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:
Illustration of 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(),
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.
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:
Tensor transforms and JIT¶
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:
Illustration of transforms¶
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




    

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:
Illustration of transforms¶
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:
Illustration of transforms¶
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.
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.
padding_mode (str) – 
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]
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:
Illustration of transforms¶
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.
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
transforms (sequence or torch.nn.Module) – list of transformations
p (float) – probability
Examples using RandomApply:
Illustration of transforms¶
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.
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.
padding_mode (str) – 
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]
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
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:
Tensor transforms and JIT¶
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:
Illustration of transforms¶
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]).
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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.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:
Illustration of transforms¶
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).
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.
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
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
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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
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]
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:
Tensor transforms and JIT¶
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(),
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
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:
Tensor transforms and JIT¶
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:
Tensor transforms and JIT¶
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.
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.
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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])
torchvision.transforms.functional.adjust_brightness(img: torch.Tensor, brightness_factor: float) → torch.Tensor[source]¶
Adjust brightness 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.




    

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
Brightness adjusted image.
Return type
PIL Image or Tensor
torchvision.transforms.functional.adjust_contrast(img: torch.Tensor, contrast_factor: float) → torch.Tensor[source]¶
Adjust contrast 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.
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
Contrast adjusted image.
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
Gamma correction adjusted image.
Return type
PIL Image or Tensor
torchvision.transforms.functional.adjust_hue(img: torch.Tensor, hue_factor: float) → torch.Tensor[source]¶
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.
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
Hue adjusted image.
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
Saturation adjusted image.
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
Sharpness adjusted image.
Return type
PIL Image or Tensor
Examples using adjust_sharpness:
Illustration of transforms¶
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.
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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
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:
Visualization utilities¶
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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
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:
Illustration of transforms¶
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.
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.
In torchscript mode sigma as single float is
not supported, use a sequence of length 1: [sigma, ].
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:
Illustration of transforms¶
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:
Illustration of transforms¶
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.
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:
Visualization utilities¶
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.
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.
padding_mode (str) – 
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]
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.
In torchscript mode single int/float value is not supported, please use a sequence
of length 1: [value, ].
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:
Illustration of transforms¶
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
\(\left(\text{size} \times \frac{\text{height}}{\text{width}}, \text{size}\right)\).
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.
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:
Illustration of transforms¶
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
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.
In torchscript mode single int/float value is not supported, please use a sequence
of length 1: [value, ].
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:
Illustration of transforms¶
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
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:
Illustration of transforms¶
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).
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:
Illustration of transforms¶
Compositions of transforms
Transforms on PIL Image and torch.*Tensor
Transforms on PIL Image only
Transforms on torch.*Tensor only
Conversion Transforms
Generic Transforms
AutoAugment Transforms
Functional Transforms