Inverted probability while applying Gaussian #286
Description
Hi,
The probability of GaussBlur function seems to be inverted.
class GaussianBlur(v2.RandomApply):
"""
Apply Gaussian Blur to the PIL image.
"""
def __init__(self, *, p: float = 0.5, radius_min: float = 0.1, radius_max: float = 2.0):
# NOTE: torchvision is applying 1 - probability to return the original image
keep_p = 1 - p
transform = v2.GaussianBlur(kernel_size=9, sigma=(radius_min, radius_max))
super().__init__(transforms=[transform], p=keep_p)While
class RandomApply(Transform):
"""Apply randomly a list of transformations with a given probability.
Args:
transforms (sequence or torch.nn.Module): list of transformations
p (float): probability of applying the list of transforms
"""I just came across this on DINOv2 and it seems like you are using the same base.