# torchvision.transforms¶

Transforms are common image transformations. They can be chained together using Compose. Most transform classes have a function equivalent: functional transforms give fine-grained control over the transformations. This is useful if you have to build a more complex transformation pipeline (e.g. in the case of segmentation tasks).

Most transformations accept both PIL images and tensor images, although some transformations are PIL-only and some are tensor-only. The Conversion Transforms may be used to convert to and from PIL images.

The transformations that accept tensor images also accept batches of tensor images. A Tensor Image is a tensor with (C, H, W) shape, where C is a number of channels, H and W are image height and width. A batch of Tensor Images is a tensor of (B, C, H, W) shape, where B is a number of images in the batch.

The expected range of the values of a tensor image is implicitely defined by the tensor dtype. Tensor images with a float dtype are expected to have values in [0, 1). Tensor images with an integer dtype are expected to have values in [0, MAX_DTYPE] where MAX_DTYPE is the largest value that can be represented in that dtype.

Randomized transformations will apply the same transformation to all the images of a given batch, but they will produce different transformations across calls. For reproducible transformations across calls, you may use functional transforms.

The following examples illustate the use of the available transforms:

Warning

Since v0.8.0 all random transformations are using torch default random generator to sample random parameters. It is a backward compatibility breaking change and user should set the random state as following:

# Previous versions
# import random
# random.seed(12)

# Now
import torch
torch.manual_seed(17)


Please, keep in mind that the same seed for torch random generator and Python random generator will not produce the same results.

## Scriptable transforms¶

In order to script the transformations, please use torch.nn.Sequential instead of Compose.

transforms = torch.nn.Sequential(
transforms.CenterCrop(10),
transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
)
scripted_transforms = torch.jit.script(transforms)


Make sure to use only scriptable transformations, i.e. that work with torch.Tensor and does not require lambda functions or PIL.Image.

For any custom transformations to be used with torch.jit.script, they should be derived from torch.nn.Module.

## Compositions of transforms¶

class torchvision.transforms.Compose(transforms)[source]

Composes several transforms together. This transform does not support torchscript. Please, see the note below.

Parameters

transforms (list of Transform objects) – list of transforms to compose.

Example

>>> transforms.Compose([
>>>     transforms.CenterCrop(10),
>>>     transforms.ToTensor(),
>>> ])


Note

In order to script the transformations, please use torch.nn.Sequential as below.

>>> transforms = torch.nn.Sequential(
>>>     transforms.CenterCrop(10),
>>>     transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
>>> )
>>> scripted_transforms = torch.jit.script(transforms)


Make sure to use only scriptable transformations, i.e. that work with torch.Tensor, does not require lambda functions or PIL.Image.

## Transforms on PIL Image and torch.*Tensor¶

class torchvision.transforms.CenterCrop(size)[source]

Crops the given image at the center. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions. If image size is smaller than output size along any edge, image is padded with 0 and then center cropped.

Parameters

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. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

Examples using CenterCrop:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be cropped.

Returns

Cropped image.

Return type

PIL Image or Tensor

class torchvision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0)[source]

Randomly change the brightness, contrast, saturation and hue of an image. If the image is torch Tensor, it is expected to have […, 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, mode “1”, “L”, “I”, “F” and modes with transparency (alpha channel) are not supported.

Parameters
• brightness (float or tuple of python:float (min, max)) – How much to jitter brightness. brightness_factor is chosen uniformly from [max(0, 1 - brightness), 1 + brightness] or the given [min, max]. Should be non negative numbers.

• contrast (float or tuple of python:float (min, max)) – How much to jitter contrast. contrast_factor is chosen uniformly from [max(0, 1 - contrast), 1 + contrast] or the given [min, max]. Should be non negative numbers.

• saturation (float or tuple of python:float (min, max)) – How much to jitter saturation. saturation_factor is chosen uniformly from [max(0, 1 - saturation), 1 + saturation] or the given [min, max]. Should be non negative numbers.

• hue (float or tuple of python:float (min, max)) – How much to jitter hue. hue_factor is chosen uniformly from [-hue, hue] or the given [min, max]. Should have 0<= hue <= 0.5 or -0.5 <= min <= max <= 0.5.

Examples using ColorJitter:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Input image.

Returns

Color jittered image.

Return type

PIL Image or Tensor

static get_params(brightness: Optional[List[float]], contrast: Optional[List[float]], saturation: Optional[List[float]], hue: Optional[List[float]]) → Tuple[torch.Tensor, Optional[float], Optional[float], Optional[float], Optional[float]][source]

Get the parameters for the randomized transform to be applied on image.

Parameters
• brightness (tuple of python:float (min, max), optional) – The range from which the brightness_factor is chosen uniformly. Pass None to turn off the transformation.

• contrast (tuple of python:float (min, max), optional) – The range from which the contrast_factor is chosen uniformly. Pass None to turn off the transformation.

• saturation (tuple of python:float (min, max), optional) – The range from which the saturation_factor is chosen uniformly. Pass None to turn off the transformation.

• hue (tuple of python:float (min, max), optional) – The range from which the hue_factor is chosen uniformly. Pass None to turn off the transformation.

Returns

The parameters used to apply the randomized transform along with their random order.

Return type

tuple

class torchvision.transforms.FiveCrop(size)[source]

Crop the given image into four corners and the central crop. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Note

This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your Dataset returns. See below for an example of how to deal with this.

Parameters

size (sequence or int) – Desired output size of the crop. If size is an int instead of sequence like (h, w), a square crop of size (size, size) is made. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

Example

>>> transform = Compose([
>>>    FiveCrop(size), # this is a list of PIL Images
>>>    Lambda(lambda crops: torch.stack([ToTensor()(crop) for crop in crops])) # returns a 4D tensor
>>> ])
>>> #In your test loop you can do the following:
>>> input, target = batch # input is a 5d tensor, target is 2d
>>> bs, ncrops, c, h, w = input.size()
>>> result = model(input.view(-1, c, h, w)) # fuse batch size and ncrops
>>> result_avg = result.view(bs, ncrops, -1).mean(1) # avg over crops


Examples using FiveCrop:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be cropped.

Returns

tuple of 5 images. Image can be PIL Image or Tensor

class torchvision.transforms.Grayscale(num_output_channels=1)[source]

Convert image to grayscale. If the image is torch Tensor, it is expected to have […, 3, H, W] shape, where … means an arbitrary number of leading dimensions

Parameters

num_output_channels (int) – (1 or 3) number of channels desired for output image

Returns

Grayscale version of the input.

• If num_output_channels == 1 : returned image is single channel

• If num_output_channels == 3 : returned image is 3 channel with r == g == b

Return type

PIL Image

Examples using Grayscale:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be converted to grayscale.

Returns

Grayscaled image.

Return type

PIL Image or Tensor

class torchvision.transforms.Pad(padding, fill=0, padding_mode='constant')[source]

Pad the given image on all sides with the given “pad” value. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means at most 2 leading dimensions for mode reflect and symmetric, at most 3 leading dimensions for mode edge, and an arbitrary number of leading dimensions for mode constant

Parameters
• padding (int or sequence) –

Padding on each border. If a single int is provided this is used to pad all borders. If sequence of length 2 is provided this is the padding on left/right and top/bottom respectively. If a sequence of length 4 is provided this is the padding for the left, top, right and bottom borders respectively.

Note

In torchscript mode padding as single int is not supported, use a sequence of length 1: [padding, ].

• fill (number 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 number is supported for torch Tensor. Only int or str or tuple value is supported for PIL Image.

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 at the edge of the image. If input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2

• reflect: pads with reflection of image without repeating the last value on the edge. For example, 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. For example, 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]

Examples using Pad:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be padded.

Returns

Return type

PIL Image or Tensor

class torchvision.transforms.RandomAffine(degrees, translate=None, scale=None, shear=None, interpolation=<InterpolationMode.NEAREST: 'nearest'>, fill=0, fillcolor=None, resample=None)[source]

Random affine transformation of the image keeping center invariant. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• degrees (sequence or number) – Range of degrees to select from. If degrees is a number instead of sequence like (min, max), the range of degrees will be (-degrees, +degrees). Set to 0 to deactivate rotations.

• translate (tuple, optional) – tuple of maximum absolute fraction for horizontal and vertical translations. For example translate=(a, b), then horizontal shift is randomly sampled in the range -img_width * a < dx < img_width * a and vertical shift is randomly sampled in the range -img_height * b < dy < img_height * b. Will not translate by default.

• scale (tuple, optional) – scaling factor interval, e.g (a, b), then scale is randomly sampled from the range a <= scale <= b. Will keep original scale by default.

• shear (sequence or number, optional) – Range of degrees to select from. If shear is a number, a shear parallel to the x axis in the range (-shear, +shear) will be applied. Else if shear is a sequence of 2 values a shear parallel to the x axis in the range (shear[0], shear[1]) will be applied. Else if shear is a sequence of 4 values, a x-axis shear in (shear[0], shear[1]) and y-axis shear in (shear[2], shear[3]) will be applied. Will not apply shear by default.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• fill (sequence or number) – Pixel fill value for the area outside the transformed image. Default is 0. If given a number, the value is used for all bands respectively.

• fillcolor (sequence or number, optional) – deprecated argument and will be removed since v0.10.0. Please use the fill parameter instead.

• resample (int, optional) – deprecated argument and will be removed since v0.10.0. Please use the interpolation parameter instead.

Examples using RandomAffine:

forward(img)[source]

img (PIL Image or Tensor): Image to be transformed.

Returns

Affine transformed image.

Return type

PIL Image or Tensor

static get_params(degrees: List[float], translate: Optional[List[float]], scale_ranges: Optional[List[float]], shears: Optional[List[float]], img_size: List[int]) → Tuple[float, Tuple[int, int], float, Tuple[float, float]][source]

Get parameters for affine transformation

Returns

params to be passed to the affine transformation

class torchvision.transforms.RandomApply(transforms, p=0.5)[source]

Apply randomly a list of transformations with a given probability.

Note

In order to script the transformation, please use torch.nn.ModuleList as input instead of list/tuple of transforms as shown below:

>>> transforms = transforms.RandomApply(torch.nn.ModuleList([
>>>     transforms.ColorJitter(),
>>> ]), p=0.3)
>>> scripted_transforms = torch.jit.script(transforms)


Make sure to use only scriptable transformations, i.e. that work with torch.Tensor, does not require lambda functions or PIL.Image.

Parameters

Examples using RandomApply:

class torchvision.transforms.RandomCrop(size, padding=None, pad_if_needed=False, fill=0, padding_mode='constant')[source]

Crop the given image at a random location. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions, but if non-constant padding is used, the input is expected to have at most 2 leading dimensions

Parameters
• 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. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

• padding (int or sequence, optional) –

Optional padding on each border of the image. Default is None. If a single int is provided this is used to pad all borders. If sequence of length 2 is provided this is the padding on left/right and top/bottom respectively. If a sequence of length 4 is provided this is the padding for the left, top, right and bottom borders respectively.

Note

In torchscript mode padding as single int is not supported, use a sequence of length 1: [padding, ].

• pad_if_needed (boolean) – It will pad the image if smaller than the desired size to avoid raising an exception. Since cropping is done after padding, the padding seems to be done at a random offset.

• fill (number 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 number is supported for torch Tensor. Only int or str or tuple value is supported for PIL Image.

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 at the edge of the image. If input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2

• reflect: pads with reflection of image without repeating the last value on the edge. For example, 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. For example, 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]

Examples using RandomCrop:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be cropped.

Returns

Cropped image.

Return type

PIL Image or Tensor

static get_params(img: torch.Tensor, output_size: Tuple[int, int]) → Tuple[int, int, int, int][source]

Get parameters for crop for a random crop.

Parameters
• img (PIL Image or Tensor) – Image to be cropped.

• output_size (tuple) – Expected output size of the crop.

Returns

params (i, j, h, w) to be passed to crop for random crop.

Return type

tuple

class torchvision.transforms.RandomGrayscale(p=0.1)[source]

Randomly convert image to grayscale with a probability of p (default 0.1). If the image is torch Tensor, it is expected to have […, 3, H, W] shape, where … means an arbitrary number of leading dimensions

Parameters

p (float) – probability that image should be converted to grayscale.

