Setting the value of `x <= 0` to `chain_depth` argument of `AugMix()` doesn't get error against the doc

[hyperkai]

🐛 Describe the bug

The doc of AugMix() says that chain_depth parameter is int as shown below:

Parameters:

• ...
• chain_depth (int) – The depth of augmentation chains. A negative value denotes stochastic

So, setting the value of 1 <= x to chain_depth argument gets the error properly as shown below:

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import AugMix

my_data = OxfordIIITPet(
    root="data",
    transform=AugMix(chain_depth=1.0)
    # transform=AugMix(chain_depth=2.0)
    # transform=AugMix(chain_depth=3.0)
)

my_data[0] # Error

TypeError: 'float' object cannot be interpreted as an integer

But setting the value of x <= 0 to chain_depth argument doesn't get error against the doc as shown below:

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import AugMix

my_data = OxfordIIITPet(
    root="data",
    transform=AugMix(chain_depth=0.0)
    # transform=AugMix(chain_depth=-1.0)
    # transform=AugMix(chain_depth=-2.0)
    # transform=AugMix(chain_depth=-3.0)
)

my_data[0]
# (<PIL.Image.Image image mode=RGB size=394x500>, 0)

Versions

import torchvision

torchvision.__version__ # '0.20.1'