Pikaliov/depth_edges_annotate_worlduav
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update segmentation.gin to unified 17 classes

Browse Source 
All datasets now use the same 17-class prompt list for transfer
learning compatibility. World-UAV segmentation needs regeneration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
pikaliov
2026-04-17 22:08:56 +03:00
parent 3b5778e303
commit d1ddb40036
1 changed files with 19 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
in/config_files/segmentation.gin
View File

@@ -1,6 +1,5 @@
# Open-vocabulary segmentation parameters
# 12 cross-view invariant classes for geo-localization
# See docs/segmentation_class_analysis.md for full rationale
# Unified 17-class open-vocabulary segmentation (shared across all datasets)
# See scripts/seg_classes.py for canonical source, docs/segmentation_class_analysis.md for rationale
SegConfig.prompts = [
'background', # 0 — unclassified
'building', # 1 — buildings, rooftops
@@ -12,7 +11,13 @@ SegConfig.prompts = [
'farmland', # 7 — agricultural terraces, fields
'railway', # 8 — railway tracks, rails
'parking lot', # 9 — parking areas
'sidewalk', # 10 — sidewalks, pedestrian zones, embankments
'sidewalk', # 10 — sidewalks, pedestrian zones
'bare soil and plowed field', # 11 — plowed fields, construction sites
'roof and rooftop', # 12 — rooftops, solar panels
'sports field and playground', # 13 — courts, pitches
'muddy ground and wetland', # 14 — wet soil, marshes, levee banks
'embankment and levee', # 15 — earthen dams, canal walls
'swimming pool', # 16 — pools (GTA-UAV suburbs)
]
SegConfig.threshold = 0.15
SegConfig.default_resolution = 1008