Pytorch Normalize() receiving torch.float32 tensor but recognising it as torch.int32

Question

I'm trying to normalize the NYU v2 Depth Dataset, and this is the transform I'm applying to each image coming through:

def standard_transform(normalise=False):
    composition = [
        transforms.Resize(standard_img_HW()),
        transforms.ToTensor(),
    ]
    if normalise:
        composition.append(transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)))
    return transforms.Compose(composition)

But it throws a runtime error of

TypeError(f"Input tensor should be a float tensor. Got {tensor.dtype}.")
TypeError: Input tensor should be a float tensor. Got torch.int32.

Now, I'd be happy to solve it if the tensors were indeed int dtypes, but the depth maps that are coming through are float32 tensors.

tensor([[[2.7520, 2.7520, 2.7522,  ..., 2.2429, 2.2428, 2.2428],
         [2.7519, 2.7520, 2.7521,  ..., 2.2429, 2.2428, 2.2427],
         [2.7518, 2.7518, 2.7520,  ..., 2.2428, 2.2427, 2.2427],
         ...,
         [2.1980, 2.1980, 2.1979,  ..., 2.0813, 2.0810, 2.0809],
         [2.1979, 2.1979, 2.1977,  ..., 2.0816, 2.0813, 2.0812],
         [2.1979, 2.1978, 2.1977,  ..., 2.0817, 2.0814, 2.0813]]])
torch.Size([1, 480, 640])
torch.float32

How should I go about solving this?

I've gone in circles making sure that the tensors are indeed tensors and not images, via ToTensor(), and also double checking that the tensors that I wish to normalise are indeed float tensors.