functional_pil.py

import numbers

import torch
try:
    import accimage
except ImportError:
    accimage = None
from PIL import Image, ImageOps, ImageEnhance
import numpy as np


@torch.jit.unused
def _is_pil_image(img):
    if accimage is not None:
        return isinstance(img, (Image.Image, accimage.Image))
    else:
        return isinstance(img, Image.Image)


@torch.jit.unused
def hflip(img):
    """Horizontally flip the given PIL Image.

    Args:
        img (PIL Image): Image to be flipped.

    Returns:
        PIL Image:  Horizontally flipped image.
    """
    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    return img.transpose(Image.FLIP_LEFT_RIGHT)


@torch.jit.unused
def vflip(img):
    """Vertically flip the given PIL Image.

    Args:
        img (PIL Image): Image to be flipped.

    Returns:
        PIL Image:  Vertically flipped image.
    """
    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    return img.transpose(Image.FLIP_TOP_BOTTOM)


@torch.jit.unused
def adjust_brightness(img, brightness_factor):
    """Adjust brightness of an RGB image.

    Args:
        img (PIL Image): Image to be adjusted.
        brightness_factor (float):  How much to adjust the brightness. Can be
            any non negative number. 0 gives a black image, 1 gives the
            original image while 2 increases the brightness by a factor of 2.

    Returns:
        PIL Image: Brightness adjusted image.
    """
    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    enhancer = ImageEnhance.Brightness(img)
    img = enhancer.enhance(brightness_factor)
    return img


@torch.jit.unused
def adjust_contrast(img, contrast_factor):
    """Adjust contrast of an Image.
    Args:
        img (PIL Image): PIL Image to be adjusted.
        contrast_factor (float): How much to adjust the contrast. Can be any
            non negative number. 0 gives a solid gray image, 1 gives the
            original image while 2 increases the contrast by a factor of 2.
    Returns:
        PIL Image: Contrast adjusted image.
    """
    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    enhancer = ImageEnhance.Contrast(img)
    img = enhancer.enhance(contrast_factor)
    return img


@torch.jit.unused
def adjust_saturation(img, saturation_factor):
    """Adjust color saturation of an image.
    Args:
        img (PIL Image): PIL Image to be adjusted.
        saturation_factor (float):  How much to adjust the saturation. 0 will
            give a black and white image, 1 will give the original image while
            2 will enhance the saturation by a factor of 2.
    Returns:
        PIL Image: Saturation adjusted image.
    """
    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    enhancer = ImageEnhance.Color(img)
    img = enhancer.enhance(saturation_factor)
    return img


@torch.jit.unused
def adjust_hue(img, hue_factor):
    """Adjust hue of an image.

    The image hue is adjusted by converting the image to HSV and
    cyclically shifting the intensities in the hue channel (H).
    The image is then converted back to original image mode.

    `hue_factor` is the amount of shift in H channel and must be in the
    interval `[-0.5, 0.5]`.

    See `Hue`_ for more details.

    .. _Hue: https://en.wikipedia.org/wiki/Hue

    Args:
        img (PIL Image): PIL Image to be adjusted.
        hue_factor (float):  How much to shift the hue channel. Should be in
            [-0.5, 0.5]. 0.5 and -0.5 give complete reversal of hue channel in
            HSV space in positive and negative direction respectively.
            0 means no shift. Therefore, both -0.5 and 0.5 will give an image
            with complementary colors while 0 gives the original image.

    Returns:
        PIL Image: Hue adjusted image.
    """
    if not(-0.5 <= hue_factor <= 0.5):
        raise ValueError('hue_factor ({}) is not in [-0.5, 0.5].'.format(hue_factor))

    if not _is_pil_image(img):
        raise TypeError('img should be PIL Image. Got {}'.format(type(img)))

    input_mode = img.mode
    if input_mode in {'L', '1', 'I', 'F'}:
        return img

    h, s, v = img.convert('HSV').split()

    np_h = np.array(h, dtype=np.uint8)
    # uint8 addition take cares of rotation across boundaries
    with np.errstate(over='ignore'):
        np_h += np.uint8(hue_factor * 255)
    h = Image.fromarray(np_h, 'L')

    img = Image.merge('HSV', (h, s, v)).convert(input_mode)
    return img


@torch.jit.unused
def pad(img, padding, fill=0, padding_mode="constant"):
    r"""Pad the given PIL.Image on all sides with the given "pad" value.

