 myhloli
|
1fd72f5f3a
refactor(magic_pdf): optimize table recognition and layout detection
|
пре 7 месеци |
|
myhloli
|
553f250fc7
refactor(magic_pdf): optimize code and improve logging
|
пре 7 месеци |
|
myhloli
|
8e1c23393c
feat(model): add tqdm progress bar to model prediction loops
|
пре 7 месеци |
|
myhloli
|
59d6b195b0
refactor(model): integrate AtomModelSingleton for OCR and improve OCR result handling
|
пре 7 месеци |
|
myhloli
|
d7d85a2881
feat(ocr): implement language-specific OCR processing
|
пре 7 месеци |
|
myhloli
|
a330651d64
feat(ocr): implement separate detection and recognition processes
|
пре 7 месеци |
 icecraft
|
bbba2a120c
feat: batch inference with ocr and lang flag
|
пре 7 месеци |
|
myhloli
|
1b34f7e4ff
refactor(magic_pdf): replace PIL with NumPy for image processing
|
пре 8 месеци |
|
myhloli
|
49d140c55b
perf(model): adjust batch size for layout and formula detection
|
пре 10 месеци |
|
myhloli
|
452a9c0bcd
refactor(model): update batch analyze logic for rapid table model
|
пре 10 месеци |
|
myhloli
|
f350222614
feat(model): improve batch analysis logic and support npu
|
пре 10 месеци |
|
myhloli
|
902dcd2cee
refactor(BatchAnalyze): comment out image rotation logic in doclayout_yolo
|
пре 10 месеци |
|
myhloli
|
50f4841716
refactor(device): optimize memory cleaning and device selection
|
пре 10 месеци |
|
icecraft
|
b2887ca0aa
refactor: refactor code
|
пре 11 месеци |
 Suven
|
be01039495
feat: add logging for detection time in BatchAnalyze when OCR is not applied
|
пре 11 месеци |
|
Suven
|
49bfdf07c8
feat: enhance batch processing in BatchAnalyze with layout and OCR timing logs
|
пре 11 месеци |
|
Suven
|
4fd1e41e0e
fix: batch methods in DocLayoutYOLO and YOLOv8 models
|
пре 11 месеци |
|
Suven
|
7ce9edc674
feat: add batch prediction methods for YOLOv8 and Unimernet models
|
пре 11 месеци |