Returns

Grayscale version of the input image with probability p and unchanged with probability (1-p). - If input image is 1 channel: grayscale version is 1 channel - If input image is 3 channel: grayscale version is 3 channel with r == g == b

Return type

PIL Image or Tensor

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be converted to grayscale.

Returns

Randomly grayscaled image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomHorizontalFlip(p=0.5)[source]

Horizontally flip the given image randomly with a given probability. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Parameters

p (float) – probability of the image being flipped. Default value is 0.5

Examples using RandomHorizontalFlip:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be flipped.

Returns

Randomly flipped image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomPerspective(distortion_scale=0.5, p=0.5, interpolation=<InterpolationMode.BILINEAR: 'bilinear'>, fill=0)[source]

Performs a random perspective transformation of the given image with a given probability. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• distortion_scale (float) – argument to control the degree of distortion and ranges from 0 to 1. Default is 0.5.

• p (float) – probability of the image being transformed. Default is 0.5.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• fill (sequence or number) – Pixel fill value for the area outside the transformed image. Default is 0. If given a number, the value is used for all bands respectively.

Examples using RandomPerspective:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be Perspectively transformed.

Returns

Randomly transformed image.

Return type

PIL Image or Tensor

static get_params(width: int, height: int, distortion_scale: float) → Tuple[List[List[int]], List[List[int]]][source]

Get parameters for perspective for a random perspective transform.

Parameters
• width (int) – width of the image.

• height (int) – height of the image.

• distortion_scale (float) – argument to control the degree of distortion and ranges from 0 to 1.

Returns

List containing [top-left, top-right, bottom-right, bottom-left] of the original image, List containing [top-left, top-right, bottom-right, bottom-left] of the transformed image.

class torchvision.transforms.RandomResizedCrop(size, scale=(0.08, 1.0), ratio=(0.75, 1.3333333333333333), interpolation=<InterpolationMode.BILINEAR: 'bilinear'>)[source]

Crop a random portion of image and resize it to a given size.

If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

A crop of the original image is made: the crop has a random area (H * W) and a random aspect ratio. This crop is finally resized to the given size. This is popularly used to train the Inception networks.

Parameters
• size (int or sequence) –

expected output size of the crop, for each edge. If size is an int instead of sequence like (h, w), a square output size (size, size) is made. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

Note

In torchscript mode size as single int is not supported, use a sequence of length 1: [size, ].

• scale (tuple of python:float) – Specifies the lower and upper bounds for the random area of the crop, before resizing. The scale is defined with respect to the area of the original image.

• ratio (tuple of python:float) – lower and upper bounds for the random aspect ratio of the crop, before resizing.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR and InterpolationMode.BICUBIC are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

Examples using RandomResizedCrop:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be cropped and resized.

Returns

Randomly cropped and resized image.

Return type

PIL Image or Tensor

static get_params(img: torch.Tensor, scale: List[float], ratio: List[float]) → Tuple[int, int, int, int][source]

Get parameters for crop for a random sized crop.

Parameters
• img (PIL Image or Tensor) – Input image.

• scale (list) – range of scale of the origin size cropped

• ratio (list) – range of aspect ratio of the origin aspect ratio cropped

Returns

params (i, j, h, w) to be passed to crop for a random sized crop.

Return type

tuple

class torchvision.transforms.RandomRotation(degrees, interpolation=<InterpolationMode.NEAREST: 'nearest'>, expand=False, center=None, fill=0, resample=None)[source]

Rotate the image by angle. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• degrees (sequence or number) – Range of degrees to select from. If degrees is a number instead of sequence like (min, max), the range of degrees will be (-degrees, +degrees).

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• expand (bool, optional) – Optional expansion flag. If true, expands the output 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 (sequence, optional) – Optional center of rotation, (x, y). Origin is the upper left corner. Default is the center of the image.

• fill (sequence or number) – Pixel fill value for the area outside the rotated image. Default is 0. If given a number, the value is used for all bands respectively.

• resample (int, optional) – deprecated argument and will be removed since v0.10.0. Please use the interpolation parameter instead.

Examples using RandomRotation:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be rotated.

Returns

Rotated image.

Return type

PIL Image or Tensor

static get_params(degrees: List[float]) → float[source]

Get parameters for rotate for a random rotation.

Returns

angle parameter to be passed to rotate for random rotation.

Return type

float

class torchvision.transforms.RandomSizedCrop(*args, **kwargs)[source]

Note: This transform is deprecated in favor of RandomResizedCrop.

class torchvision.transforms.RandomVerticalFlip(p=0.5)[source]

Vertically flip the given image randomly with a given probability. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Parameters

p (float) – probability of the image being flipped. Default value is 0.5

Examples using RandomVerticalFlip:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be flipped.

Returns

Randomly flipped image.

Return type

PIL Image or Tensor

class torchvision.transforms.Resize(size, interpolation=<InterpolationMode.BILINEAR: 'bilinear'>, max_size=None, antialias=None)[source]

Resize the input image to the given size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Warning

The output image might be different depending on its type: when downsampling, the interpolation of PIL images and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences in the performance of a network. Therefore, it is preferable to train and serve a model with the same input types.

Parameters
• size (sequence or int) –

Desired output size. If size is a sequence like (h, w), output size will be matched to this. If size is an int, smaller edge of the image will be matched to this number. i.e, if height > width, then image will be rescaled to (size * height / width, size).

Note

In torchscript mode size as single int is not supported, use a sequence of length 1: [size, ].

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR and InterpolationMode.BICUBIC are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• max_size (int, optional) – The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than max_size after being resized according to size, then the image is resized again so that the longer edge is equal to max_size. As a result, size might be overruled, i.e the smaller edge may be shorter than size. This is only supported if size is an int (or a sequence of length 1 in torchscript mode).

• antialias (bool, optional) –

antialias flag. If img is PIL Image, the flag is ignored and anti-alias is always used. If img is Tensor, the flag is False by default and can be set True for InterpolationMode.BILINEAR only mode.

Warning

There is no autodiff support for antialias=True option with input img as Tensor.

Examples using Resize:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be scaled.

Returns

Rescaled image.

Return type

PIL Image or Tensor

class torchvision.transforms.Scale(*args, **kwargs)[source]

Note: This transform is deprecated in favor of Resize.

class torchvision.transforms.TenCrop(size, vertical_flip=False)[source]

Crop the given image into four corners and the central crop plus the flipped version of these (horizontal flipping is used by default). If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Note

This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your Dataset returns. See below for an example of how to deal with this.

Parameters
• 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. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

• vertical_flip (bool) – Use vertical flipping instead of horizontal

Example

>>> transform = Compose([
>>>    TenCrop(size), # this is a list of PIL Images
>>>    Lambda(lambda crops: torch.stack([ToTensor()(crop) for crop in crops])) # returns a 4D tensor
>>> ])
>>> #In your test loop you can do the following:
>>> input, target = batch # input is a 5d tensor, target is 2d
>>> bs, ncrops, c, h, w = input.size()
>>> result = model(input.view(-1, c, h, w)) # fuse batch size and ncrops
>>> result_avg = result.view(bs, ncrops, -1).mean(1) # avg over crops

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be cropped.

Returns

tuple of 10 images. Image can be PIL Image or Tensor

class torchvision.transforms.GaussianBlur(kernel_size, sigma=(0.1, 2.0))[source]

Blurs image with randomly chosen Gaussian blur. If the image is torch Tensor, it is expected to have […, C, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• kernel_size (int or sequence) – Size of the Gaussian kernel.

• sigma (float or tuple of python:float (min, max)) – Standard deviation to be used for creating kernel to perform blurring. If float, sigma is fixed. If it is tuple of float (min, max), sigma is chosen uniformly at random to lie in the given range.

Returns

Gaussian blurred version of the input image.

Return type

PIL Image or Tensor

Examples using GaussianBlur:

forward(img: torch.Tensor) → torch.Tensor[source]
Parameters

img (PIL Image or Tensor) – image to be blurred.

Returns

Gaussian blurred image

Return type

PIL Image or Tensor

static get_params(sigma_min: float, sigma_max: float) → float[source]

Choose sigma for random gaussian blurring.

Parameters
• sigma_min (float) – Minimum standard deviation that can be chosen for blurring kernel.

• sigma_max (float) – Maximum standard deviation that can be chosen for blurring kernel.

Returns

Standard deviation to be passed to calculate kernel for gaussian blurring.

Return type

float

class torchvision.transforms.RandomInvert(p=0.5)[source]

Inverts the colors of the given image randomly with a given probability. If img is a Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters

p (float) – probability of the image being color inverted. Default value is 0.5

Examples using RandomInvert:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be inverted.

Returns

Randomly color inverted image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomPosterize(bits, p=0.5)[source]

Posterize the image randomly with a given probability by reducing the number of bits for each color channel. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters
• bits (int) – number of bits to keep for each channel (0-8)

• p (float) – probability of the image being color inverted. Default value is 0.5

Examples using RandomPosterize:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be posterized.

Returns

Randomly posterized image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomSolarize(threshold, p=0.5)[source]

Solarize the image randomly with a given probability by inverting all pixel values above a threshold. If img is a Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters
• threshold (float) – all pixels equal or above this value are inverted.

• p (float) – probability of the image being color inverted. Default value is 0.5

Examples using RandomSolarize:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be solarized.

Returns

Randomly solarized image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomAdjustSharpness(sharpness_factor, p=0.5)[source]

Adjust the sharpness of the image randomly with a given probability. If the image is torch Tensor, it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• sharpness_factor (float) – How much to adjust the sharpness. Can be any non negative number. 0 gives a blurred image, 1 gives the original image while 2 increases the sharpness by a factor of 2.

• p (float) – probability of the image being color inverted. Default value is 0.5

Examples using RandomAdjustSharpness:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be sharpened.

Returns

Randomly sharpened image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomAutocontrast(p=0.5)[source]

Autocontrast the pixels of the given image randomly with a given probability. If the image is torch Tensor, it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters

p (float) – probability of the image being autocontrasted. Default value is 0.5

Examples using RandomAutocontrast:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be autocontrasted.

Returns

Randomly autocontrasted image.

Return type

PIL Image or Tensor

class torchvision.transforms.RandomEqualize(p=0.5)[source]

Equalize the histogram of the given image randomly with a given probability. If the image is torch Tensor, it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “P”, “L” or “RGB”.

Parameters

p (float) – probability of the image being equalized. Default value is 0.5

Examples using RandomEqualize:

forward(img)[source]
Parameters

img (PIL Image or Tensor) – Image to be equalized.

Returns

Randomly equalized image.

Return type

PIL Image or Tensor

## Transforms on PIL Image only¶

class torchvision.transforms.RandomChoice(transforms)[source]

Apply single transformation randomly picked from a list. This transform does not support torchscript.

class torchvision.transforms.RandomOrder(transforms)[source]

Apply a list of transformations in a random order. This transform does not support torchscript.

## Transforms on torch.*Tensor only¶

class torchvision.transforms.LinearTransformation(transformation_matrix, mean_vector)[source]

Transform a tensor image with a square transformation matrix and a mean_vector computed offline. This transform does not support PIL Image. Given transformation_matrix and mean_vector, will flatten the torch.*Tensor and subtract mean_vector from it which is then followed by computing the dot product with the transformation matrix and then reshaping the tensor to its original shape.

Applications:

whitening transformation: Suppose X is a column vector zero-centered data. Then compute the data covariance matrix [D x D] with torch.mm(X.t(), X), perform SVD on this matrix and pass it as transformation_matrix.

Parameters
• transformation_matrix (Tensor) – tensor [D x D], D = C x H x W

• mean_vector (Tensor) – tensor [D], D = C x H x W

forward(tensor: torch.Tensor) → torch.Tensor[source]
Parameters

tensor (Tensor) – Tensor image to be whitened.

Returns

Transformed image.

Return type

Tensor

class torchvision.transforms.Normalize(mean, std, inplace=False)[source]

Normalize a tensor image with mean and standard deviation. This transform does not support PIL Image. Given mean: (mean[1],...,mean[n]) and std: (std[1],..,std[n]) for n channels, this transform will normalize each channel of the input torch.*Tensor i.e., output[channel] = (input[channel] - mean[channel]) / std[channel]

Note

This transform acts out of place, i.e., it does not mutate the input tensor.

Parameters
• 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 in-place.

