opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-24 23:10:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(lite_model): Adapt iite Mode to the Hybrid OCR Mode in Version 0.10

Browse Source
This commit is contained in:
myhloli
2024-11-28 15:06:54 +08:00
parent 89c7bd0419
commit 9b4d77dcd4
1 changed files with 23 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/model/pp_structure_v2.py
+23 -3
View File
@@ -18,11 +18,31 @@ def region_to_bbox(region):
class CustomPaddleModel:
def __init__(self, ocr: bool = False, show_log: bool = False, lang=None):
def __init__(self,
ocr: bool = False,
show_log: bool = False,
lang=None,
det_db_box_thresh=0.3,
use_dilation=True,
det_db_unclip_ratio=1.8
):
if lang is not None:
self.model = PPStructure(table=False, ocr=ocr, show_log=show_log, lang=lang)
self.model = PPStructure(table=False,
ocr=True,
show_log=show_log,
lang=lang,
det_db_box_thresh=det_db_box_thresh,
use_dilation=use_dilation,
det_db_unclip_ratio=det_db_unclip_ratio,
)
else:
self.model = PPStructure(table=False, ocr=ocr, show_log=show_log)
self.model = PPStructure(table=False,
ocr=True,
show_log=show_log,
det_db_box_thresh=det_db_box_thresh,
use_dilation=use_dilation,
det_db_unclip_ratio=det_db_unclip_ratio,
)
def __call__(self, img):
try: