Hi guys,

I meet a problem that, how to get the index of a element in a Tensor whose value is True?

Such as, a Tensor like:

False False Fasle

Flase True False

False False False

Then I can get the index of (1,1).

So how can I implement this operation?

Your answer and idea will be appreciated!

1 Like

`nonzero()`

would return you the indices of all non-zero entries (in that case `True`

):

```
x = torch.bernoulli(torch.ones(3, 3) * 0.5).bool()
print(x)
> tensor([[ True, True, False],
[False, False, True],
[ True, False, False]])
print(x.nonzero())
> tensor([[0, 0],
[0, 1],
[1, 2],
[2, 0]])
```

2 Likes

Thanks sincerely for your answer and guide!