Commit 15c88304 authored by xu rui's avatar xu rui
Browse files

feat: comment parse_title

parent 432e1ae5
...@@ -253,7 +253,7 @@ def parse_pdf_for_train( ...@@ -253,7 +253,7 @@ def parse_pdf_for_train(
# isSimpleLayout_flag, fullColumn_cnt, subColumn_cnt, curPage_loss = evaluate_pdf_layout(page_id, page, model_output_json) # isSimpleLayout_flag, fullColumn_cnt, subColumn_cnt, curPage_loss = evaluate_pdf_layout(page_id, page, model_output_json)
接下来开始进行预处理过程 接下来开始进行预处理过程
""" """
title_bboxs = parse_titles(page_id, page, model_output_json) # title_bboxs = parse_titles(page_id, page, model_output_json)
"""去掉每页的页码、页眉、页脚""" """去掉每页的页码、页眉、页脚"""
page_no_bboxs = parse_pageNos(page_id, page, model_output_json) page_no_bboxs = parse_pageNos(page_id, page, model_output_json)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment