Shortcuts

Source code for torchvision.transforms.functional

from __future__ import division
import torch
import sys
import math
from PIL import Image, ImageOps, ImageEnhance, __version__ as PILLOW_VERSION
try:
    import accimage
except ImportError:
    accimage = None
import numpy as np
from numpy import sin, cos, tan
import numbers
import collections
import warnings

if sys.version_info < (3, 3):
    Sequence = collections.Sequence
    Iterable = collections.Iterable
else:
    Sequence = collections.abc.Sequence
    Iterable = collections.abc.Iterable


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


def _is_tensor_image(img):
    return torch.is_tensor(img) and img.ndimension() == 3


def _is_numpy(img):
    return isinstance(img, np.ndarray)


def _is_numpy_image(img):
    return img.ndim in {2, 3}


[docs]def to_tensor(pic): """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. See ``ToTensor`` for more details. Args: pic (PIL Image or numpy.ndarray): Image to be converted to tensor. Returns: Tensor: Converted image. """ if not(_is_pil_image(pic) or _is_numpy(pic)): raise TypeError('pic should be PIL Image or ndarray. Got {}'.format(type(pic))) if _is_numpy(pic) and not _is_numpy_image(pic): raise ValueError('pic should be 2/3 dimensional. Got {} dimensions.'.format(pic.ndim)) if isinstance(pic, np.ndarray): # handle numpy array if pic.ndim == 2: pic = pic[:, :, None] img = torch.from_numpy(pic.transpose((2, 0, 1))) # backward compatibility if isinstance(img, torch.ByteTensor): return img.float().div(255) else: return img if accimage is not None and isinstance(pic, accimage.Image): nppic = np.zeros([pic.channels, pic.height, pic.width], dtype=np.float32) pic.copyto(nppic) return torch.from_numpy(nppic) # handle PIL Image if pic.mode == 'I': img = torch.from_numpy(np.array(pic, np.int32, copy=False)) elif pic.mode == 'I;16': img = torch.from_numpy(np.array(pic, np.int16, copy=False)) elif pic.mode == 'F': img = torch.from_numpy(np.array(pic, np.float32, copy=False)) elif pic.mode == '1': img = 255 * torch.from_numpy(np.array(pic, np.uint8, copy=False)) else: img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes())) img = img.view(pic.size[1], pic.size[0], len(pic.getbands())) # put it from HWC to CHW format # yikes, this transpose takes 80% of the loading time/CPU img = img.transpose(0, 1).transpose(0, 2).contiguous() if isinstance(img, torch.ByteTensor): return img.float().div(255) else: return img
[docs]def to_pil_image(pic, mode=None): """Convert a tensor or an ndarray to PIL Image. See :class:`~torchvision.transforms.ToPILImage` for more details. Args: pic (Tensor or numpy.ndarray): Image to be converted to PIL Image. mode (`PIL.Image mode`_): color space and pixel depth of input data (optional). .. _PIL.Image mode: https://pillow.readthedocs.io/en/latest/handbook/concepts.html#concept-modes Returns: PIL Image: Image converted to PIL Image. """ if not(isinstance(pic, torch.Tensor) or isinstance(pic, np.ndarray)): raise TypeError('pic should be Tensor or ndarray. Got {}.'.format(type(pic))) elif isinstance(pic, torch.Tensor): if pic.ndimension() not in {2, 3}: raise ValueError('pic should be 2/3 dimensional. Got {} dimensions.'.format(pic.ndimension())) elif pic.ndimension() == 2: # if 2D image, add channel dimension (CHW) pic = pic.unsqueeze(0) elif isinstance(pic, np.ndarray): if pic.ndim not in {2, 3}: raise ValueError('pic should be 2/3 dimensional. Got {} dimensions.'.format(pic.ndim)) elif pic.ndim == 2: # if 2D image, add channel dimension (HWC) pic = np.expand_dims(pic, 2) npimg = pic if isinstance(pic, torch.FloatTensor) and mode != 'F': pic = pic.mul(255).byte() if isinstance(pic, torch.Tensor): npimg = np.transpose(pic.numpy(), (1, 2, 0)) if not isinstance(npimg, np.ndarray): raise TypeError('Input pic must be a torch.Tensor or NumPy ndarray, ' + 'not {}'.format(type(npimg))) if npimg.shape[2] == 1: expected_mode = None npimg = npimg[:, :, 0] if npimg.dtype == np.uint8: expected_mode = 'L' elif npimg.dtype == np.int16: expected_mode = 'I;16' elif npimg.dtype == np.int32: expected_mode = 'I' elif npimg.dtype == np.float32: expected_mode = 'F' if mode is not None and mode != expected_mode: raise ValueError("Incorrect mode ({}) supplied for input type {}. Should be {}" .format(mode, np.dtype, expected_mode)) mode = expected_mode elif npimg.shape[2] == 2: permitted_2_channel_modes = ['LA'] if mode is not None and mode not in permitted_2_channel_modes: raise ValueError("Only modes {} are supported for 2D inputs".format(permitted_2_channel_modes)) if mode is None and npimg.dtype == np.uint8: mode = 'LA' elif npimg.shape[2] == 4: permitted_4_channel_modes = ['RGBA', 'CMYK', 'RGBX'] if mode is not None and mode not in permitted_4_channel_modes: raise ValueError("Only modes {} are supported for 4D inputs".format(permitted_4_channel_modes)) if mode is None and npimg.dtype == np.uint8: mode = 'RGBA' else: permitted_3_channel_modes = ['RGB', 'YCbCr', 'HSV'] if mode is not None and mode not in permitted_3_channel_modes: raise ValueError("Only modes {} are supported for 3D inputs".format(permitted_3_channel_modes)) if mode is None and npimg.dtype == np.uint8: mode = 'RGB' if mode is None: raise TypeError('Input type {} is not supported'.format(npimg.dtype)) return Image.fromarray(npimg, mode=mode)
[docs]def normalize(tensor, mean, std, inplace=False): """Normalize a tensor image with mean and standard deviation. .. note:: This transform acts out of place by default, i.e., it does not mutates the input tensor. See :class:`~torchvision.transforms.Normalize` for more details. Args: tensor (Tensor): Tensor image of size (C, H, W) to be normalized. mean (sequence): Sequence of means for each channel. std (sequence): Sequence of standard deviations for each channel. inplace(bool,optional): Bool to make this operation inplace. Returns: Tensor: Normalized Tensor image. """ if not _is_tensor_image(tensor): raise TypeError('tensor is not a torch image.') if not inplace: tensor = tensor.clone() dtype = tensor.dtype mean = torch.as_tensor(mean, dtype=dtype, device=tensor.device) std = torch.as_tensor(std, dtype=dtype, device=tensor.device) tensor.sub_(mean[:, None, None]).div_(std[:, None, None]) return tensor
[docs]def resize(img, size, interpolation=Image.BILINEAR): r"""Resize the input PIL Image to the given size. Args: img (PIL Image): Image to be resized. size (sequence or int): Desired output size. If size is a sequence like (h, w), the output size will be matched to this. If size is an int, the smaller edge of the image will be matched to this number maintaing the aspect ratio. i.e, if height > width, then image will be rescaled to :math:`\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)` interpolation (int, optional): Desired interpolation. Default is ``PIL.Image.BILINEAR`` Returns: PIL Image: Resized image. """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) if not (isinstance(size, int) or (isinstance(size, Iterable) and len(size) == 2)): raise TypeError('Got inappropriate size arg: {}'.format(size)) if isinstance(size, int): w, h = img.size if (w <= h and w == size) or (h <= w and h == size): return img if w < h: ow = size oh = int(size * h / w) return img.resize((ow, oh), interpolation) else: oh = size ow = int(size * w / h) return img.resize((ow, oh), interpolation) else: return img.resize(size[::-1], interpolation)
def scale(*args, **kwargs): warnings.warn("The use of the transforms.Scale transform is deprecated, " + "please use transforms.Resize instead.") return resize(*args, **kwargs)
