https://stackoverflow.com/questions/55266154/pytorch-preferred-way-to-copy-a-tensor
Use .clone().detach() (or preferrably .detach().clone())
If you first detach the tensor and then clone it, the computation path is not copied, the other way around it is copied and then abandoned. Thus,
.detach().clone()is very slightly more efficient.-- pytorch forums
as it's slightly fast and explicit in what it does.
