vla / scripts /prepare_baseline_dataset.py
anhtld's picture
Initial commit: DoVLA-CIL codebase (h=16 breakthrough)
adc02fa verified
Raw
History Blame Contribute Delete
1.12 kB
#!/usr/bin/env python
from __future__ import annotations
import argparse
import sys
from pathlib import Path
PROJECT_ROOT = Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
sys.path.insert(0, str(PROJECT_ROOT))
from dovla_cil.experiments.baselines import ( # noqa: E402
list_baselines,
prepare_dataset_for_baseline,
)
def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser(description="Prepare a transformed CIL baseline dataset.")
parser.add_argument("--dataset", type=Path, required=True)
parser.add_argument("--baseline", choices=list_baselines(), required=True)
parser.add_argument("--out", type=Path, required=True)
parser.add_argument("--shard-size", type=int, default=2048)
parser.add_argument("--seed", type=int, default=0)
args = parser.parse_args(argv)
output = prepare_dataset_for_baseline(
args.dataset,
args.baseline,
args.out,
shard_size=args.shard_size,
seed=args.seed,
)
print(output)
return 0
if __name__ == "__main__":
raise SystemExit(main())