[docs]def pad(img, padding, fill=0, padding_mode='constant'): r"""Pad the given PIL Image on all sides with specified padding mode and fill value. Args: img (PIL Image): Image to be padded. padding (int or tuple): Padding on each border. If a single int is provided this is used to pad all borders. If tuple of length 2 is provided this is the padding on left/right and top/bottom respectively. If a tuple of length 4 is provided this is the padding for the left, top, right and bottom borders respectively. fill: 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)): 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, Sequence) and len(padding) not in [2, 4]: raise ValueError("Padding must be an int or a 2, or 4 element tuple, not a " + "{} element tuple".format(len(padding))) assert padding_mode in ['constant', 'edge', 'reflect', 'symmetric'], \ 'Padding mode should be either constant, edge, reflect or symmetric' if padding_mode == 'constant': 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, Sequence) and len(padding) == 2: pad_left = pad_right = padding[0] pad_top = pad_bottom = padding[1] if isinstance(padding, Sequence) 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)
[docs]def crop(img, top, left, height, width): """Crop the given PIL Image. Args: img (PIL Image): Image to be cropped. (0,0) denotes the top left corner of the image. top (int): Vertical component of the top left corner of the crop box. left (int): Horizontal component of the top left corner of the crop box. height (int): Height of the crop box. width (int): Width of the crop box. Returns: PIL Image: Cropped image. """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) return img.crop((left, top, left + width, top + height))
[docs]def center_crop(img, output_size): """Crop the given PIL Image and resize it to desired size. Args: img (PIL Image): Image to be cropped. (0,0) denotes the top left corner of the image. output_size (sequence or int): (height, width) of the crop box. If int, it is used for both directions Returns: PIL Image: Cropped image. """ if isinstance(output_size, numbers.Number): output_size = (int(output_size), int(output_size)) image_width, image_height = img.size crop_height, crop_width = output_size crop_top = int(round((image_height - crop_height) / 2.)) crop_left = int(round((image_width - crop_width) / 2.)) return crop(img, crop_top, crop_left, crop_height, crop_width)
[docs]def resized_crop(img, top, left, height, width, size, interpolation=Image.BILINEAR): """Crop the given PIL Image and resize it to desired size. Notably used in :class:`~torchvision.transforms.RandomResizedCrop`. Args: img (PIL Image): Image to be cropped. (0,0) denotes the top left corner of the image. top (int): Vertical component of the top left corner of the crop box. left (int): Horizontal component of the top left corner of the crop box. height (int): Height of the crop box. width (int): Width of the crop box. size (sequence or int): Desired output size. Same semantics as ``resize``. interpolation (int, optional): Desired interpolation. Default is ``PIL.Image.BILINEAR``. Returns: PIL Image: Cropped image. """ assert _is_pil_image(img), 'img should be PIL Image' img = crop(img, top, left, height, width) img = resize(img, size, interpolation) return img
[docs]def hflip(img): """Horizontally flip the given PIL Image. Args: img (PIL Image): Image to be flipped. Returns: PIL Image: Horizontall 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)
def _get_perspective_coeffs(startpoints, endpoints): """Helper function to get the coefficients (a, b, c, d, e, f, g, h) for the perspective transforms. In Perspective Transform each pixel (x, y) in the orignal image gets transformed as, (x, y) -> ( (ax + by + c) / (gx + hy + 1), (dx + ey + f) / (gx + hy + 1) ) Args: List containing [top-left, top-right, bottom-right, bottom-left] of the orignal image, List containing [top-left, top-right, bottom-right, bottom-left] of the transformed image Returns: octuple (a, b, c, d, e, f, g, h) for transforming each pixel. """ matrix = [] for p1, p2 in zip(endpoints, startpoints): matrix.append([p1[0], p1[1], 1, 0, 0, 0, -p2[0] * p1[0], -p2[0] * p1[1]]) matrix.append([0, 0, 0, p1[0], p1[1], 1, -p2[1] * p1[0], -p2[1] * p1[1]]) A = torch.tensor(matrix, dtype=torch.float) B = torch.tensor(startpoints, dtype=torch.float).view(8) res = torch.lstsq(B, A)[0] return res.squeeze_(1).tolist()
