Confusion about "y1 = tensor @ tensor.T" in PyTorch

Asked Jul 19 '21 at 17:39

Active Jul 19 '21 at 17:39

Viewed 72 times

Well, I am new to PyTorch and starting to introduce myself to it from the official website. In there, https://pytorch.org/tutorials/beginner/basics/tensorqs_tutorial.html

it says, for multiplication between two tensors:

y1 = tensor @ tensor.T

is used where after multiplying two tensors the value is stored in 'y1'. Can you please explain this line and why and how the '@' is used?

Thank You.

asked Jul 19 '21 at 17:39

nahidosen

1

This is a python operator that does matrix multiplication. See [PEP 465](https://www.python.org/dev/peps/pep-0465/) for more information. – jkr Jul 19 '21 at 17:44
^ Look for `__matmul__` – Ivan Jul 19 '21 at 19:34

0 Answers0