Function pad

src/transformers/src/transformers/image_transforms.py:667–750

Pads the `image` with the specified (height, width) `padding` and `mode`. Args: image (`np.ndarray`): The image to pad. padding (`int` or `Tuple[int, int]` or `Iterable[Tuple[int, int]]`): Padding to apply to the edges of the height, width axes. Can

(
    image: np.ndarray,
    padding: Union[int, Tuple[int, int], Iterable[Tuple[int, int]]],
    mode: PaddingMode = PaddingMode.CONSTANT,
    constant_values: Union[float, Iterable[float]] = 0.0,
    data_format: Optional[Union[str, ChannelDimension]] = None,
    input_data_format: Optional[Union[str, ChannelDimension]] = None,
)

def pad(
    image: np.ndarray,
    padding: Union[int, Tuple[int, int], Iterable[Tuple[int, int]]],
    mode: PaddingMode = PaddingMode.CONSTANT,
    constant_values: Union[float, Iterable[float]] = 0.0,
    data_format: Optional[Union[str, ChannelDimension]] = None,
    input_data_format: Optional[Union[str, ChannelDimension]] = None,
) -> np.ndarray:
    """
    Pads the `image` with the specified (height, width) `padding` and `mode`.

    Args:
        image (`np.ndarray`):
            The image to pad.
        padding (`int` or `Tuple[int, int]` or `Iterable[Tuple[int, int]]`):
            Padding to apply to the edges of the height, width axes. Can be one of three formats:
            - `((before_height, after_height), (before_width, after_width))` unique pad widths for each axis.
            - `((before, after),)` yields same before and after pad for height and width.
            - `(pad,)` or int is a shortcut for before = after = pad width for all axes.
        mode (`PaddingMode`):
            The padding mode to use. Can be one of:
                - `"constant"`: pads with a constant value.
                - `"reflect"`: pads with the reflection of the vector mirrored on the first and last values of the
                  vector along each axis.
                - `"replicate"`: pads with the replication of the last value on the edge of the array along each axis.
                - `"symmetric"`: pads with the reflection of the vector mirrored along the edge of the array.
        constant_values (`float` or `Iterable[float]`, *optional*):
            The value to use for the padding if `mode` is `"constant"`.
        data_format (`str` or `ChannelDimension`, *optional*):
            The channel dimension format for the output image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            If unset, will use same as the input image.
        input_data_format (`str` or `ChannelDimension`, *optional*):
            The channel dimension format for the input image. Can be one of:
                - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
                - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
            If unset, will use the inferred format of the input image.

    Returns:
        `np.ndarray`: The padded image.

    """
    if input_data_format is None:
        input_data_format = infer_channel_dimension_format(image)

    def _expand_for_data_format(values):
        """
        Convert values to be in the format expected by np.pad based on the data format.
        """
        if isinstance(values, (int, float)):
            values = ((values, values), (values, values))
        elif isinstance(values, tuple) and len(values) == 1:
            values = ((values[0], values[0]), (values[0], values[0]))
        elif isinstance(values, tuple) and len(values) == 2 and isinstance(values[0], int):
            values = (values, values)
        elif isinstance(values, tuple) and len(values) == 2 and isinstance(values[0], tuple):
            values = values