[docs]def perspective(img, startpoints, endpoints, interpolation=Image.BICUBIC): """Perform perspective transform of the given PIL Image. Args: img (PIL Image): Image to be transformed. startpoints: List containing [top-left, top-right, bottom-right, bottom-left] of the orignal image endpoints: List containing [top-left, top-right, bottom-right, bottom-left] of the transformed image interpolation: Default- Image.BICUBIC Returns: PIL Image: Perspectively transformed Image. """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) coeffs = _get_perspective_coeffs(startpoints, endpoints) return img.transform(img.size, Image.PERSPECTIVE, coeffs, interpolation)
[docs]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)
[docs]def five_crop(img, size): """Crop the given PIL Image into four corners and the central crop. .. Note:: This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your ``Dataset`` returns. Args: size (sequence or int): Desired output size of the crop. If size is an int instead of sequence like (h, w), a square crop (size, size) is made. Returns: tuple: tuple (tl, tr, bl, br, center) Corresponding top left, top right, bottom left, bottom right and center crop. """ if isinstance(size, numbers.Number): size = (int(size), int(size)) else: assert len(size) == 2, "Please provide only two dimensions (h, w) for size." image_width, image_height = img.size crop_height, crop_width = size if crop_width > image_width or crop_height > image_height: msg = "Requested crop size {} is bigger than input size {}" raise ValueError(msg.format(size, (image_height, image_width))) tl = img.crop((0, 0, crop_width, crop_height)) tr = img.crop((image_width - crop_width, 0, image_width, crop_height)) bl = img.crop((0, image_height - crop_height, crop_width, image_height)) br = img.crop((image_width - crop_width, image_height - crop_height, image_width, image_height)) center = center_crop(img, (crop_height, crop_width)) return (tl, tr, bl, br, center)
[docs]def ten_crop(img, size, vertical_flip=False): r"""Crop the given PIL Image into four corners and the central crop plus the flipped version of these (horizontal flipping is used by default). .. Note:: This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your ``Dataset`` returns. Args: size (sequence or int): Desired output size of the crop. If size is an int instead of sequence like (h, w), a square crop (size, size) is made. vertical_flip (bool): Use vertical flipping instead of horizontal Returns: tuple: tuple (tl, tr, bl, br, center, tl_flip, tr_flip, bl_flip, br_flip, center_flip) Corresponding top left, top right, bottom left, bottom right and center crop and same for the flipped image. """ if isinstance(size, numbers.Number): size = (int(size), int(size)) else: assert len(size) == 2, "Please provide only two dimensions (h, w) for size." first_five = five_crop(img, size) if vertical_flip: img = vflip(img) else: img = hflip(img) second_five = five_crop(img, size) return first_five + second_five
[docs]def adjust_brightness(img, brightness_factor): """Adjust brightness of an Image. Args: img (PIL Image): PIL 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
[docs]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
[docs]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
[docs]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
