• Bus error (core dumped)

  #553 opened 8 days ago by CloudAndMist
  9

• 微信群的链接加不进去啦

  #549 opened 8 days ago by duanyu
  0

• 开启表格解析后依然有大部分表格未被解析

  #548 opened 8 days ago by mingyonga8
  6

• 推理加速

  #524 opened 11 days ago by albin3
  1

• docker部署后怎么使用有文档么？

  #546 opened 8 days ago by singeleaf
  0

• 升级magic pdf最新版本后出现Segmentation fault

  #543 opened 10 days ago by randydl
  3

• 在线体验端pdf识别结果问题

  #545 opened 9 days ago by X17exe
  0

• 英文部分检测乱码

  #538 opened 10 days ago by clareliu1234
  2

• ModuleNotFoundError: No module named 'pycocotools'

  #530 opened 10 days ago by yangtutuaka
  5

• docker部署

  #540 opened 10 days ago by TastSong
  1

• 'fairscale'模块不存在

  #535 opened 10 days ago by yang123456he
  4

• 公式检测和公式识别不准确

  #537 opened 10 days ago by zhangmain666
  0

• 模型预加载

  #517 opened 10 days ago by BronyaKaslana06
  3

• 求帮助：识别时输出kill，然后识别中断

  #525 opened 10 days ago by meng0423
  2

• latex识别错误

  #515 opened 11 days ago by Barmaid1076
  2

• magic_pdf_parse_main.py的最佳配置

  #516 opened 12 days ago by HaoRenkk123
  1

• The model repeatedly initializes when processing multiple PDFs in a single process, and it does not implement a singleton pattern.

  #502 opened 11 days ago by drunkpig
  1

• 标题和图片的问题

  #520 opened 11 days ago by luocongqiu
  0

• 在magic_pdf_parse_main这个demo中，如何才能批量处理PDF文件

  #513 opened 13 days ago by chenliutiao
  1

• 如何将Excel表格解析为表头与各行数据（即字典形式）可以一 一对应的列表文本格式？同时支持解析合并单元格。

  #519 opened 11 days ago by Thirty502
  0

• 使用small_ocr.pdf实验，解析结果为空

  #509 opened 14 days ago by huhk-sysu
  2

• pdf解析报错 segmentation fault

  #505 opened 15 days ago by audio-github-2020
  0

• Library not loaded: @loader_path/libjxl.0.6.1.dylib

  #504 opened 15 days ago by audio-github-2020
  2

• 表格上出现页眉会被识别为正文

  #498 opened 16 days ago by kakaxisisan
  0

• pdf识别不出图片

  #497 opened 16 days ago by Ceceliachenen
  0