Examples using Normalize:

forward(tensor: torch.Tensor) → torch.Tensor[source]
Parameters

tensor (Tensor) – Tensor image to be normalized.

Returns

Normalized Tensor image.

Return type

Tensor

class torchvision.transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3), value=0, inplace=False)[source]

Randomly selects a rectangle region in an torch Tensor image and erases its pixels. This transform does not support PIL Image. ‘Random Erasing Data Augmentation’ by Zhong et al. See https://arxiv.org/abs/1708.04896

Parameters
• p – probability that the random erasing operation will be performed.

• scale – range of proportion of erased area against input image.

• ratio – range of aspect ratio of erased area.

• value – erasing value. Default is 0. If a single int, it is used to erase all pixels. If a tuple of length 3, it is used to erase R, G, B channels respectively. If a str of ‘random’, erasing each pixel with random values.

• inplace – boolean to make this transform inplace. Default set to False.

Returns

Erased Image.

Example

>>> transform = transforms.Compose([
>>>   transforms.RandomHorizontalFlip(),
>>>   transforms.ToTensor(),
>>>   transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
>>>   transforms.RandomErasing(),
>>> ])

forward(img)[source]
Parameters

img (Tensor) – Tensor image to be erased.

Returns

Erased Tensor image.

Return type

img (Tensor)

static get_params(img: torch.Tensor, scale: Tuple[float, float], ratio: Tuple[float, float], value: Optional[List[float]] = None) → Tuple[int, int, int, int, torch.Tensor][source]

Get parameters for erase for a random erasing.

Parameters
• img (Tensor) – Tensor image to be erased.

• scale (sequence) – range of proportion of erased area against input image.

• ratio (sequence) – range of aspect ratio of erased area.

• value (list, optional) – erasing value. If None, it is interpreted as “random” (erasing each pixel with random values). If len(value) is 1, it is interpreted as a number, i.e. value[0].

Returns

params (i, j, h, w, v) to be passed to erase for random erasing.

Return type

tuple

class torchvision.transforms.ConvertImageDtype(dtype: torch.dtype)[source]

Convert a tensor image to the given dtype and scale the values accordingly This function does not support PIL Image.

Parameters

dtype (torch.dpython:type) – Desired data type of the output

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 torch.float32 to torch.int32 or torch.int64 as well as for trying to cast torch.float64 to 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.

Examples using ConvertImageDtype:

## Conversion Transforms¶

class torchvision.transforms.ToPILImage(mode=None)[source]

Convert a tensor or an ndarray to PIL Image. This transform does not support torchscript.

Converts a torch.*Tensor of shape C x H x W or a numpy ndarray of shape H x W x C to a PIL Image while preserving the value range.

Parameters

mode (PIL.Image mode) – color space and pixel depth of input data (optional). If mode is None (default) there are some assumptions made about the input data: - If the input has 4 channels, the mode is assumed to be RGBA. - If the input has 3 channels, the mode is assumed to be RGB. - If the input has 2 channels, the mode is assumed to be LA. - If the input has 1 channel, the mode is determined by the data type (i.e int, float, short).

Examples using ToPILImage:

class torchvision.transforms.ToTensor[source]

Convert a PIL Image or numpy.ndarray to tensor. This transform does not support torchscript.

Converts a PIL Image or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0] if the PIL Image belongs to one of the modes (L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK, 1) or if the numpy.ndarray has dtype = np.uint8

In the other cases, tensors are returned without scaling.

Note

Because the input image is scaled to [0.0, 1.0], this transformation should not be used when transforming target image masks. See the references for implementing the transforms for image masks.

## Generic Transforms¶

class torchvision.transforms.Lambda(lambd)[source]

Apply a user-defined lambda as a transform. This transform does not support torchscript.

Parameters

lambd (function) – Lambda/function to be used for transform.

## AutoAugment Transforms¶

AutoAugment is a common Data Augmentation technique that can improve the accuracy of Image Classification models. Though the data augmentation policies are directly linked to their trained dataset, empirical studies show that ImageNet policies provide significant improvements when applied to other datasets. In TorchVision we implemented 3 policies learned on the following datasets: ImageNet, CIFAR10 and SVHN. The new transform can be used standalone or mixed-and-matched with existing transforms:

class torchvision.transforms.AutoAugmentPolicy[source]

AutoAugment policies learned on different datasets. Available policies are IMAGENET, CIFAR10 and SVHN.

Examples using AutoAugmentPolicy:

class torchvision.transforms.AutoAugment(policy: torchvision.transforms.autoaugment.AutoAugmentPolicy = <AutoAugmentPolicy.IMAGENET: 'imagenet'>, interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.NEAREST: 'nearest'>, fill: Optional[List[float]] = None)[source]

AutoAugment data augmentation method based on “AutoAugment: Learning Augmentation Strategies from Data”. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have […, 1 or 3, H, W] shape, where … means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Parameters
• policy (AutoAugmentPolicy) – Desired policy enum defined by torchvision.transforms.autoaugment.AutoAugmentPolicy. Default is AutoAugmentPolicy.IMAGENET.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported.

• fill (sequence or number, optional) – Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively.

Examples using AutoAugment:

forward(img: torch.Tensor)[source]

img (PIL Image or Tensor): Image to be transformed.

Returns

AutoAugmented image.

Return type

PIL Image or Tensor

static get_params(transform_num: int) → Tuple[int, torch.Tensor, torch.Tensor][source]

Get parameters for autoaugment transformation

Returns

params required by the autoaugment transformation

## Functional Transforms¶

Functional transforms give you fine-grained control of the transformation pipeline. As opposed to the transformations above, functional transforms don’t contain a random number generator for their parameters. That means you have to specify/generate all parameters, but the functional transform will give you reproducible results across calls.

