import math
import numbers
import warnings
from typing import Any, Optional
import numpy as np
from PIL import Image
import torch
from torch import Tensor
from torch.jit.annotations import List, Tuple
try:
import accimage
except ImportError:
accimage = None
from . import functional_pil as F_pil
from . import functional_tensor as F_t
_is_pil_image = F_pil._is_pil_image
_parse_fill = F_pil._parse_fill
def _get_image_size(img: Tensor) -> List[int]:
"""Returns image sizea as (w, h)
"""
if isinstance(img, torch.Tensor):
return F_t._get_image_size(img)
return F_pil._get_image_size(img)
def _get_image_num_channels(img: Tensor) -> int:
if isinstance(img, torch.Tensor):
return F_t._get_image_num_channels(img)
return F_pil._get_image_num_channels(img)
@torch.jit.unused
def _is_numpy(img: Any) -> bool:
return isinstance(img, np.ndarray)
@torch.jit.unused
def _is_numpy_image(img: Any) -> bool:
return img.ndim in {2, 3}
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(F_pil._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))).contiguous()
# 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
img = img.permute((2, 0, 1)).contiguous()
if isinstance(img, torch.ByteTensor):
return img.float().div(255)
else:
return img
def pil_to_tensor(pic):
"""Convert a ``PIL Image`` to a tensor of the same type.
See :class:`~torchvision.transforms.PILToTensor` for more details.
Args:
pic (PIL Image): Image to be converted to tensor.
Returns:
Tensor: Converted image.
"""
if not F_pil._is_pil_image(pic):
raise TypeError('pic should be PIL Image. Got {}'.format(type(pic)))
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.as_tensor(nppic)
# handle PIL Image
img = torch.as_tensor(np.asarray(pic))
img = img.view(pic.size[1], pic.size[0], len(pic.getbands()))
# put it from HWC to CHW format
img = img.permute((2, 0, 1))
return img
def convert_image_dtype(image: torch.Tensor, dtype: torch.dtype = torch.float) -> torch.Tensor:
"""Convert a tensor image to the given ``dtype`` and scale the values accordingly
Args:
image (torch.Tensor): Image to be converted
dtype (torch.dtype): Desired data type of the output
Returns:
Tensor: Converted image
.. note::
When converting from a smaller to a larger integer ``dtype`` the maximum values are **not** mapped exactly.
If converted back and forth, this mismatch has no effect.
Raises:
RuntimeError: When trying to cast :class:`torch.float32` to :class:`torch.int32` or :class:`torch.int64` as
well as for trying to cast :class:`torch.float64` to :class:`torch.int64`. These conversions might lead to
overflow errors since the floating point ``dtype`` cannot store consecutive integers over the whole range
of the integer ``dtype``.
"""
if not isinstance(image, torch.Tensor):
raise TypeError('Input img should be Tensor Image')
return F_t.convert_image_dtype(image, dtype)
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.Tensor):
if pic.is_floating_point() and mode != 'F':
pic = pic.mul(255).byte()
npimg = np.transpose(pic.cpu().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)
def normalize(tensor: Tensor, mean: List[float], std: List[float], inplace: bool = False) -> Tensor:
"""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) or (B, 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 isinstance(tensor, torch.Tensor):
raise TypeError('Input tensor should be a torch tensor. Got {}.'.format(type(tensor)))
if tensor.ndim < 3:
raise ValueError('Expected tensor to be a tensor image of size (..., C, H, W). Got tensor.size() = '
'{}.'.format(tensor.size()))
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)
if (std == 0).any():
raise ValueError('std evaluated to zero after conversion to {}, leading to division by zero.'.format(dtype))
if mean.ndim == 1:
mean = mean.view(-1, 1, 1)
if std.ndim == 1:
std = std.view(-1, 1, 1)
tensor.sub_(mean).div_(std)
return tensor
def resize(img: Tensor, size: List[int], interpolation: int = Image.BILINEAR) -> Tensor:
r"""Resize the input image to the given size.
The image can be a PIL Image or a torch Tensor, in which case it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
Args:
img (PIL Image or Tensor): 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 maintaining
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)`.
In torchscript mode size as single int is not supported, use a tuple or
list of length 1: ``[size, ]``.
interpolation (int, optional): Desired interpolation enum defined by `filters`_.
Default is ``PIL.Image.BILINEAR``. If input is Tensor, only ``PIL.Image.NEAREST``, ``PIL.Image.BILINEAR``
and ``PIL.Image.BICUBIC`` are supported.
Returns:
PIL Image or Tensor: Resized image.
"""
if not isinstance(img, torch.Tensor):
return F_pil.resize(img, size=size, interpolation=interpolation)
return F_t.resize(img, size=size, interpolation=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)
def pad(img: Tensor, padding: List[int], fill: int = 0, padding_mode: str = "constant") -> Tensor:
r"""Pad the given image on all sides with the given "pad" value.
The image can be a PIL Image or a torch Tensor, in which case it is expected
to have [..., H, W] shape, where ... means an arbitrary number of leading dimensions
Args:
img (PIL Image or Tensor): 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 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.
In torchscript mode padding as single int is not supported, use a tuple or
list of length 1: ``[padding, ]``.
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. Only int value is supported for Tensors.
padding_mode: Type of padding. Should be: constant, edge, reflect or symmetric. Default is constant.
Mode symmetric is not yet supported for Tensor inputs.
- 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)
Loading ...