Why does PyTorch gather function require index argument to be of type LongTensor?

Question

I'm writing some code in PyTorch and I came across the gather function. Checking the documentation I saw that the index argument takes in a LongTensor, why is that? Why does it need to take in a LongTensor instead of another type such as IntTensor? What are the benefits?

Long is a datatype that can hold decimal values but not int. — bigbounty
– bigbounty, Commented May 28, 2019 at 4:59

Shai · Accepted Answer · 2019-05-28 05:12:50Z

1

By default all indices in pytorch are represented as long tensors - allowing for indexing very large tensors beyond just 4GB elements (maximal value of "regular" int).

answered May 28, 2019 at 5:12

Shai

115k39 gold badges259 silver badges398 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Why does PyTorch gather function require index argument to be of type LongTensor?

1 Answer 1

Comments

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Related