scripts/prepare_ifakefakedb.py

"""
scripts/prepare_ifakefakedb.py

Prepares the iFakeFaceDB dataset for fingerprint engine training.
Kaggle slug: tapakah68/artificial-faces-dataset or similar.

iFakeFaceDB contains ~87k StyleGAN-generated fake faces, useful for
increasing unknown_gan class coverage.

Kaggle usage:
  !python scripts/prepare_ifakefakedb.py \
    --source  /kaggle/input/artificial-faces-dataset \
    --output  /kaggle/working/processed/fingerprint \
    --max     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)
    if not source.exists():
        log.error(f"Source not found: {source}")
        return

    rng  = random.Random(args.seed)
    imgs = [p for p in source.rglob("*") if p.suffix.lower() in IMG_EXTS]
    rng.shuffle(imgs)
    imgs = imgs[:args.max]

    n_train = int(len(imgs) * 0.85)
    splits  = {"train": imgs[:n_train], "val": imgs[n_train:]}

    for split, subset in splits.items():
        dst_dir = Path(args.output) / split / "fake"
        dst_dir.mkdir(parents=True, exist_ok=True)
        for img in subset:
            dst = dst_dir / f"ifake_{img.name}"
            if not dst.exists():
                shutil.copy2(img, dst)
        log.info(f"  {split}/fake: {len(subset)} images (generator: unknown_gan / StyleGAN)")

    log.info("iFakeFaceDB preparation complete.")


def parse_args():
    p = argparse.ArgumentParser()
    p.add_argument("--source", default="/kaggle/input/artificial-faces-dataset")
    p.add_argument("--output", default="/kaggle/working/processed/fingerprint")
    p.add_argument("--max",    type=int, default=20000)
    p.add_argument("--seed",   type=int, default=42)
    return p.parse_args()


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