import glob import os input_path = os.getenv("REALISM_DATASET_DIGIFACE1M") input_img_list = sorted(glob.glob(os.path.join(input_path, '**/*.[jpJP][pnPN]*[gG]'), recursive=True)) print(f"Found {len(input-input_img_list)} images") with open('./list.txt', 'w') as file: file.writelines(input_img_list)