Count Unique elements in pytorch Tensor

Question

Suppose I have the following tensor: y = torch.randint(0, 3, (10,)). How would you go about counting the 0's 1's and 2's in there?

The only way I can think of is by using collections.Counter(y) but was wondering if there was a more "pytorch" way of doing this. A use case for example would be when building the confusion matrix for predictions.

Ivan · Accepted Answer · 2021-08-27 05:52:37Z

13

You can use torch.unique with the return_counts option:

>>> x = torch.randint(0, 3, (10,))
tensor([1, 1, 0, 2, 1, 0, 1, 1, 2, 1])

>>> x.unique(return_counts=True)
(tensor([0, 1, 2]), tensor([2, 6, 2]))

answered Aug 27, 2021 at 5:52

Ivan

41.3k9 gold badges78 silver badges120 bronze badges

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

Collectives™ on Stack Overflow

Count Unique elements in pytorch Tensor

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related