Jens/geointel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add guarded promoted YOLO activation
GeoIntel CI / docs-smoke (push) Has been cancelled
Details
GeoIntel CI / contract-smoke (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Codex
2026-07-11 10:45:06 +02:00
parent 340be960e9
commit b1a4074cc8
13 changed files with 550 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/AI_PIPELINES.md
+27 -5
View File
@@ -335,13 +335,35 @@ hard-negative gates, then run `sparse_building_context` as a separate review
matrix. The first expanded local model improved dense AOI F1, but Kasterlee-bos
false positives block default promotion.
The current inactive AOI1024 background-aware local model asset,
The AOI1024 background-aware local model asset,
`geointel-building-yolov8s-aoi1024bg512r3e50-pt`, is exposed in Detection Lab
only through deliberate operator profiles. `balanced-review` applies threshold
`0.15` for the strongest positive-AOI F1 observed so far; `conservative-review`
applies threshold `0.35` for higher precision review. Both profiles remain
candidate-only, not default-approved, because the promotion recommendation is
still `none` and background false-positive pressure has not passed the gate.
`0.15` for the strongest positive-AOI F1 observed so far, but remains
candidate-only because pure-empty false-positive pressure failed at that
threshold. `conservative-review` applies threshold `0.35` and is marked as the
promoted candidate after the split-background report passed the strict
pure-empty gate. Sparse-context detections remain review-only evidence, not a
default-promotion blocker.
To update a Tower/Unraid `.env` from a promoted report, use the guarded
activation helper. It validates the exact report candidate key, verifies that
the candidate has `promotion_status=promote_candidate`, resolves the local model
asset under the mounted models directory, and writes environment updates only
when `--apply` is supplied:
```bash
python scripts/activate_promoted_yolo_candidate.py \
--promotion-report artifacts/detection-model-promotion/split-aware/aoi1024bg512r3e50-high-threshold-split-20260710T222934Z/detection_model_promotion_report.json \
--candidate-key 'geointel-building-yolov8s-aoi1024bg512r3e50-pt|512|64|0.35' \
--models-dir /mnt/user/appdata/geointel/models \
--env-file /mnt/user/appdata/geointel/.env \
--json
```
Re-run with `--apply` only after reviewing the emitted env updates. The helper
does not download weights, load a model or run inference. Restart or rebuild the
runtime after applying because `YOLO_MODEL_PATH` is read from environment
configuration.
To compare the same model/tile/threshold grid across all prepared operator
samples, use: