flowvision.transforms¶
Utils for Image Transforms¶

class
flowvision.transforms.
CenterCrop
(size)[source]¶ Crops the given image at the center. If the image is oneflow 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]).

class
flowvision.transforms.
Compose
(transforms)[source]¶ Composes several transforms together. Please, see the note below. :param transforms: list of transforms to compose. :type transforms: list of
Transform
objectsExample
>>> transforms.Compose([ >>> transforms.CenterCrop(10), >>> transforms.ToTensor(), >>> ])
Note
In order to script the transformations, please use
flow.nn.Sequential
as below. >>> transforms = flow.nn.Sequential( >>> transforms.CenterCrop(10), >>> transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)), >>> ) Make sure to use only scriptable transformations, i.e. that work withflow.Tensor
, does not require lambda functions orPIL.Image
.

class
flowvision.transforms.
ConvertImageDtype
(dtype: oneflow._oneflow_internal.dtype)[source]¶ Convert a tensor image to the given
dtype
and scale the values accordingly This function does not support PIL Image. Parameters
dtype (flow.dtype) – 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
flow.float32
toflow.int32
orflow.int64
as well as for trying to castflow.float64
toflow.int64
. These conversions might lead to overflow errors since the floating pointdtype
cannot store consecutive integers over the whole range of the integerdtype
.

class
flowvision.transforms.
FiveCrop
(size)[source]¶ Crop the given image into four corners and the central crop. If the image is flow 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: flow.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
flowvision.transforms.
GaussianBlur
(kernel_size, sigma=(0.1, 2.0))[source]¶ Blurs image with randomly chosen Gaussian blur. If the image is oneflow 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 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

forward
(img: oneflow.Tensor) → oneflow.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
flowvision.transforms.
Grayscale
(num_output_channels=1)[source]¶ Convert image to grayscale. If the image is oneflow 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  Ifnum_output_channels == 3
: returned image is 3 channel with r == g == b Return type
PIL Image

class
flowvision.transforms.
Lambda
(lambd)[source]¶ Apply a userdefined lambda as a transform.
 Parameters
lambd (function) – Lambda/function to be used for transform.

class
flowvision.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])
forn
channels, this transform will normalize each channel of the inputflow.*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 inplace.

class
flowvision.transforms.
PILToTensor
[source]¶ Convert a
PIL Image
to a tensor of the same typeConverts a PIL Image (H x W x C) to a Tensor of shape (C x H x W).

class
flowvision.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 oneflow 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.
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 oneflow 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 oneflow 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
flowvision.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
flow.nn.ModuleList
as input instead of list/tuple of transforms as shown below:>>> transforms = transforms.RandomApply(flow.nn.ModuleList([ >>> transforms.ColorJitter(), >>> ]), p=0.3)
Make sure to use only scriptable transformations, i.e. that work with
flow.Tensor
, does not require lambda functions orPIL.Image
. Parameters
transforms (sequence or Module) – list of transformations
p (float) – probability

class
flowvision.transforms.
RandomChoice
(transforms)[source]¶ Apply single transformation randomly picked from a list.

class
flowvision.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 oneflow Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions, but if nonconstant 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.
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 flow 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 flow 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]

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: oneflow.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
flowvision.transforms.
RandomGrayscale
(p=0.1)[source]¶ Randomly convert image to grayscale with a probability of p (default 0.1). If the image is flow 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 (1p).  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
flowvision.transforms.
RandomHorizontalFlip
(p=0.5)[source]¶ Horizontally flip the given image randomly with a given probability. If the image is flow 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

class
flowvision.transforms.
RandomOrder
(transforms)[source]¶ Apply a list of transformations in a random order.

class
flowvision.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 flow 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]).scale (tuple of 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 float) – lower and upper bounds for the random aspect ratio of the crop, before resizing.
interpolation (InterpolationMode) – Desired interpolation enum defined by
flowvision.transforms.InterpolationMode
. Default isInterpolationMode.BILINEAR
. If input is Tensor, onlyInterpolationMode.NEAREST
,InterpolationMode.BILINEAR
andInterpolationMode.BICUBIC
are supported. For backward compatibility integer values (e.g.PIL.Image.NEAREST
) are still acceptable.

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: oneflow.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
flowvision.transforms.
RandomSizedCrop
(*args, **kwargs)[source]¶ Note: This transform is deprecated in favor of RandomResizedCrop.

class
flowvision.transforms.
RandomTransforms
(transforms)[source]¶ Base class for a list of transformations with randomness
 Parameters
transforms (sequence) – list of transformations

class
flowvision.transforms.
RandomVerticalFlip
(p=0.5)[source]¶ Vertically flip the given image randomly with a given probability. If the image is flow 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

class
flowvision.transforms.
Resize
(size, interpolation=<InterpolationMode.BILINEAR: 'bilinear'>)[source]¶ Resize the input image to the given size. If the image is oneflow Tensor, it is expected to have […, H, W] shape, where … means an arbitrary number of leading dimensions
 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).
interpolation (InterpolationMode) – Desired interpolation enum defined by
flowvision.transforms.InterpolationMode
. Default isInterpolationMode.BILINEAR
. If input is Tensor, onlyInterpolationMode.NEAREST
,InterpolationMode.BILINEAR
andInterpolationMode.BICUBIC
are supported. For backward compatibility integer values (e.g.PIL.Image.NEAREST
) are still acceptable.

class
flowvision.transforms.
Scale
(*args, **kwargs)[source]¶ Note: This transform is deprecated in favor of Resize.

class
flowvision.transforms.
Solarization
(p=0.1)[source]¶ Apply Solarization to the input PIL Image.
 Parameters
p (float) – probability that image should be applied with solarization operation.

class
flowvision.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 flow 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: flow.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
flowvision.transforms.
ToPILImage
(mode=None)[source]¶ Convert a tensor or an ndarray to PIL Image.
Converts a flow.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
isNone
(default) there are some assumptions made about the input data:  If the input has 4 channels, themode
is assumed to beRGBA
.  If the input has 3 channels, themode
is assumed to beRGB
.  If the input has 2 channels, themode
is assumed to beLA
.  If the input has 1 channel, themode
is determined by the data type (i.eint
,float
,short
).

class
flowvision.transforms.
ToTensor
[source]¶ Convert a
PIL Image
ornumpy.ndarray
to tensor.Converts a PIL Image or numpy.ndarray (H x W x C) in the range [0, 255] to a flow.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.