Example: you can apply a functional transform with the same parameters to multiple images like this:

import torchvision.transforms.functional as TF
import random

def my_segmentation_transforms(image, segmentation):
if random.random() > 0.5:
angle = random.randint(-30, 30)
image = TF.rotate(image, angle)
segmentation = TF.rotate(segmentation, angle)
# more transforms ...
return image, segmentation


Example: you can use a functional transform to build transform classes with custom behavior:

import torchvision.transforms.functional as TF
import random

class MyRotationTransform:
"""Rotate by one of the given angles."""

def __init__(self, angles):
self.angles = angles

def __call__(self, x):
angle = random.choice(self.angles)
return TF.rotate(x, angle)

rotation_transform = MyRotationTransform(angles=[-30, -15, 0, 15, 30])

class torchvision.transforms.functional.InterpolationMode[source]

Interpolation modes Available interpolation methods are nearest, bilinear, bicubic, box, hamming, and lanczos.

torchvision.transforms.functional.adjust_brightness(img: torch.Tensor, brightness_factor: float) → torch.Tensor[source]

Parameters
• img (PIL Image or Tensor) – Image to be adjusted. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions.

• 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

Return type

PIL Image or Tensor

torchvision.transforms.functional.adjust_contrast(img: torch.Tensor, contrast_factor: float) → torch.Tensor[source]

Parameters
• img (PIL Image or Tensor) – Image to be adjusted. If img is torch Tensor, it is expected to be in […, 3, H, W] format, where … means it can have an arbitrary number of leading dimensions.

• 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

Return type

PIL Image or Tensor

torchvision.transforms.functional.adjust_gamma(img: torch.Tensor, gamma: float, gain: float = 1) → torch.Tensor[source]

Perform gamma correction on an image.

Also known as Power Law Transform. Intensities in RGB mode are adjusted based on the following equation:

$I_{\text{out}} = 255 \times \text{gain} \times \left(\frac{I_{\text{in}}}{255}\right)^{\gamma}$

See Gamma Correction for more details.

Parameters
• img (PIL Image or Tensor) – PIL Image to be adjusted. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, modes with transparency (alpha channel) are not supported.

• gamma (float) – Non negative real number, same as $$\gamma$$ 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.

Returns

Return type

PIL Image or Tensor

torchvision.transforms.functional.adjust_hue(img: torch.Tensor, hue_factor: float) → torch.Tensor[source]

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.

Parameters
• img (PIL Image or Tensor) – Image to be adjusted. If img is torch Tensor, it is expected to be in […, 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image mode “1”, “L”, “I”, “F” and modes with transparency (alpha channel) are not supported.

• 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

Return type

PIL Image or Tensor

torchvision.transforms.functional.adjust_saturation(img: torch.Tensor, saturation_factor: float) → torch.Tensor[source]

Adjust color saturation of an image.

Parameters
• img (PIL Image or Tensor) – Image to be adjusted. If img is torch Tensor, it is expected to be in […, 3, H, W] format, where … means it can have an arbitrary number of leading dimensions.

• 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

Return type

PIL Image or Tensor

torchvision.transforms.functional.adjust_sharpness(img: torch.Tensor, sharpness_factor: float) → torch.Tensor[source]

Adjust the sharpness of an image.

Parameters
• img (PIL Image or Tensor) – Image to be adjusted. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions.

• sharpness_factor (float) – How much to adjust the sharpness. Can be any non negative number. 0 gives a blurred image, 1 gives the original image while 2 increases the sharpness by a factor of 2.

Returns

Return type

PIL Image or Tensor

Examples using adjust_sharpness:

torchvision.transforms.functional.affine(img: torch.Tensor, angle: float, translate: List[int], scale: float, shear: List[float], interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.NEAREST: 'nearest'>, fill: Optional[List[float]] = None, resample: Optional[int] = None, fillcolor: Optional[List[float]] = None) → torch.Tensor[source]

Apply affine transformation on the image keeping image center invariant. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• img (PIL Image or Tensor) – image to transform.

• angle (number) – rotation angle in degrees between -180 and 180, clockwise direction.

• translate (sequence of python:integers) – horizontal and vertical translations (post-rotation translation)

• scale (float) – overall scale

• shear (float or sequence) – shear angle value in degrees between -180 to 180, clockwise direction. If a sequence 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.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• fill (sequence or number, optional) –

Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively.

Note

In torchscript mode single int/float value is not supported, please use a sequence of length 1: [value, ].

• fillcolor (sequence, int, float) – deprecated argument and will be removed since v0.10.0. Please use the fill parameter instead.

• resample (int, optional) – deprecated argument and will be removed since v0.10.0. Please use the interpolation parameter instead.

Returns

Transformed image.

Return type

PIL Image or Tensor

Examples using affine:

torchvision.transforms.functional.autocontrast(img: torch.Tensor) → torch.Tensor[source]

Maximize contrast of an image by remapping its pixels per channel so that the lowest becomes black and the lightest becomes white.

Parameters

img (PIL Image or Tensor) – Image on which autocontrast is applied. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Returns

An image that was autocontrasted.

Return type

PIL Image or Tensor

Examples using autocontrast:

torchvision.transforms.functional.center_crop(img: torch.Tensor, output_size: List[int]) → torch.Tensor[source]

Crops the given image at the center. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions. If image size is smaller than output size along any edge, image is padded with 0 and then center cropped.

Parameters
• img (PIL Image or Tensor) – Image to be cropped.

• output_size (sequence or int) – (height, width) of the crop box. If int or sequence with single int, it is used for both directions.

Returns

Cropped image.

Return type

PIL Image or Tensor

Examples using center_crop:

torchvision.transforms.functional.convert_image_dtype(image: torch.Tensor, dtype: torch.dtype = torch.float32) → torch.Tensor[source]

Convert a tensor image to the given dtype and scale the values accordingly This function does not support PIL Image.

Parameters
• image (torch.Tensor) – Image to be converted

• dtype (torch.dpython:type) – Desired data type of the output

Returns

Converted image

Return type

Tensor

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 torch.float32 to torch.int32 or torch.int64 as well as for trying to cast torch.float64 to 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.

Examples using convert_image_dtype:

torchvision.transforms.functional.crop(img: torch.Tensor, top: int, left: int, height: int, width: int) → torch.Tensor[source]

Crop the given image at specified location and output size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions. If image size is smaller than output size along any edge, image is padded with 0 and then cropped.

Parameters
• img (PIL Image or Tensor) – 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

Cropped image.

Return type

PIL Image or Tensor

Examples using crop:

torchvision.transforms.functional.equalize(img: torch.Tensor) → torch.Tensor[source]

Equalize the histogram of an image by applying a non-linear mapping to the input in order to create a uniform distribution of grayscale values in the output.

