37f44372b1
unlock albumentations version ( #14746 )
2025-02-25 16:30:08 +08:00
2b7b76310b
fix formula rec models hpi_config ( #14739 )
...
1. for formula rec models, the channel of input data is 1;
2. for latex_ocr_rec models, fix min/max size of dynamic shape.
2025-02-25 14:59:49 +08:00
dc34f9b45a
use the env variable PADDLE_OCR_BASE_DIR if it exists to download models ( #14686 )
...
* use the env variable PADDLE_OCR_BASE_DIR to download models
* use PADDLE_OCR_BASE_DIR env variable to download models
2025-02-15 07:44:23 +08:00
17fff8cca4
fix dy shapes of trt for rec models ( #14654 )
2025-02-11 11:17:23 +08:00
2c0c4beb06
repair bleu score computation ( #14626 )
2025-02-06 16:02:59 +08:00
c685537e64
Add Thai character dictionary for OCR recognition ( #14620 )
...
* Add Thai character dictionary for OCR recognition
* Update Thai character dictionary with empty new line at end of file
2025-02-05 16:09:49 +08:00
cf4c0591ba
repair bug in latexocr cpu infer and typo ( #14552 )
2025-01-16 15:56:13 +08:00
52bc8f0eab
fix slanext export bug ( #14519 )
...
* add slanext models
* refine codes
* refine codes
* refine codes
* fix export SLANeXt
* fix export bugs
2025-01-09 11:49:23 +08:00
bf2b73f0f0
add version control for export and modify hpi config ( #14513 )
2025-01-08 17:29:52 +08:00
a6b96bbfb1
fix SLANeXt export bug ( #14512 )
...
* add slanext models
* refine codes
* refine codes
* refine codes
* fix export SLANeXt
2025-01-07 19:21:34 +08:00
359ab6cb76
fix latex_ocr inference ( #14498 )
...
* add
* update
* add
* add
2025-01-07 11:26:03 +08:00
ed6fe285a8
add ppocrv4_doc dict ( #14499 )
2025-01-06 15:55:59 +08:00
e314510319
import encryption for aistudio & fix sync bn
2025-01-03 15:34:29 +08:00
4f7476d7b8
fix_server_v4_det_output ( #14472 )
2025-01-03 11:59:22 +08:00
2f0a29ed3a
modify export with pir ( #14441 )
2024-12-30 17:00:42 +08:00
0d41ffc91d
repair formula bug when export ( #14442 )
2024-12-24 17:44:31 +08:00
d523388ed1
Add pp formulanet ( #14429 )
...
* add ppformulanet
* rename loss
* modify doc
* add export code
* modify yaml for global ref
2024-12-23 13:14:33 +08:00
0697d248f8
support export with pir and no pir ( #14379 )
2024-12-19 20:16:26 +08:00
04c989b7fe
repair type bug for ppocrv3 ( #14397 )
2024-12-16 14:19:57 +08:00
ae67d96f3e
add slanext models ( #14374 )
...
* add slanext models
* refine codes
* refine codes
* refine codes
2024-12-13 13:39:19 +08:00
f49dec92d6
fix shape64 ( #14376 )
2024-12-12 16:02:56 +08:00
78e7184022
add unimernet model ( #14357 )
...
* add unimernet model
* add commate and single test
* repair pytest
* delete export and infer
* delete [ file
2024-12-12 14:17:24 +08:00
2672be5763
fix:calcute the left_center_pt and right_center_pt from min_area_quad ( #14363 )
2024-12-11 21:56:34 +08:00
9c01b43301
paddle.shape return int64 tensor ( #14318 )
2024-12-04 14:26:57 +08:00
6d2bc9f573
add d2s_train_image_shape for static train ( #14312 )
2024-12-02 20:03:12 +08:00
0018cbd2b6
support latexocr static train ( #14297 )
2024-11-29 17:44:53 +08:00
8fdc409edf
change support list ( #14293 )
2024-11-29 15:18:54 +08:00
500381c940
fix benchmark det_r50_vd_pse_v2_0 train error ( #14239 )
2024-11-16 10:44:12 +08:00
1d4e7a80a0
rename train result ( #14217 )
2024-11-13 15:49:52 +08:00
9b92a1c661
Remove Python 2 compatibility dependency six ( #14202 )
...
* Remove Python 2 compatibility dependency
* Remove Python 2 compatibility dependency six
* Update operators.py
* Remove Python 2 compatibility dependency six
2024-11-12 11:01:20 +08:00
b153f10d97
update hpi config ( #14076 )
2024-11-08 17:38:32 +08:00
15fb82dfa1
upgrade to numpy 2.0 and remove imgaug ( #13937 )
...
* upgrade to numpy 2.0 and remove imgaug
* fix bug
* fix bug
* fix bug
* fix bug
* fix bug
* add license
2024-11-06 12:09:01 +08:00
661cda1289
fix nan in ppocrv4 for benchmark ( #14072 )
...
* fix nan in ppocrv4 for benchmark
* fix config
2024-10-23 11:55:43 +08:00
7541776021
fix isnan_v2 is not supported in paddle2onnx ( #14060 )
2024-10-22 09:18:50 +08:00
de457325cd
reset latex ocr ( #14046 )
2024-10-18 19:51:32 +08:00
349a604951
fix nan in dp16 ( #14043 )
2024-10-18 18:00:08 +08:00
e621d034b5
fix a pir while bug ( #14016 )
2024-10-16 16:24:59 +08:00
362103bd0b
fix lateocr bug ( #13920 )
2024-09-28 19:11:31 +08:00
2b51369324
support export after save model ( #13844 )
2024-09-25 01:11:01 +08:00
ac5313d0b1
fix bugs for SLANet infer ( #13861 )
2024-09-13 12:53:09 +08:00
4832bb62ad
Fix pir dy2st train ( #13853 )
2024-09-11 18:54:37 +08:00
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
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
aabff3958c
fix setting of make border epoch ( #13783 )
2024-08-29 22:27:28 +08:00
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
01e60ff9e1
add vietnamese char dict ( #13698 )
2024-08-19 22:35:40 +08:00
e22ce35c94
Add files via upload ( #13685 )
...
Burmese dictionary expansion
2024-08-18 21:54:43 +08:00
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
6dc021115c
disable automatic checks for new version albumentations ( #13583 )
2024-08-07 07:00:05 +08:00
20de659502
fix download bug when use multi gpus ( #13610 )
2024-08-06 21:15:52 +08:00
Wang Xin
zhangyubo0722
mauryaland
Tingquan Gao
liuhongen1234567
Thanajade Dechananthachai
Liu Jiaxuan
vivienfanghuagood
Sunflower7788
wanghuancoder
fangfangzk
Christian Clauss
wangna11BD
WangZhen
johnlockejrr
Sunflower7788
Songling Huang
changdazhou