[docs]def adjust_gamma(img, gamma, gain=1): r"""Perform gamma correction on an image. Also known as Power Law Transform. Intensities in RGB mode are adjusted based on the following equation: .. math:: I_{\text{out}} = 255 \times \text{gain} \times \left(\frac{I_{\text{in}}}{255}\right)^{\gamma} See `Gamma Correction`_ for more details. .. _Gamma Correction: https://en.wikipedia.org/wiki/Gamma_correction Args: img (PIL Image): PIL Image to be adjusted. gamma (float): Non negative real number, same as :math:`\gamma` in the equation. gamma larger than 1 make the shadows darker, while gamma smaller than 1 make dark regions lighter. gain (float): The constant multiplier. """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) if gamma < 0: raise ValueError('Gamma should be a non-negative real number') input_mode = img.mode img = img.convert('RGB') gamma_map = [255 * gain * pow(ele / 255., gamma) for ele in range(256)] * 3 img = img.point(gamma_map) # use PIL's point-function to accelerate this part img = img.convert(input_mode) return img
[docs]def rotate(img, angle, resample=False, expand=False, center=None, fill=None): """Rotate the image by angle. Args: img (PIL Image): PIL Image to be rotated. angle (float or int): In degrees degrees counter clockwise order. resample (``PIL.Image.NEAREST`` or ``PIL.Image.BILINEAR`` or ``PIL.Image.BICUBIC``, optional): An optional resampling filter. See `filters`_ for more information. If omitted, or if the image has mode "1" or "P", it is set to ``PIL.Image.NEAREST``. expand (bool, optional): Optional expansion flag. If true, expands the output image to make it large enough to hold the entire rotated image. If false or omitted, make the output image the same size as the input image. Note that the expand flag assumes rotation around the center and no translation. center (2-tuple, optional): Optional center of rotation. Origin is the upper left corner. Default is the center of the image. fill (n-tuple or int or float): Pixel fill value for area outside the rotated image. If int or float, the value is used for all bands respectively. Defaults to 0 for all bands. This option is only available for ``pillow>=5.2.0``. .. _filters: https://pillow.readthedocs.io/en/latest/handbook/concepts.html#filters """ def parse_fill(fill, num_bands): if PILLOW_VERSION < "5.2.0": if fill is None: return {} else: msg = ("The option to fill background area of the rotated image, " "requires pillow>=5.2.0") raise RuntimeError(msg) if fill is None: fill = 0 if isinstance(fill, (int, float)): fill = tuple([fill] * num_bands) if len(fill) != num_bands: msg = ("The number of elements in 'fill' does not match the number of " "bands of the image ({} != {})") raise ValueError(msg.format(len(fill), num_bands)) return {"fillcolor": fill} if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) opts = parse_fill(fill, len(img.getbands())) return img.rotate(angle, resample, expand, center, **opts)
def _get_inverse_affine_matrix(center, angle, translate, scale, shear): # Helper method to compute inverse matrix for affine transformation # As it is explained in PIL.Image.rotate # We need compute INVERSE of affine transformation matrix: M = T * C * RSS * C^-1 # where T is translation matrix: [1, 0, tx | 0, 1, ty | 0, 0, 1] # C is translation matrix to keep center: [1, 0, cx | 0, 1, cy | 0, 0, 1] # RSS is rotation with scale and shear matrix # RSS(a, s, (sx, sy)) = # = R(a) * S(s) * SHy(sy) * SHx(sx) # = [ s*cos(a - sy)/cos(sy), s*(-cos(a - sy)*tan(x)/cos(y) - sin(a)), 0 ] # [ s*sin(a + sy)/cos(sy), s*(-sin(a - sy)*tan(x)/cos(y) + cos(a)), 0 ] # [ 0 , 0 , 1 ] # # where R is a rotation matrix, S is a scaling matrix, and SHx and SHy are the shears: # SHx(s) = [1, -tan(s)] and SHy(s) = [1 , 0] # [0, 1 ] [-tan(s), 1] # # Thus, the inverse is M^-1 = C * RSS^-1 * C^-1 * T^-1 if isinstance(shear, numbers.Number): shear = [shear, 0] if not isinstance(shear, (tuple, list)) and len(shear) == 2: raise ValueError( "Shear should be a single value or a tuple/list