Parameters

img (PIL Image or Tensor) – Image on which equalize is applied. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. The tensor dtype must be torch.uint8 and values are expected to be in [0, 255]. If img is PIL Image, it is expected to be in mode “P”, “L” or “RGB”.

Returns

An image that was equalized.

Return type

PIL Image or Tensor

Examples using equalize:

torchvision.transforms.functional.erase(img: torch.Tensor, i: int, j: int, h: int, w: int, v: torch.Tensor, inplace: bool = False) → torch.Tensor[source]

Erase the input Tensor Image with given value. This transform does not support PIL Image.

Parameters
• 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

Erased image.

Return type

Tensor Image

torchvision.transforms.functional.five_crop(img: torch.Tensor, size: List[int]) → Tuple[torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor, torch.Tensor][source]

Crop the given image into four corners and the central crop. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Note

This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your Dataset returns.

Parameters
• img (PIL Image or Tensor) – Image to be cropped.

• 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. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

Returns

tuple (tl, tr, bl, br, center) Corresponding top left, top right, bottom left, bottom right and center crop.

Return type

tuple

Examples using five_crop:

torchvision.transforms.functional.gaussian_blur(img: torch.Tensor, kernel_size: List[int], sigma: Optional[List[float]] = None) → torch.Tensor[source]

Performs Gaussian blurring on the image by given kernel. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• img (PIL Image or Tensor) – Image to be blurred

• kernel_size (sequence of python:ints or int) –

Gaussian kernel size. Can be a sequence of integers like (kx, ky) or a single integer for square kernels.

Note

In torchscript mode kernel_size as single int is not supported, use a sequence of length 1: [ksize, ].

• sigma (sequence of python:floats or float, optional) –

Gaussian kernel standard deviation. Can be a sequence of floats like (sigma_x, sigma_y) or a single float to define the same sigma in both X/Y directions. If None, then it is computed using kernel_size as sigma = 0.3 * ((kernel_size - 1) * 0.5 - 1) + 0.8. Default, None.

Note

In torchscript mode sigma as single float is not supported, use a sequence of length 1: [sigma, ].

Returns

Gaussian Blurred version of the image.

Return type

PIL Image or Tensor

Examples using gaussian_blur:

torchvision.transforms.functional.hflip(img: torch.Tensor) → torch.Tensor[source]

Horizontally flip the given image.

Parameters

img (PIL Image or Tensor) – Image to be flipped. If img is a Tensor, it is expected to be in […, H, W] format, where … means it can have an arbitrary number of leading dimensions.

Returns

Horizontally flipped image.

Return type

PIL Image or Tensor

Examples using hflip:

torchvision.transforms.functional.invert(img: torch.Tensor) → torch.Tensor[source]

Invert the colors of an RGB/grayscale image.

Parameters

img (PIL Image or Tensor) – Image to have its colors inverted. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

Returns

Color inverted image.

Return type

PIL Image or Tensor

Examples using invert:

torchvision.transforms.functional.normalize(tensor: torch.Tensor, mean: List[float], std: List[float], inplace: bool = False) → torch.Tensor[source]

Normalize a float tensor image with mean and standard deviation. This transform does not support PIL Image.

Note

This transform acts out of place by default, i.e., it does not mutates the input tensor.

See Normalize for more details.

Parameters
• tensor (Tensor) – Float 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

Normalized Tensor image.

Return type

Tensor

Examples using normalize:

torchvision.transforms.functional.pad(img: torch.Tensor, padding: List[int], fill: int = 0, padding_mode: str = 'constant') → torch.Tensor[source]

Pad the given image on all sides with the given “pad” value. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means at most 2 leading dimensions for mode reflect and symmetric, at most 3 leading dimensions for mode edge, and an arbitrary number of leading dimensions for mode constant

Parameters
• img (PIL Image or Tensor) – Image to be padded.

• padding (int or sequence) –

Padding on each border. If a single int is provided this is used to pad all borders. If sequence of length 2 is provided this is the padding on left/right and top/bottom respectively. If a sequence of length 4 is provided this is the padding for the left, top, right and bottom borders respectively.

Note

In torchscript mode padding as single int is not supported, use a sequence of length 1: [padding, ].

• fill (number 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 number is supported for torch Tensor. Only int or str or tuple value is supported for PIL Image.

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 at the edge of the image. If input a 5D torch Tensor, the last 3 dimensions will be padded instead of the last 2

• reflect: pads with reflection of image without repeating the last value on the edge. For example, 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. For example, 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

Return type

PIL Image or Tensor

Examples using pad:

torchvision.transforms.functional.perspective(img: torch.Tensor, startpoints: List[List[int]], endpoints: List[List[int]], interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.BILINEAR: 'bilinear'>, fill: Optional[List[float]] = None) → torch.Tensor[source]

Perform perspective transform of the given image. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• img (PIL Image or Tensor) – Image to be transformed.

• startpoints (list of list of python:ints) – List containing four lists of two integers corresponding to four corners [top-left, top-right, bottom-right, bottom-left] of the original image.

• endpoints (list of list of python:ints) – List containing four lists of two integers corresponding to four corners [top-left, top-right, bottom-right, bottom-left] of the transformed image.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• fill (sequence or number, optional) –

Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively.

Note

In torchscript mode single int/float value is not supported, please use a sequence of length 1: [value, ].

Returns

transformed Image.

Return type

PIL Image or Tensor

Examples using perspective:

torchvision.transforms.functional.pil_to_tensor(pic)[source]

Convert a PIL Image to a tensor of the same type. This function does not support torchscript.

See PILToTensor for more details.

Parameters

pic (PIL Image) – Image to be converted to tensor.

Returns

Converted image.

Return type

Tensor

torchvision.transforms.functional.posterize(img: torch.Tensor, bits: int) → torch.Tensor[source]

Posterize an image by reducing the number of bits for each color channel.

Parameters
• img (PIL Image or Tensor) – Image to have its colors posterized. If img is torch Tensor, it should be of type torch.uint8 and it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

• bits (int) – The number of bits to keep for each channel (0-8).

Returns

Posterized image.

