"""Encode an image, or run a synthetic smoke check when no image is supplied.""" import argparse from pathlib import Path import coremltools as ct import numpy as np from PIL import Image, ImageOps def main() -> None: parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("image", type=Path, nargs="?") parser.add_argument("--model", type=Path, default=Path("models/DINOv3ViTB16-FP32-448.mlpackage")) parser.add_argument("--output", type=Path) args = parser.parse_args() model = ct.models.MLModel(str(args.model), compute_units=ct.ComputeUnit.ALL) image_type = model.get_spec().description.input[0].type.imageType size = (image_type.width, image_type.height) if args.image: with Image.open(args.image) as source: image = ImageOps.exif_transpose(source).convert("RGB").resize(size, Image.Resampling.BICUBIC) else: y, x = np.mgrid[0:size[1], 0:size[0]] pixels = np.stack((x * 255 // size[0], y * 255 // size[1], (x + y) * 255 // sum(size)), axis=-1).astype(np.uint8) image = Image.fromarray(pixels) prediction = model.predict({"image": image}) vector = np.asarray(prediction["embedding"], dtype=np.float32).reshape(-1) patches = np.asarray(prediction["patch_embeddings"], dtype=np.float32).reshape(-1, 768) if vector.shape != (768,) or not np.isfinite(vector).all(): raise SystemExit("Invalid embedding") if not np.isfinite(patches).all(): raise SystemExit("Invalid patch embeddings") norm = float(np.linalg.norm(vector)) if not np.isclose(norm, 1, atol=1e-4): raise SystemExit(f"Embedding is not normalized: {norm}") if args.output: args.output.parent.mkdir(parents=True, exist_ok=True) np.save(args.output, vector) print(f"shape={vector.shape}, dtype={vector.dtype}, L2 norm={norm:.8f}") print(f"patches={patches.shape} (unnormalized)") if __name__ == "__main__": main()