from typing import Any, Dict, Optional
from torch import Tensor
from kornia.augmentation._2d.intensity.base import IntensityAugmentationBase2D
from kornia.enhance import equalize
[docs]class RandomEqualize(IntensityAugmentationBase2D):
r"""Equalize given tensor image or a batch of tensor images randomly.
.. image:: _static/img/RandomEqualize.png
Args:
p: Probability to equalize an image.
same_on_batch: apply the same transformation across the batch.
keepdim: whether to keep the output shape the same as input (True) or broadcast it
to the batch form (False).
Shape:
- Input: :math:`(C, H, W)` or :math:`(B, C, H, W)`, Optional: :math:`(B, 3, 3)`
- Output: :math:`(B, C, H, W)`
.. note::
This function internally uses :func:`kornia.enhance.equalize`.
Examples:
>>> rng = torch.manual_seed(0)
>>> input = torch.rand(1, 1, 5, 5)
>>> equalize = RandomEqualize(p=1.)
>>> equalize(input)
tensor([[[[0.4963, 0.7682, 0.0885, 0.1320, 0.3074],
[0.6341, 0.4901, 0.8964, 0.4556, 0.6323],
[0.3489, 0.4017, 0.0223, 0.1689, 0.2939],
[0.5185, 0.6977, 0.8000, 0.1610, 0.2823],
[0.6816, 0.9152, 0.3971, 0.8742, 0.4194]]]])
To apply the exact augmenation again, you may take the advantage of the previous parameter state:
>>> input = torch.rand(1, 3, 32, 32)
>>> aug = RandomEqualize(p=1.)
>>> (aug(input) == aug(input, params=aug._params)).all()
tensor(True)
"""
def __init__(self, same_on_batch: bool = False, p: float = 0.5, keepdim: bool = False) -> None:
super().__init__(p=p, same_on_batch=same_on_batch, keepdim=keepdim)
def apply_transform(
self, input: Tensor, params: Dict[str, Tensor], flags: Dict[str, Any], transform: Optional[Tensor] = None
) -> Tensor:
return equalize(input)