赵小蒙
|
27c080a944
pipeline调整
|
1 year ago |
赵小蒙
|
b94fd7f068
Merge remote-tracking branch 'origin/master'
|
1 year ago |
赵小蒙
|
755ea5b049
更新依赖列表,增加wordninja
|
1 year ago |
赵小蒙
|
99055af331
英文文本拼接时,如果单个单词超过15个字符,则对该单词进行切分处理。行间公式/图片/表格独立占有一行
|
1 year ago |
icecraft
|
36e86dcbc5
Merge pull request #7 from myhloli/feat/add_layout
|
1 year ago |
许瑞
|
4f1f7d62d5
feat: add layout
|
1 year ago |
赵小蒙
|
1d5d778197
qa版本最终阶段保留pdf_intermediate_dict信息
|
1 year ago |
赵小蒙
|
90ea9096e5
部分layout最底部的文本圈不全,降低阈值减少底边文本被丢弃的可能性
|
1 year ago |
赵小蒙
|
0dbbf9c362
解决'[]'括起来的文本被识别成链接的问题
|
1 year ago |
kernel.h@qq.com
|
8e3beebd1a
修复index越界错误
|
1 year ago |
icecraft
|
439c18f9c4
Merge pull request #6 from myhloli/feat/add_extract_train_data
|
1 year ago |
许瑞
|
390fdb2cd5
fix: fix typo
|
1 year ago |
许瑞
|
09269c845e
feat: add extract_train_data
|
1 year ago |
kernel.h@qq.com
|
056aed8677
制作OCR markdown
|
1 year ago |
kernel.h@qq.com
|
ef5d9137f4
实现对论文中列表的识别
|
1 year ago |
赵小蒙
|
c5624ace1e
line_to_standard_format 逻辑更新
|
1 year ago |
kernel.h@qq.com
|
d062bb6ce9
merge
|
1 year ago |
赵小蒙
|
a4a9fd6934
Merge remote-tracking branch 'origin/master'
|
1 year ago |
赵小蒙
|
ce96c3f67c
为ocr模式的demo增加online模式,pipeline进行微调适配online模式
|
1 year ago |
liusilu
|
2acd1ecc46
Merge branch 'master' of https://github.com/myhloli/Magic-PDF
|
1 year ago |
liusilu
|
2fb4b2efea
add pdf tools
|
1 year ago |
xuchao
|
d2cb75e8ac
利用下一行开头具有的空格特征分割段落
|
1 year ago |
xuchao
|
acabae5624
实现页面与页面之间段落的合并
|
1 year ago |
赵小蒙
|
49bf40cc3c
Merge remote-tracking branch 'origin/master'
|
1 year ago |
赵小蒙
|
ef267e0957
qa需求定制输出
|
1 year ago |
liusilu
|
d3e6853a2b
Merge branch 'master' of https://github.com/myhloli/Magic-PDF
|
1 year ago |
liusilu
|
d1504a94bf
add pdf tools
|
1 year ago |
赵小蒙
|
eb79c884c2
修复image_path的连接符
|
1 year ago |
赵小蒙
|
21043c18a1
Merge remote-tracking branch 'origin/master'
|
1 year ago |
赵小蒙
|
5b9f096045
修复image_path的连接符
|
1 year ago |