Return type

PIL Image or Tensor

Examples using posterize:

torchvision.transforms.functional.resize(img: torch.Tensor, size: List[int], interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.BILINEAR: 'bilinear'>, max_size: Optional[int] = None, antialias: Optional[bool] = None) → torch.Tensor[source]

Resize the input image to the given size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Warning

The output image might be different depending on its type: when downsampling, the interpolation of PIL images and tensors is slightly different, because PIL applies antialiasing. This may lead to significant differences in the performance of a network. Therefore, it is preferable to train and serve a model with the same input types.

Parameters
• 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 $$\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)$$.

Note

In torchscript mode size as single int is not supported, use a sequence of length 1: [size, ].

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR and InterpolationMode.BICUBIC are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• max_size (int, optional) – The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than max_size after being resized according to size, then the image is resized again so that the longer edge is equal to max_size. As a result, size might be overruled, i.e the smaller edge may be shorter than size. This is only supported if size is an int (or a sequence of length 1 in torchscript mode).

• antialias (bool, optional) –

antialias flag. If img is PIL Image, the flag is ignored and anti-alias is always used. If img is Tensor, the flag is False by default and can be set True for InterpolationMode.BILINEAR only mode.

Warning

There is no autodiff support for antialias=True option with input img as Tensor.

Returns

Resized image.

Return type

PIL Image or Tensor

Examples using resize:

torchvision.transforms.functional.resized_crop(img: torch.Tensor, top: int, left: int, height: int, width: int, size: List[int], interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.BILINEAR: 'bilinear'>) → torch.Tensor[source]

Crop the given image and resize it to desired size. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Notably used in RandomResizedCrop.

Parameters
• img (PIL Image or Tensor) – 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 (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.BILINEAR. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR and InterpolationMode.BICUBIC are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

Returns

Cropped image.

Return type

PIL Image or Tensor

Examples using resized_crop:

torchvision.transforms.functional.rgb_to_grayscale(img: torch.Tensor, num_output_channels: int = 1) → torch.Tensor[source]

Convert RGB image to grayscale version of image. If the image is torch Tensor, it is expected to have […, 3, H, W] shape, where … means an arbitrary number of leading dimensions

Note

Please, note that this method supports only RGB images as input. For inputs in other color spaces, please, consider using meth:~torchvision.transforms.functional.to_grayscale with PIL Image.

Parameters
• img (PIL Image or Tensor) – RGB Image to be converted to grayscale.

• num_output_channels (int) – number of channels of the output image. Value can be 1 or 3. Default, 1.

Returns

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

Return type

PIL Image or Tensor

torchvision.transforms.functional.rotate(img: torch.Tensor, angle: float, interpolation: torchvision.transforms.functional.InterpolationMode = <InterpolationMode.NEAREST: 'nearest'>, expand: bool = False, center: Optional[List[int]] = None, fill: Optional[List[float]] = None, resample: Optional[int] = None) → torch.Tensor[source]

Rotate the image by angle. If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions.

Parameters
• img (PIL Image or Tensor) – image to be rotated.

• angle (number) – rotation angle value in degrees, counter-clockwise.

• interpolation (InterpolationMode) – Desired interpolation enum defined by torchvision.transforms.InterpolationMode. Default is InterpolationMode.NEAREST. If input is Tensor, only InterpolationMode.NEAREST, InterpolationMode.BILINEAR are supported. For backward compatibility integer values (e.g. PIL.Image.NEAREST) are still acceptable.

• 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 (sequence, optional) – Optional center of rotation. Origin is the upper left corner. Default is the center of the image.

• fill (sequence or number, optional) –

Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively.

Note

In torchscript mode single int/float value is not supported, please use a sequence of length 1: [value, ].

Returns

Rotated image.

Return type

PIL Image or Tensor

Examples using rotate:

torchvision.transforms.functional.solarize(img: torch.Tensor, threshold: float) → torch.Tensor[source]

Solarize an RGB/grayscale image by inverting all pixel values above a threshold.

Parameters
• img (PIL Image or Tensor) – Image to have its colors inverted. If img is torch Tensor, it is expected to be in […, 1 or 3, H, W] format, where … means it can have an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode “L” or “RGB”.

• threshold (float) – All pixels equal or above this value are inverted.

Returns

Solarized image.

Return type

PIL Image or Tensor

Examples using solarize:

torchvision.transforms.functional.ten_crop(img: torch.Tensor, size: List[int], vertical_flip: bool = False) → List[torch.Tensor][source]

Generate ten cropped images from the given image. Crop the given image into four corners and the central crop plus the flipped version of these (horizontal flipping is used by default). If the image is torch Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions

Note

This transform returns a tuple of images and there may be a mismatch in the number of inputs and targets your Dataset returns.

Parameters
• img (PIL Image or Tensor) – Image to be cropped.

• 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. If provided a sequence of length 1, it will be interpreted as (size[0], size[0]).

• vertical_flip (bool) – Use vertical flipping instead of horizontal

Returns

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.

Return type

tuple

torchvision.transforms.functional.to_grayscale(img, num_output_channels=1)[source]

Convert PIL image of any mode (RGB, HSV, LAB, etc) to grayscale version of image. This transform does not support torch Tensor.

Parameters
• img (PIL Image) – PIL Image to be converted to grayscale.

• num_output_channels (int) – number of channels of the output image. Value can be 1 or 3. Default is 1.

Returns

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

Return type

PIL Image

Examples using to_grayscale:

torchvision.transforms.functional.to_pil_image(pic, mode=None)[source]

Convert a tensor or an ndarray to PIL Image. This function does not support torchscript.

See ToPILImage for more details.

Parameters
• 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).

Returns

Image converted to PIL Image.

Return type

PIL Image

Examples using to_pil_image:

torchvision.transforms.functional.to_tensor(pic)[source]

Convert a PIL Image or numpy.ndarray to tensor. This function does not support torchscript.

See ToTensor for more details.

Parameters

pic (PIL Image or numpy.ndarray) – Image to be converted to tensor.

Returns

Converted image.

Return type

Tensor

torchvision.transforms.functional.vflip(img: torch.Tensor) → torch.Tensor[source]

Vertically flip the given image.

Parameters

img (PIL Image or Tensor) – Image to be flipped. If img is a Tensor, it is expected to be in […, H, W] format, where … means it can have an arbitrary number of leading dimensions.

Returns

Vertically flipped image.

Return type

PIL Image or Tensor

Examples using vflip: