venv/lib/python3.11/site-packages/datasets/packaged_modules/imagefolder/imagefolder.py

import datasets

from ..folder_based_builder import folder_based_builder


logger = datasets.utils.logging.get_logger(__name__)


class ImageFolderConfig(folder_based_builder.FolderBasedBuilderConfig):
    """BuilderConfig for ImageFolder."""

    drop_labels: bool = None
    drop_metadata: bool = None

    def __post_init__(self):
        super().__post_init__()


class ImageFolder(folder_based_builder.FolderBasedBuilder):
    BASE_FEATURE = datasets.Image
    BASE_COLUMN_NAME = "image"
    BUILDER_CONFIG_CLASS = ImageFolderConfig
    EXTENSIONS: list[str]  # definition at the bottom of the script


# Obtained with:
# ```
# import PIL.Image
# IMAGE_EXTENSIONS = []
# PIL.Image.init()
# for ext, format in PIL.Image.EXTENSION.items():
#     if format in PIL.Image.OPEN:
#         IMAGE_EXTENSIONS.append(ext[1:])
# ```
# We intentionally do not run this code on launch because:
# (1) Pillow is an optional dependency, so importing Pillow in global namespace is not allowed
# (2) To ensure the list of supported extensions is deterministic
IMAGE_EXTENSIONS = [
    ".blp",
    ".bmp",
    ".dib",
    ".bufr",
    ".cur",
    ".pcx",
    ".dcx",
    ".dds",
    ".ps",
    ".eps",
    ".fit",
    ".fits",
    ".fli",
    ".flc",
    ".ftc",
    ".ftu",
    ".gbr",
    ".gif",
    ".grib",
    # ".h5",   # may contain zero or several images
    # ".hdf",  # may contain zero or several images
    ".png",
    ".apng",
    ".jp2",
    ".j2k",
    ".jpc",
    ".jpf",
    ".jpx",
    ".j2c",
    ".icns",
    ".ico",
    ".im",
    ".iim",
    ".tif",
    ".tiff",
    ".jfif",
    ".jpe",
    ".jpg",
    ".jpeg",
    ".mpg",
    ".mpeg",
    ".msp",
    ".pcd",
    ".pxr",
    ".pbm",
    ".pgm",
    ".ppm",
    ".pnm",
    ".psd",
    ".bw",
    ".rgb",
    ".rgba",
    ".sgi",
    ".ras",
    ".tga",
    ".icb",
    ".vda",
    ".vst",
    ".webp",
    ".wmf",
    ".emf",
    ".xbm",
    ".xpm",
]
ImageFolder.EXTENSIONS = IMAGE_EXTENSIONS