expand AI-assisted review to full building corpus

scripts/README.md

@@ -6,6 +6,11 @@ model and dataset hashes, standard Ultralytics detection metrics and a separate
 pure-background detection count. The output claim is validation ranking only;
 the script neither reads protected test data nor promotes a model.
 
+`render_operator_yolo_label_qa_contact_sheets.py` paginates complete visual
+reviews with `--tiles-per-sheet` (default `64`). This keeps large corpora
+inspectable while preserving deterministic tile selection, ordering, label
+accounting and stable `contact_sheet_001.png` naming for the first page.
+
 Setup-, import-, demo- en maintenance-scripts voor GeoIntel.
 
 ## WALOUS source provisioning

scripts/render_operator_yolo_label_qa_contact_sheets.py

@@ -19,7 +19,7 @@ from PIL import Image, ImageDraw, ImageFont
 
 JSON_NAME = "operator_yolo_label_qa_summary.json"
 MARKDOWN_NAME = "operator_yolo_label_qa_contact_sheet.md"
-CONTACT_SHEET_NAME = "contact_sheet_001.png"
+CONTACT_SHEET_NAME_TEMPLATE = "contact_sheet_{index:03d}.png"
 
 
 def parse_args() -> argparse.Namespace:
@@ -37,6 +37,12 @@ def parse_args() -> argparse.Namespace:
     )
     parser.add_argument("--columns", type=int, default=4, help="Contact-sheet columns")
     parser.add_argument("--thumb-size", type=int, default=256, help="Rendered tile thumbnail size in pixels")
+    parser.add_argument(
+        "--tiles-per-sheet",
+        type=int,
+        default=64,
+        help="Maximum rendered cards per contact-sheet page. Default: 64.",
+    )
     parser.add_argument(
         "--blank-range-threshold",
         type=int,
@@ -329,16 +335,17 @@ def build_report(summary: dict[str, Any], summary_path: Path, args: argparse.Nam
             }
         )
 
-    contact_sheets = []
-    if rendered_cards:
-        contact_sheets.append(
-            {
-                "path": CONTACT_SHEET_NAME,
-                "tile_count": len(rendered_cards),
-                "columns": args.columns,
-                "thumb_size": args.thumb_size,
-            }
-        )
+    if args.tiles_per_sheet <= 0:
+        raise ValueError("tiles_per_sheet must be positive")
+    contact_sheets = [
+        {
+            "path": CONTACT_SHEET_NAME_TEMPLATE.format(index=(start // args.tiles_per_sheet) + 1),
+            "tile_count": len(rendered_cards[start : start + args.tiles_per_sheet]),
+            "columns": args.columns,
+            "thumb_size": args.thumb_size,
+        }
+        for start in range(0, len(rendered_cards), args.tiles_per_sheet)
+    ]
 
     return (
         {
@@ -350,6 +357,7 @@ def build_report(summary: dict[str, Any], summary_path: Path, args: argparse.Nam
             "requested_sample_slugs": sorted(set(args.sample_slug)),
             "columns": args.columns,
             "thumb_size": args.thumb_size,
+            "tiles_per_sheet": args.tiles_per_sheet,
             "selected_tile_count": len(selected_tiles),
             "selected_sample_count": len(
                 {str(tile.get("sample_slug") or "unknown") for tile in selected_tiles}
@@ -424,8 +432,10 @@ def main() -> int:
 
     summary = load_json(summary_path)
     report, cards = build_report(summary, summary_path, args)
-    if cards:
-        build_contact_sheet(cards, args.columns, output_dir / CONTACT_SHEET_NAME)
+    for page_index, start in enumerate(range(0, len(cards), args.tiles_per_sheet), start=1):
+        page_cards = cards[start : start + args.tiles_per_sheet]
+        page_name = CONTACT_SHEET_NAME_TEMPLATE.format(index=page_index)
+        build_contact_sheet(page_cards, args.columns, output_dir / page_name)
 
     (output_dir / JSON_NAME).write_text(json.dumps(report, indent=2, sort_keys=True), encoding="utf-8")
     write_markdown(report, output_dir)