Support larger operator training samples

scripts/prepare_operator_real_data_samples.py

@@ -12,7 +12,7 @@ import argparse
 import json
 import os
 import sys
-from dataclasses import dataclass
+from dataclasses import dataclass, replace
 from pathlib import Path
 from typing import Any
 
@@ -196,6 +196,24 @@ def parse_args() -> argparse.Namespace:
         default="operator_samples_manifest.json",
         help="Manifest filename written inside output-dir.",
     )
+    parser.add_argument(
+        "--width",
+        type=int,
+        default=int(os.environ.get("OPERATOR_SAMPLE_WIDTH", "512")),
+        help="Orthophoto WMS output width in pixels. Use larger values for operator training datasets.",
+    )
+    parser.add_argument(
+        "--height",
+        type=int,
+        default=int(os.environ.get("OPERATOR_SAMPLE_HEIGHT", "512")),
+        help="Orthophoto WMS output height in pixels. Use larger values for operator training datasets.",
+    )
+    parser.add_argument(
+        "--half-size-scale",
+        type=float,
+        default=float(os.environ.get("OPERATOR_SAMPLE_HALF_SIZE_SCALE", "1")),
+        help="Multiplier applied to each documented AOI half-size in meters.",
+    )
     return parser.parse_args()
 
 
@@ -229,6 +247,25 @@ def selected_samples(raw: str) -> list[OperatorSample]:
     return [SAMPLES[slug] for slug in slugs]
 
 
+def apply_sample_overrides(
+    sample: OperatorSample,
+    *,
+    width: int,
+    height: int,
+    half_size_scale: float,
+) -> OperatorSample:
+    if width <= 0 or height <= 0:
+        raise SystemExit("--width and --height must be positive integers")
+    if half_size_scale <= 0:
+        raise SystemExit("--half-size-scale must be greater than zero")
+    return replace(
+        sample,
+        width=width,
+        height=height,
+        half_size_m=sample.half_size_m * half_size_scale,
+    )
+
+
 def sample_bounds(sample: OperatorSample) -> tuple[tuple[float, float, float, float], list[float]]:
     lambert = Transformer.from_crs("EPSG:4326", "EPSG:31370", always_xy=True)
     wgs84 = Transformer.from_crs("EPSG:31370", "EPSG:4326", always_xy=True)
@@ -273,6 +310,12 @@ def geojson_feature_count(path: Path) -> int:
     return len(payload.get("features") or [])
 
 
+def sample_artifact_paths(sample: OperatorSample, output_dir: Path) -> tuple[Path, Path]:
+    ortho_path = output_dir / f"{sample.slug}_orthophoto_wms_{sample.width}.tif"
+    reference_path = output_dir / f"{sample.slug}_grb_gbg_buildings.geojson"
+    return ortho_path, reference_path
+
+
 def fetch_orthophoto(sample: OperatorSample, ortho_path: Path, lambert_bbox: tuple[float, float, float, float]) -> str:
     minx, miny, maxx, maxy = lambert_bbox
     wms_params = {
@@ -352,8 +395,7 @@ def fetch_reference(sample: OperatorSample, reference_path: Path, geo_bbox: list
 
 
 def prepare_sample(sample: OperatorSample, output_dir: Path, force: bool) -> dict[str, Any]:
-    ortho_path = output_dir / f"{sample.slug}_orthophoto_wms_512.tif"
-    reference_path = output_dir / f"{sample.slug}_grb_gbg_buildings.geojson"
+    ortho_path, reference_path = sample_artifact_paths(sample, output_dir)
     lambert_bbox, geo_bbox = sample_bounds(sample)
     skip_existing = ortho_path.exists() and reference_path.exists() and not force
 
@@ -370,6 +412,8 @@ def prepare_sample(sample: OperatorSample, output_dir: Path, force: bool) -> dic
         "center_lon": sample.center_lon,
         "center_lat": sample.center_lat,
         "half_size_m": sample.half_size_m,
+        "width": sample.width,
+        "height": sample.height,
         "sample_role": sample.sample_role,
         "allow_empty_reference": sample.allow_empty_reference,
         "raster_path": str(ortho_path),
@@ -416,13 +460,28 @@ def main() -> int:
     ensure_gis_dependencies()
     output_dir: Path = args.output_dir
     output_dir.mkdir(parents=True, exist_ok=True)
-    samples = [prepare_sample(sample, output_dir, force=args.force) for sample in selected_samples(args.samples)]
+    samples = [
+        prepare_sample(
+            apply_sample_overrides(
+                sample,
+                width=args.width,
+                height=args.height,
+                half_size_scale=args.half_size_scale,
+            ),
+            output_dir,
+            force=args.force,
+        )
+        for sample in selected_samples(args.samples)
+    ]
     write_readme(output_dir, samples)
 
     manifest = {
         "schema_version": 1,
         "description": "GeoIntel operator real-data samples for configured-YOLO QA validation.",
         "output_dir": str(output_dir),
+        "sample_width": args.width,
+        "sample_height": args.height,
+        "half_size_scale": args.half_size_scale,
         "samples": samples,
     }
     manifest_path = output_dir / args.manifest_name