centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 11:08:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

feat: backup footnote_bbox_tmp

Browse Source
This commit is contained in:
xu rui
2024-03-23 14:11:50 +08:00
parent 15c8830416
commit 05161c6e62
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
magic_pdf/pdf_parse_for_train.py
View File

@@ -531,6 +531,7 @@ def parse_pdf_for_train(
page_info["bak_page_no_bboxes"] = page_no_bboxs
page_info["bak_header_bboxes"] = header_bboxs
page_info["bak_footer_bboxes"] = footer_bboxs
page_info["bak_footer_note_bboxes"] = footnote_bboxes_tmp
pdf_info_dict[f"page_{page_id}"] = page_info

2
magic_pdf/train_utils/convert_to_train_format.py
View File

@@ -54,7 +54,7 @@ def convert_to_train_format(jso: dict) -> []:
n_bbox = {"category_id": 10, "bbox": inter_equation["bbox"]}
bboxes.append(n_bbox)
for footnote in v['footnote_bboxes_tmp']:
for footnote in v['bak_footer_note_bboxes']:
n_bbox = {"category_id": 5, "bbox": footnote["bbox"]}
bboxes.append(n_bbox)