- class torchvision.transforms.ConvertImageDtype(dtype: dtype)¶
Convert a tensor image to the given
dtypeand scale the values accordingly.
This function does not support PIL Image.
dtype (torch.dpython:type) – Desired data type of the output
When converting from a smaller to a larger integer
dtypethe maximum values are not mapped exactly. If converted back and forth, this mismatch has no effect.
RuntimeError – When trying to cast
torch.int64as well as for trying to cast
torch.int64. These conversions might lead to overflow errors since the floating point
dtypecannot store consecutive integers over the whole range of the integer
Define the computation performed at every call.
Should be overridden by all subclasses.
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.