Expand operator hard-negative AOIs
GeoIntel CI / docs-smoke (push) Has been cancelled
GeoIntel CI / contract-smoke (push) Has been cancelled

This commit is contained in:
Codex
2026-07-09 02:15:54 +02:00
parent 34f09fe323
commit 54e6ad888e
6 changed files with 127 additions and 10 deletions
+11 -8
View File
@@ -182,13 +182,14 @@ This writes GeoTIFF/GeoJSON pairs and `operator_samples_manifest.json` under
`/app/storage/operator-data` inside the container, which maps to
`storage/operator-data` in the Tower appdata checkout. The default corpus
contains reference AOIs for Geel, Mol, Turnhout, Herentals, Balen, Retie and
Westerlo plus background candidates for Postel-bos, Lommel-heide and
Kasterlee-bos. Normal reference AOIs still fail when GRB returns no buildings;
background candidates are explicitly marked with `sample_role` and may write an
empty reference FeatureCollection for negative-tile training. The helper fetches
only the explicit documented AOIs, records Digitaal Vlaanderen attribution and
reuses existing files by default. Use `--force` only when the local runtime
artifacts should be regenerated.
Westerlo plus background candidates for Postel-bos, Lommel-heide,
Kasterlee-bos, Dessel-heide, Ravels-bos, Meerhout-bos, Geel-Bel,
Arendonk-heide and Herenthout-bos. Normal reference AOIs still fail when GRB
returns no buildings; background candidates are explicitly marked with
`sample_role` and may write an empty reference FeatureCollection for
negative-tile training. The helper fetches only the explicit documented AOIs,
records Digitaal Vlaanderen attribution and reuses existing files by default.
Use `--force` only when the local runtime artifacts should be regenerated.
The real-data smoke is intentionally mutating and refuses to run without
operator-supplied files. Current V1 upload support expects a georeferenced
@@ -351,6 +352,8 @@ Current Tower audit status:
- `yolo-building-tile-hardneg160r4` and `yolo-building-tile-hardneg160r8`:
repeat-heavy hard-negative variants; useful evidence, but add more unique
background AOIs before training another hard-negative-balanced candidate.
- Regenerate `operator_samples_manifest.json` after pulling Sprint 147+ so the
expanded unique background AOI set is available for the next tile export.
For hard-negative-balanced experiments, repeat only train-split negative tiles
from samples marked `sample_role=background_candidate`:
@@ -415,7 +418,7 @@ before changing model defaults:
```bash
OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \
OPERATOR_BACKGROUND_SAMPLE_SLUGS="postel_bos lommel_heide kasterlee_bos" \
OPERATOR_BACKGROUND_SAMPLE_SLUGS="postel_bos lommel_heide kasterlee_bos dessel_heide ravels_bos meerhout_bos geel_bel arendonk_heide herenthout_bos" \
QUALITY_MODEL_ASSET_IDS="geointel-building-yolov8n-expanded160e50-pt geointel-building-yolov8n-tile30-pt yolov8s-building-segmentation-pt" \
QUALITY_TILE_SIZES="640" \
QUALITY_TILE_OVERLAPS="64" \