photo_editor/dataset/subset.py

"""
Subset selection: first N image IDs from the canonical list.
N comes from settings (FIVEK_SUBSET_SIZE).
"""
from typing import List

from photo_editor.config import get_settings
from photo_editor.dataset.paths import list_all_image_ids


def get_subset_image_ids() -> List[str]:
    """
    Return the first FIVEK_SUBSET_SIZE image IDs from filesAdobe.txt.
    Order is deterministic for reproducibility.
    """
    s = get_settings()
    all_ids = list_all_image_ids(s.fivek_file_list)
    n = min(max(1, s.fivek_subset_size), len(all_ids))
    return all_ids[:n]