    Args:
        img (PIL Image): Image to be padded.
        padding (int or tuple or list): Padding on each border. If a single int is provided this
            is used to pad all borders. If a tuple or list of length 2 is provided this is the padding
            on left/right and top/bottom respectively. If a tuple or list of length 4 is provided
            this is the padding for the left, top, right and bottom borders respectively. For compatibility reasons
            with ``functional_tensor.pad``, if a tuple or list of length 1 is provided, it is interpreted as
            a single int.
        fill (int or str or tuple): Pixel fill value for constant fill. Default is 0. If a tuple of
            length 3, it is used to fill R, G, B channels respectively.
            This value is only used when the padding_mode is constant.
        padding_mode: Type of padding. Should be: constant, edge, reflect or symmetric. Default is constant.

            - constant: pads with a constant value, this value is specified with fill

            - edge: pads with the last value on the edge of the image

            - reflect: pads with reflection of image (without repeating the last value on the edge)

                       padding [1, 2, 3, 4] with 2 elements on both sides in reflect mode
                       will result in [3, 2, 1, 2, 3, 4, 3, 2]

            - symmetric: pads with reflection of image (repeating the last value on the edge)

                         padding [1, 2, 3, 4] with 2 elements on both sides in symmetric mode
                         will result in [2, 1, 1, 2, 3, 4, 4, 3]

    Returns:
        PIL Image: Padded image.
    """

    if not _is_pil_image(img):
        raise TypeError("img should be PIL Image. Got {}".format(type(img)))

    if not isinstance(padding, (numbers.Number, tuple, list)):
        raise TypeError("Got inappropriate padding arg")
    if not isinstance(fill, (numbers.Number, str, tuple)):
        raise TypeError("Got inappropriate fill arg")
    if not isinstance(padding_mode, str):
        raise TypeError("Got inappropriate padding_mode arg")

    if isinstance(padding, list):
        padding = tuple(padding)

    if isinstance(padding, tuple) and len(padding) not in [1, 2, 4]:
        raise ValueError("Padding must be an int or a 1, 2, or 4 element tuple, not a " +
                         "{} element tuple".format(len(padding)))

    if isinstance(padding, tuple) and len(padding) == 1:
        # Compatibility with `functional_tensor.pad`
        padding = padding[0]

    if padding_mode not in ["constant", "edge", "reflect", "symmetric"]:
        raise ValueError("Padding mode should be either constant, edge, reflect or symmetric")

    if padding_mode == "constant":
        if isinstance(fill, numbers.Number):
            fill = (fill,) * len(img.getbands())
        if len(fill) != len(img.getbands()):
            raise ValueError("fill should have the same number of elements "
                             "as the number of channels in the image "
                             "({}), got {} instead".format(len(img.getbands()), len(fill)))
        if img.mode == "P":
            palette = img.getpalette()
            image = ImageOps.expand(img, border=padding, fill=fill)
            image.putpalette(palette)
            return image

        return ImageOps.expand(img, border=padding, fill=fill)
    else:
        if isinstance(padding, int):
            pad_left = pad_right = pad_top = pad_bottom = padding
        if isinstance(padding, tuple) and len(padding) == 2:
            pad_left = pad_right = padding[0]
            pad_top = pad_bottom = padding[1]
        if isinstance(padding, tuple) and len(padding) == 4:
            pad_left = padding[0]
            pad_top = padding[1]
            pad_right = padding[2]
            pad_bottom = padding[3]

        if img.mode == 'P':
            palette = img.getpalette()
            img = np.asarray(img)
            img = np.pad(img, ((pad_top, pad_bottom), (pad_left, pad_right)), padding_mode)
            img = Image.fromarray(img)
            img.putpalette(palette)
            return img

        img = np.asarray(img)
        # RGB image
        if len(img.shape) == 3:
            img = np.pad(img, ((pad_top, pad_bottom), (pad_left, pad_right), (0, 0)), padding_mode)
        # Grayscale image
        if len(img.shape) == 2:
            img = np.pad(img, ((pad_top, pad_bottom), (pad_left, pad_right)), padding_mode)

        return Image.fromarray(img)