scripts/prepare_cifake.py

"""
scripts/prepare_cifake.py

Prepares the CIFAKE dataset (Kaggle: bird-coder/cifake-real-and-ai-generated-synthetic-images)
for use in the fingerprint engine training pipeline.

CIFAKE contains 60k real images (CIFAR-10) and 60k AI-generated equivalents.
Useful as extra training data for the fingerprint engine.

Kaggle usage:
  !python scripts/prepare_cifake.py \
    --source  /kaggle/input/cifake-real-and-ai-generated-synthetic-images \
    --output  /kaggle/working/processed/fingerprint \
    --max_per_class 20000
"""
from __future__ import annotations

import argparse
import logging
import random
import shutil
from pathlib import Path

logging.basicConfig(level=logging.INFO, format="%(asctime)s  %(message)s")
log = logging.getLogger(__name__)

IMG_EXTS = {".jpg", ".jpeg", ".png"}


def main(args: argparse.Namespace) -> None:
    source = Path(args.source)
    output = Path(args.output)
    rng    = random.Random(args.seed)

    if not source.exists():
        log.error(f"Source not found: {source}")
        return

    for split in ["train", "test"]:
        for label, is_fake in [("REAL", "real"), ("FAKE", "fake")]:
            src_dir = source / split / label
            if not src_dir.exists():
                src_dir = source / label
            if not src_dir.exists():
                log.warning(f"  Not found: {src_dir}")
                continue

            imgs = [p for p in src_dir.iterdir() if p.suffix.lower() in IMG_EXTS]
            rng.shuffle(imgs)
            imgs = imgs[:args.max_per_class]

            out_split = "train" if split == "train" else "val"
            dst_dir   = output / out_split / is_fake
            dst_dir.mkdir(parents=True, exist_ok=True)

            for img in imgs:
                dst = dst_dir / f"cifake_{img.name}"
                if not dst.exists():
                    shutil.copy2(img, dst)

            log.info(f"  cifake/{split}/{label} → {out_split}/{is_fake}: {len(imgs)} images")

    log.info("CIFAKE preparation complete.")


def parse_args():
    p = argparse.ArgumentParser()
    p.add_argument("--source",        default="/kaggle/input/cifake-real-and-ai-generated-synthetic-images")
    p.add_argument("--output",        default="/kaggle/working/processed/fingerprint")
    p.add_argument("--max_per_class", type=int, default=20000)
    p.add_argument("--seed",          type=int, default=42)
    return p.parse_args()


if __name__ == "__main__":
    main(parse_args())