mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adapting label mapping for updated layout model

Browse Source 
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak 2024-10-03 16:04:40 +02:00
parent 9b72a61914
commit aba833ab56
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docling/models/layout_model.py
View File

@ -33,6 +33,7 @@ class LayoutModel:
"Page-footer", "Page-footer",
"Code", "Code",
"List-item", "List-item",
# "Title"
# "Formula", # "Formula",
] ]
PAGE_HEADER_LABELS = ["Page-header", "Page-footer"] PAGE_HEADER_LABELS = ["Page-header", "Page-footer"]
@ -71,6 +72,7 @@ class LayoutModel:
CLASS_REMAPPINGS = { CLASS_REMAPPINGS = {
"Document Index": "Table", "Document Index": "Table",
"Title": "Section-header"
} }
_log.debug("================= Start postprocess function ====================") _log.debug("================= Start postprocess function ====================")
@ -277,6 +279,7 @@ class LayoutModel:
bbox=BoundingBox.model_validate(pred_item), bbox=BoundingBox.model_validate(pred_item),
cells=[], cells=[],
) )
clusters.append(cluster) clusters.append(cluster)
# Map cells to clusters # Map cells to clusters