Promote focused small-building detector

scripts/export_operator_yolo_tile_dataset.py

@@ -26,7 +26,14 @@ PURE_EMPTY_BACKGROUND_CATEGORY = "pure_empty_negative"
 SPARSE_BACKGROUND_CATEGORY = "sparse_building_context"
 LOW_VARIANCE_NEGATIVE_SKIP_REASON = "low_visual_variance_negative"
 DEFAULT_VALIDATION_SAMPLE_SLUGS = frozenset(
-    {"turnhout", "retie", "westerlo", "arendonk_heide"}
+    {
+        "turnhout",
+        "retie",
+        "westerlo",
+        "arendonk_heide",
+        "vosselaar_center",
+        "grobbendonk_center",
+    }
 )
 DEFAULT_VALIDATION_SAMPLES = ",".join(sorted(DEFAULT_VALIDATION_SAMPLE_SLUGS))
 rasterio: Any = None
@@ -69,12 +76,20 @@ def parse_args() -> argparse.Namespace:
     )
     parser.add_argument("--tile-size", type=int, default=int(os.environ.get("OPERATOR_YOLO_TILE_SIZE", "256")))
     parser.add_argument("--stride", type=int, default=int(os.environ.get("OPERATOR_YOLO_TILE_STRIDE", "128")))
+    parser.add_argument(
+        "--samples",
+        default=os.environ.get("OPERATOR_YOLO_SAMPLES", ""),
+        help=(
+            "Optional comma/space separated manifest sample slugs to export. "
+            "An empty value keeps every manifest sample."
+        ),
+    )
     parser.add_argument(
         "--val-samples",
         default=os.environ.get("OPERATOR_YOLO_VAL_SAMPLES", DEFAULT_VALIDATION_SAMPLES),
         help=(
             "Comma/space separated sample slugs assigned to validation. "
-            "Defaults to the documented Turnhout, Retie, Westerlo and Arendonk-heide holdouts."
+            "Defaults to all documented validation samples."
         ),
     )
     parser.add_argument(
@@ -152,6 +167,31 @@ def split_slugs(raw: str) -> set[str]:
     return {value.strip().lower() for value in raw.replace(",", " ").split() if value.strip()}
 
 
+def select_manifest_samples(
+    samples: list[dict[str, Any]],
+    requested_slugs: set[str],
+) -> tuple[list[dict[str, Any]], list[str]]:
+    manifest_slugs = {
+        str(sample.get("sample_slug") or "").strip().lower()
+        for sample in samples
+        if str(sample.get("sample_slug") or "").strip()
+    }
+    if not requested_slugs:
+        return samples, []
+    unknown = requested_slugs - manifest_slugs
+    if unknown:
+        raise SystemExit(
+            "YOLO sample selection references unknown samples: " + ", ".join(sorted(unknown))
+        )
+    selected = [
+        sample
+        for sample in samples
+        if str(sample.get("sample_slug") or "").strip().lower() in requested_slugs
+    ]
+    excluded = sorted(manifest_slugs - requested_slugs)
+    return selected, excluded
+
+
 def validate_validation_split(samples: list[dict[str, Any]], val_slugs: set[str]) -> set[str]:
     sample_slugs = {
         str(sample.get("sample_slug") or "").strip().lower()
@@ -533,9 +573,13 @@ def main() -> int:
     ensure_yolo_directories(args.output_dir)
 
     manifest = json.loads(args.manifest_path.read_text(encoding="utf-8-sig"))
-    samples = manifest.get("samples") or []
-    if not samples:
+    manifest_samples = manifest.get("samples") or []
+    if not manifest_samples:
         raise SystemExit("Operator sample manifest contains no samples")
+    samples, excluded_sample_slugs = select_manifest_samples(
+        manifest_samples,
+        split_slugs(args.samples),
+    )
     val_slugs = validate_validation_split(samples, split_slugs(args.val_samples))
     exported_tiles: list[dict[str, Any]] = []
     for sample in samples:
@@ -584,7 +628,12 @@ def main() -> int:
         "min_label_visible_ratio": args.min_label_visible_ratio,
         "drop_low_variance_negatives": args.drop_low_variance_negatives,
         "blank_range_threshold": args.blank_range_threshold,
+        "source_manifest_sample_count": len(manifest_samples),
         "source_sample_count": len(samples),
+        "selected_sample_slugs": sorted(
+            str(sample.get("sample_slug") or "").strip().lower() for sample in samples
+        ),
+        "excluded_sample_slugs": excluded_sample_slugs,
         "validation_sample_slugs": sorted(val_slugs),
         **validation_coverage,
         "tile_count": len(kept_tiles),