 myhloli
|
1279f2cd0f
feat(model): add support for DocLayout-YOLO model
|
1 tahun lalu |
|
myhloli
|
011a1b973b
refactor(ocr):Increase the dilation factor in OCR to address the issue of word concatenation.
|
1 tahun lalu |
|
myhloli
|
1f1dd3538d
feat(list&index block): detect and merge list and index blocks
|
1 tahun lalu |
|
myhloli
|
fb9949c44f
perf(pdf_extract_kit): conditional memory cleanup based on GPU capacity
|
1 tahun lalu |
|
myhloli
|
be1b1ae7fc
refactor(model): improve timing information and performance
|
1 tahun lalu |
|
myhloli
|
4c9bf8abd5
refactor(memory management): remove unused clean_memory function
|
1 tahun lalu |
|
myhloli
|
f2a3a49541
fix(pdf_extract_kit):change unimernet base -> small
|
1 tahun lalu |
|
myhloli
|
4811a3d1df
fix(pdf-extract): ensure model is set to evaluation mode before processing
|
1 tahun lalu |
|
myhloli
|
c36fa049b0
refactor(pdf_extract): use Image.crop directly with layout detection
|
1 tahun lalu |
|
myhloli
|
a4c72e2e33
fix: solve conflicts
|
1 tahun lalu |
 quyuan
|
f9df92aa34
fix: add magic-pdf-dev case
|
1 tahun lalu |
 drunkpig
|
554048086e
Realese 0.8.0 (#587)
|
1 tahun lalu |
|
drunkpig
|
9f352df0eb
Realese 0.8.0 (#586)
|
1 tahun lalu |
|
Xiaomeng Zhao
|
73f66af9bd
Merge pull request #584 from myhloli/update-unimernet-to-0.2.0
|
1 tahun lalu |
|
myhloli
|
4f340c4429
refactor(pdf_extract_kit): update model config and weight paths for UniMERNet-0.2.0
|
1 tahun lalu |
|
myhloli
|
4b372f3f7e
feat(ocr): pass language parameter for custom model init
|
1 tahun lalu |
|
Xiaomeng Zhao
|
aac9109414
refactor(pdf_extract_kit): implement singleton pattern for atomic models (#533)
|
1 tahun lalu |
 yyy
|
d714ac8b76
Release: Release 0.7.1 verison, update dev (#527)
|
1 tahun lalu |
|
yyy
|
1dc915a4a9
release: release 0.7.1 version (#526)
|
1 tahun lalu |
|
Xiaomeng Zhao
|
041b9465b9
fix(pdf-extract): adjust box threshold for OCR detection (#447)
|
1 tahun lalu |
|
myhloli
|
334ccac24e
fix(pdf-extract-kit): ensure table extraction success with additional ending conditionAdd an additional condition to determine the success of table extraction by checking
|
1 tahun lalu |
|
myhloli
|
29e590a701
refactor(pdf_extract_kit): optimize image processing and table recognition logicRefactor the image processing logic for OCR and table recognition to ensure
|
1 tahun lalu |
 liukaiwen
|
377b49eb24
add table recognition success detect
|
1 tahun lalu |
|
liukaiwen
|
b18496b0ae
add table recognition success detect
|
1 tahun lalu |
|
liukaiwen
|
cae215bb5e
fix table recognition bug#321
|
1 tahun lalu |
|
liukaiwen
|
b8adb630ee
Merge branch 'master' of github.com:papayalove/Magic-PDF
|
1 tahun lalu |
|
myhloli
|
52156eaee9
fix(pdf-extract): ensure table recognition config defaults to disabled
|
1 tahun lalu |
 Kaiwen Liu
|
37925f36d9
feat(model inference): add table recognition and conversion to LaTeX (#284)
|
1 tahun lalu |
|
liukaiwen
|
b9667fd3e3
add table recognition and conversion to LaTeX
|
1 tahun lalu |
|
liukaiwen
|
dbe628ee07
add table recognition and conversion to LaTeX
|
1 tahun lalu |
