Raise near-duplicate dedup threshold from 0.10 to 0.20

0.10 only removed burst shots (distance 0.01-0.05). Same-event photos with similar pose and lighting sit at 0.10-0.20 and were passing through, producing visually similar training images especially for people with small datasets. 0.20 removes these while still preserving genuinely different poses, expressions, and lighting conditions.
2026-06-14 02:52:12 +00:00
parent 6e34d41036
commit 694f860b6d
1 changed files with 1 additions and 1 deletions
@@ -304,7 +304,7 @@ def _select_by_embedding(
 # Near-Duplicate Removal
 # =============================================================================

-_DEDUP_THRESHOLD = 0.10  # cosine distance — burst shots are ~0.01-0.05 apart
+_DEDUP_THRESHOLD = 0.20  # cosine distance — burst shots ~0.01-0.05, same-event similar shots ~0.10-0.20


 def _dedup_embeddings(