containing " + "two values. Got {}".format(shear)) rot = math.radians(angle) sx, sy = [math.radians(s) for s in shear] cx, cy = center tx, ty = translate # RSS without scaling a = cos(rot - sy) / cos(sy) b = -cos(rot - sy) * tan(sx) / cos(sy) - sin(rot) c = sin(rot - sy) / cos(sy) d = -sin(rot - sy) * tan(sx) / cos(sy) + cos(rot) # Inverted rotation matrix with scale and shear # det([[a, b], [c, d]]) == 1, since det(rotation) = 1 and det(shear) = 1 M = [d, -b, 0, -c, a, 0] M = [x / scale for x in M] # Apply inverse of translation and of center translation: RSS^-1 * C^-1 * T^-1 M[2] += M[0] * (-cx - tx) + M[1] * (-cy - ty) M[5] += M[3] * (-cx - tx) + M[4] * (-cy - ty) # Apply center translation: C * RSS^-1 * C^-1 * T^-1 M[2] += cx M[5] += cy return M
[docs]def affine(img, angle, translate, scale, shear, resample=0, fillcolor=None): """Apply affine transformation on the image keeping image center invariant Args: img (PIL Image): PIL Image to be rotated. angle (float or int): rotation angle in degrees between -180 and 180, clockwise direction. translate (list or tuple of integers): horizontal and vertical translations (post-rotation translation) scale (float): overall scale shear (float or tuple or list): shear angle value in degrees between -180 to 180, clockwise direction. If a tuple of list is specified, the first value corresponds to a shear parallel to the x axis, while the second value corresponds to a shear parallel to the y axis. resample (``PIL.Image.NEAREST`` or ``PIL.Image.BILINEAR`` or ``PIL.Image.BICUBIC``, optional): An optional resampling filter. See `filters`_ for more information. If omitted, or if the image has mode "1" or "P", it is set to ``PIL.Image.NEAREST``. fillcolor (int): Optional fill color for the area outside the transform in the output image. (Pillow>=5.0.0) """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) assert isinstance(translate, (tuple, list)) and len(translate) == 2, \ "Argument translate should be a list or tuple of length 2" assert scale > 0.0, "Argument scale should be positive" output_size = img.size center = (img.size[0] * 0.5 + 0.5, img.size[1] * 0.5 + 0.5) matrix = _get_inverse_affine_matrix(center, angle, translate, scale, shear) kwargs = {"fillcolor": fillcolor} if PILLOW_VERSION[0] >= '5' else {} return img.transform(output_size, Image.AFFINE, matrix, resample, **kwargs)
[docs]def to_grayscale(img, num_output_channels=1): """Convert image to grayscale version of image. Args: img (PIL Image): Image to be converted to grayscale. Returns: PIL Image: Grayscale version of the image. if num_output_channels = 1 : returned image is single channel if num_output_channels = 3 : returned image is 3 channel with r = g = b """ if not _is_pil_image(img): raise TypeError('img should be PIL Image. Got {}'.format(type(img))) if num_output_channels == 1: img = img.convert('L') elif num_output_channels == 3: img = img.convert('L') np_img = np.array(img, dtype=np.uint8) np_img = np.dstack([np_img, np_img, np_img]) img = Image.fromarray(np_img, 'RGB') else: raise ValueError('num_output_channels should be either 1 or 3') return img
[docs]def erase(img, i, j, h, w, v, inplace=False): """ Erase the input Tensor Image with given value. Args: img (Tensor Image): Tensor image of size (C, H, W) to be erased i (int): i in (i,j) i.e coordinates of the upper left corner. j (int): j in (i,j) i.e coordinates of the upper left corner. h (int): Height of the erased region. w (int): Width of the erased region. v: Erasing value. inplace(bool, optional): For in-place operations. By default is set False. Returns: Tensor Image: Erased image. """ if not isinstance(img, torch.Tensor): raise TypeError('img should be Tensor Image. Got {}'.format(type(img))) if not inplace: img = img.clone() img[:, i:i + h, j:j + w] = v return img

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources