Commit Graph

6281 Commits (1c8233d5bcaa1b545e92fab6d937ee3a5ee0501e)
 

Author SHA1 Message Date
Wang Xin 1c8233d5bc
fix SRN algorithm infer error (#13851) 2024-09-11 19:16:30 +08:00
WangZhen 4832bb62ad
Fix pir dy2st train (#13853) 2024-09-11 18:54:37 +08:00
Wang Xin 33d5570249
fix the CI running errors in tests. (#13846) 2024-09-09 17:38:07 +08:00
Wang Xin 5b54ac4606
update kie doc (#13799) 2024-09-02 19:28:02 +08:00
johnlockejrr ada310811a
Add Syriac script support (#13800)
* Add Syriac Language support dictionary

The Syriac Script is a Unicode block containing characters for all forms of the Syriac alphabet, including the Estrangela, Serto, Eastern Syriac, and the Christian Palestinian Aramaic variants. It is used in Literary Syriac, Neo-Aramaic, and Arabic among Syriac-speaking Christians. It was used historically to write Armenian, Persian, Ottoman Turkish, and Malayalam. The script, like Arabic and Hebrew is RTL.

https://en.wikipedia.org/wiki/Syriac_(Unicode_block)
https://en.wikipedia.org/wiki/Syriac_language

* Add Syriac script support for training

The Syriac Script is a Unicode block containing characters for all forms of the Syriac alphabet, including the Estrangela, Serto, Eastern Syriac, and the Christian Palestinian Aramaic variants. It is used in Literary Syriac, Neo-Aramaic, and Arabic among Syriac-speaking Christians. It was used historically to write Armenian, Persian, Ottoman Turkish, and Malayalam. The script, like Arabic and Hebrew is RTL.

https://en.wikipedia.org/wiki/Syriac_(Unicode_block)
https://en.wikipedia.org/wiki/Syriac_language
2024-09-01 20:10:42 +08:00
johnlockejrr 6225a90ef0
Add support for Hebrew Language and Alphabet (#13797)
* Add Hebrew language support for training

https://en.wikipedia.org/wiki/Unicode_and_HTML_for_the_Hebrew_alphabet

* Add Hebrew language dictionary

https://en.wikipedia.org/wiki/Unicode_and_HTML_for_the_Hebrew_alphabet

* Add Samaritan Script dictionary

Samaritan Script is RTL like Arabic and Hebrew, used for Samaritan Hebrew and Aramaic, sometimes has Arabic letters in some texts.

https://en.wikipedia.org/wiki/Samaritan_(Unicode_block)
https://en.wikipedia.org/wiki/Samaritan_Hebrew
https://en.wikipedia.org/wiki/Samaritan_Aramaic_language

* Add Samaritan Script training

Samaritan Script is RTL like Arabic and Hebrew, used for Samaritan Hebrew and Aramaic, sometimes has Arabic letters in some texts.

https://en.wikipedia.org/wiki/Samaritan_(Unicode_block)
https://en.wikipedia.org/wiki/Samaritan_Hebrew
https://en.wikipedia.org/wiki/Samaritan_Aramaic_language

* Update hebrew_dict.txt
2024-09-01 09:18:37 +08:00
topduke 77f4c01f69
Fix doc link in docs (#13792)
* fix configs link

* fix configs link

* fix configs link

* fix configs link
2024-08-30 18:35:25 +08:00
Sunflower7788 aabff3958c
fix setting of make border epoch (#13783) 2024-08-29 22:27:28 +08:00
Wang Xin 759317feb6
docs: Update applications/overview.md (#13763) 2024-08-28 16:38:25 +08:00
Kayzwer 78ddaa44a0
remove unused enumerate (#13760) 2024-08-28 09:10:33 +08:00
achieve_dream e9fca96d4f
rename MKLDNN to OneDNN (#13757)
[Windows Inference Library (version 3.0.0-beta1) - MKL](https://www.paddlepaddle.org.cn/inference/master/guides/install/download_lib.html#windows) renames the mkldnn folder to onednn.
2024-08-27 12:52:00 +08:00
liuhongen1234567 30811fba3c
Repair the bug in the inference script for LaTeX OCR (#13750)
* test

* dataprocess_abspath2relpath

* repair bug in infer/predict_rec for latexocr
2024-08-26 14:21:41 +08:00
Wang Xin ba1c81358f
use setuptools-scm extracts PaddleOCR versions (#13716)
* use setuptools-scm extracts PaddleOCR versions

* fix bug
2024-08-23 17:27:31 +08:00
liuhongen1234567 1752c56cb7
修改LaTeXOCR的数据处理部分,将生成的数据集中的绝对路径改为相对路径 (#13702)
* test

* dataprocess_abspath2relpath
2024-08-20 15:45:57 +08:00
Songling Huang 01e60ff9e1
add vietnamese char dict (#13698) 2024-08-19 22:35:40 +08:00
SWHL 0ca03dde4e
docs: Remove doc/datasets directory and fix docs/datasets documents (#13700) 2024-08-19 22:00:22 +08:00
zhangyubo0722 b12d4fff34
Code Style Unification (#13697) 2024-08-19 17:21:44 +08:00
zhangyubo0722 6986a2a2a2
Remove channel links from documentation (#13674) 2024-08-19 14:41:18 +08:00
jiqirenfeile 8812c07cd4
Update ch_PP-OCRv4_rec_distillation.yml (#13692)
Refactor YAML config to define max_text_length as an anchor for reuse
2024-08-19 08:50:59 +08:00
Songling Huang e22ce35c94
Add files via upload (#13685)
Burmese dictionary expansion
2024-08-18 21:54:43 +08:00
Wang Xin 0b0bfc1be1
cache Python dependencies and PaddleOCR files (#13682) 2024-08-16 16:08:32 +08:00
SWHL 8f7d73ee0d
chore: Update issue template (#13679) 2024-08-16 09:37:07 +08:00
Wang Xin fe564a6d55
docs: Update docs and fix markdown render error (#13678) 2024-08-16 08:21:40 +08:00
Wang Xin 08d35f6d88
docs: Update docs and remove old docs (#13662)
* update docs

* update docs
2024-08-15 18:45:05 +08:00
Tingquan Gao 543a4dd2a0
setuptools 72.2.0 result in that MANIFEST.in is invalid (#13670) 2024-08-15 18:18:16 +08:00
Wang Xin 73b1636650
docs: Update docs and remove out-of-date event (#13660)
* update doc remove out-of-date event

* Update README.md

* Update README_en.md
2024-08-15 08:23:10 +08:00
liuhongen1234567 5f0b90a110
Fix some issues with LaTeXOCR in paddleX (#13646)
* repair_some_Bug_for_paddlex

* style2

* style2

* add_epilson_for groupnorm
2024-08-14 11:30:25 +08:00
Wang Xin 6dc021115c
disable automatic checks for new version albumentations (#13583) 2024-08-07 07:00:05 +08:00
changdazhou 20de659502
fix download bug when use multi gpus (#13610) 2024-08-06 21:15:52 +08:00
SWHL d7ea48ea92
docs: Add android_demo docs (#13601)
* docs: Shorten the image path

* docs: Remove duplicate images

* docs: Fix docs errors

* docs: Add android_demo docs
2024-08-06 10:21:57 +08:00
Wang Xin 09b7f6cf8b
ci: Skip text files when running test ci on push (#13582) 2024-08-05 21:26:55 +08:00
SWHL d590a8d39a
docs: Fix docs errors (#13588)
* docs: Shorten the image path

* docs: Remove duplicate images

* docs: Fix docs errors
2024-08-04 18:02:01 +08:00
SWHL 74529b2a29
docs: Shorten the image path and remove dupliate images (#13585)
* docs: Shorten the image path

* docs: Remove duplicate images
2024-08-03 23:44:19 +08:00
Wang Xin 9a90c8ff33
update dive into OCR book link (#13581) 2024-08-02 19:42:56 +08:00
Wang Xin 28c7be63ec
improve the reading experience of some documents (#13562) 2024-08-02 19:41:36 +08:00
changdazhou b6211b936b
support benchmark for paddlepaddle3.0 (#13574) 2024-08-02 19:24:40 +08:00
Gmgge d69bf81907
docs: Update the pdf file path in the operation demonstration (#13575) 2024-08-02 17:09:02 +08:00
changdazhou 9c19e6dffe
fix bug for paddlepaddle3.0 (#13568) 2024-08-01 22:50:44 +08:00
Wang Xin 6c9bae667b
skip text files when running test ci (#13561)
* skip text files when running test ci

* fix bug
2024-08-01 11:45:32 +08:00
SWHL 5de9392333
chore(Issue_template): Add validation of Environment and MPE code (#13559) 2024-08-01 09:37:02 +08:00
Wang Xin d3ed42241a
add latexocr docs and fix some typos (#13532) 2024-07-31 21:59:51 +08:00
laolitou cab3fcbcdf
fix: 'numpy' has no attribute 'astype' (#13554) 2024-07-31 12:36:31 +08:00
SWHL 358560f03d
docs: Remove old applications docs (#13551)
* docs: Add overview of applications page

* docs: Remove applications docs
2024-07-31 10:58:36 +08:00
MonkeyBrothers c3e2bff244
fix a typo (#13544) 2024-07-30 14:39:40 +08:00
SWHL 0a2e6933e0
docs: Update README_en (#13545)
* docs: Update README

* docs: Update English README

* docs: Update README_en
2024-07-30 14:38:54 +08:00
SWHL 7862eb0224
docs: Update README (#13543)
* docs: Update README

* docs: Update English README
2024-07-30 13:09:43 +08:00
zhangyubo0722 6c12df47b2
merge release/2.6.1 to main (#13523) 2024-07-29 19:09:42 +08:00
hiroi-sora 192300837f
Fix cpp_infer "--enable_mkldnn=false" not effective (#13539)
* Fix "--enable_mkldnn=false" not effective

When using the --enable_mkldnn command line option, MKLDNN should be enabled when set to true and disabled when set to false. But, using the PaddlePaddle v3.0.0-beta1 inference library, the --enable_mkldnn=false option did not work as expected, causing MKLDNN to remain enabled regardless of the setting.

This commit adds a call to `config.DisableMKLDNN()` in the else branch to explicitly disable MKLDNN when `--enable_mkldnn=false` is set.

* fix code style: clang-format
2024-07-29 17:01:40 +08:00
SWHL d1583d4e08
chore: Update bug report template (#13508) 2024-07-26 08:33:42 +08:00
SWHL fc61c869b5
chore: Update issue template (#13505)
* chore: Update the default bug report template

* chore: Update bug report template

* chore: Update bug report template
2024-07-25 23:06:40 +08:00