ABSTRACT
In fact, a torchtensor is like an R array, in that it can be of arbitrary dimensionality. But unlike array, it is designed for fast and scalable execution of mathematical calculations, and you can move it to the GPU. To do anything useful with torch, you need to know about tensors. However, that procedure can get unwieldy when we have to pass in lots of different values. Luckily, there is an alternative approach that applies whenever values should be identical throughout or follow an apparent pattern. Once converted to factors, these are just as distant, semantically, as are “san francisco” and any other location. Again, whether this is of relevance depends on the specifics of the data, as well as your goal.
