transform_random_perspective: Random perspective transformation of an image with a given...

transform_random_perspectiveR Documentation

Random perspective transformation of an image with a given probability

Description

Performs a random perspective transformation of the given image with a given probability

Usage

transform_random_perspective(
  img,
  distortion_scale = 0.5,
  p = 0.5,
  interpolation = 2,
  fill = 0
)

Arguments

img

A magick-image, array or torch_tensor.

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

(int, optional) Desired interpolation. An integer 0 = nearest, 2 = bilinear, and 3 = bicubic or a name from magick::filter_types().

fill

(int or str or tuple): Pixel fill value for constant fill. Default is 0. If a tuple of length 3, it is used to fill R, G, B channels respectively. This value is only used when the padding_mode is constant. Only int value is supported for Tensors.

See Also

Other transforms: transform_adjust_brightness(), transform_adjust_contrast(), transform_adjust_gamma(), transform_adjust_hue(), transform_adjust_saturation(), transform_affine(), transform_center_crop(), transform_color_jitter(), transform_convert_image_dtype(), transform_crop(), transform_five_crop(), transform_grayscale(), transform_hflip(), transform_linear_transformation(), transform_normalize(), transform_pad(), transform_perspective(), transform_random_affine(), transform_random_apply(), transform_random_choice(), transform_random_crop(), transform_random_erasing(), transform_random_grayscale(), transform_random_horizontal_flip(), transform_random_order(), transform_random_resized_crop(), transform_random_rotation(), transform_random_vertical_flip(), transform_resized_crop(), transform_resize(), transform_rgb_to_grayscale(), transform_rotate(), transform_ten_crop(), transform_to_tensor(), transform_vflip()


torchvision documentation built on April 14, 2023, 5:08 p.m.