feat: disable auto include table title

cb1b02e7 · 许瑞 · f0c463ed · cb1b02e7
Commit cb1b02e7 authored Mar 26, 2024 by 许瑞
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

magic_pdf/pdf_parse_for_train.py magic_pdf/pdf_parse_for_train.py +1 -1

No files found.
--- a/magic_pdf/pdf_parse_for_train.py
+++ b/magic_pdf/pdf_parse_for_train.py
@@ -220,7 +220,7 @@ def parse_pdf_for_train(
        # 解析表格并对table_bboxes进行位置的微调,防止表格周围的文字被截断
        table_bboxes = parse_tables(page_id, page, model_output_json)
        table_bboxes = fix_tables(
-            page, table_bboxes, include_table_title=True, scan_line_num=2
+            page, table_bboxes, include_table_title=False, scan_line_num=2
        )  # 修正
        table_bboxes = fix_table_text_block(
            text_raw_blocks, table_bboxes