Initial public release

scripts/build_grayscale_yolo_dataset.py

@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+"""Create a checksummed luminance-normalized YOLO dataset without changing labels/splits."""
+
+from __future__ import annotations
+
+import argparse
+import hashlib
+import json
+import shutil
+import sys
+from pathlib import Path
+
+from PIL import Image
+
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+if str(SCRIPT_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPT_DIR))
+
+from training_release_manifest import (  # noqa: E402
+    TrainingReleaseError,
+    assert_yolo_summary_bound_to_training_release,
+    file_sha256,
+    training_release_paths,
+)
+
+
+def sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with path.open("rb") as stream:
+        for chunk in iter(lambda: stream.read(1024 * 1024), b""):
+            digest.update(chunk)
+    return digest.hexdigest()
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--summary", type=Path, required=True)
+    parser.add_argument("--train-yaml", type=Path, required=True)
+    parser.add_argument("--corpus-manifest", type=Path, required=True)
+    parser.add_argument("--output-dir", type=Path, required=True)
+    parser.add_argument(
+        "--fixture-mode",
+        action="store_true",
+        help="Accept only an explicitly fixture-only release; never creates a production-ready derived dataset.",
+    )
+    parser.add_argument("--force", action="store_true")
+    args = parser.parse_args()
+    try:
+        release = assert_yolo_summary_bound_to_training_release(
+            summary_path=args.summary,
+            train_yaml=args.train_yaml,
+            corpus_manifest=args.corpus_manifest,
+            fixture_mode=args.fixture_mode,
+        )
+    except TrainingReleaseError as exc:
+        raise SystemExit(str(exc)) from exc
+    if args.output_dir.exists():
+        if not args.force:
+            raise SystemExit(f"Output exists: {args.output_dir}")
+        shutil.rmtree(args.output_dir)
+    args.output_dir.mkdir(parents=True)
+
+    summary = json.loads(args.summary.read_text(encoding="utf-8"))
+    converted = 0
+    for tile in summary["tiles"]:
+        split = tile["split"]
+        source_image = Path(tile["image_path"])
+        source_label = Path(tile["label_path"])
+        image_target = args.output_dir / "images" / split / source_image.name
+        label_target = args.output_dir / "labels" / split / source_label.name
+        image_target.parent.mkdir(parents=True, exist_ok=True)
+        label_target.parent.mkdir(parents=True, exist_ok=True)
+        with Image.open(source_image) as image:
+            image.convert("L").convert("RGB").save(image_target)
+        shutil.copyfile(source_label, label_target)
+        tile["image_path"] = str(image_target)
+        tile["label_path"] = str(label_target)
+        converted += 1
+
+    dataset_yaml = args.output_dir / "dataset.yaml"
+    dataset_yaml.write_text(
+        f"path: {args.output_dir}\ntrain: images/train\nval: images/val\nnames:\n  0: building\n",
+        encoding="utf-8",
+    )
+    # The source release binds the original image bytes.  These transformed
+    # bytes cannot inherit it, so remove its operational release pointers and
+    # retain them only as explicitly non-trainable parent evidence below.
+    for field_name in (
+        "training_release_manifest",
+        "training_release_manifest_sha256",
+        "training_release_freeze",
+        "training_asset_manifest",
+    ):
+        summary.pop(field_name, None)
+    summary.update(
+        {
+            "output_dir": str(args.output_dir),
+            "dataset_yaml": str(dataset_yaml),
+            "preprocessing": "luminance_rgb_replicated",
+            "source_summary": str(args.summary),
+            "source_summary_sha256": sha256(args.summary),
+        }
+    )
+    output_summary = args.output_dir / "yolo_tile_dataset_summary.json"
+    output_summary.write_text(json.dumps(summary, indent=2), encoding="utf-8")
+    evidence = {
+        "schema_version": 1,
+        "status": "ok",
+        "preprocessing": "luminance_rgb_replicated",
+        "source_summary": str(args.summary),
+        "source_summary_sha256": sha256(args.summary),
+        "source_training_release": str(training_release_paths(args.train_yaml)["release_manifest"]),
+        "source_training_release_sha256": file_sha256(
+            training_release_paths(args.train_yaml)["release_manifest"]
+        ),
+        "source_corpus_manifest_sha256": release["corpus"]["manifest_sha256"],
+        "converted_tile_count": converted,
+        "output_summary": str(output_summary),
+        "output_summary_sha256": sha256(output_summary),
+        "dataset_yaml": str(dataset_yaml),
+        "training_eligible": False,
+        "training_eligibility_reason": (
+            "Derived image bytes require a new governed corpus, validation report and immutable training release."
+        ),
+    }
+    (args.output_dir / "grayscale-dataset-evidence.json").write_text(
+        json.dumps(evidence, indent=2), encoding="utf-8"
+    )
+    print(json.dumps(evidence, indent=2))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())