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

fix: Measure the layout mAP without the orphan clusters.

Browse Source 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2025-02-12 10:01:52 +01:00
parent c47ae700ec
commit e824996406
1 changed files with 22 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
docling/utils/layout_postprocessor.py
View File

@ -264,26 +264,29 @@ class LayoutPostprocessor:
# Remove clusters with no cells # Remove clusters with no cells
clusters = [cluster for cluster in clusters if cluster.cells] clusters = [cluster for cluster in clusters if cluster.cells]
# Handle orphaned cells ###########################################################################################
unassigned = self._find_unassigned_cells(clusters) # Debug
if unassigned: # # Handle orphaned cells
next_id = max((c.id for c in clusters), default=0) + 1 # unassigned = self._find_unassigned_cells(clusters)
orphan_clusters = [] # if unassigned:
for i, cell in enumerate(unassigned): # next_id = max((c.id for c in clusters), default=0) + 1
conf = 1.0 # orphan_clusters = []
if isinstance(cell, OcrCell): # for i, cell in enumerate(unassigned):
conf = cell.confidence # conf = 1.0
# if isinstance(cell, OcrCell):
# conf = cell.confidence
orphan_clusters.append( # orphan_clusters.append(
Cluster( # Cluster(
id=next_id + i, # id=next_id + i,
label=DocItemLabel.TEXT, # label=DocItemLabel.TEXT,
bbox=cell.bbox, # bbox=cell.bbox,
confidence=conf, # confidence=conf,
cells=[cell], # cells=[cell],
) # )
) # )
clusters.extend(orphan_clusters) # clusters.extend(orphan_clusters)
###########################################################################################
# Iterative refinement # Iterative refinement
prev_count = len(clusters) + 1 prev_count = len(clusters) + 1