# Vector output summing to one, best loss function?

**URL:** <https://discuss.pytorch.org/t/vector-output-summing-to-one-best-loss-function/132584>\
**Category:** Uncategorized\
**Created:** [September 22, 2021, 7:12pm UTC](https://discuss.pytorch.org/t/vector-output-summing-to-one-best-loss-function/132584 "2021-09-22T19:12:13Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [September 22, 2021, 7:38pm UTC](https://discuss.pytorch.org/t/vector-output-summing-to-one-best-loss-function/132584/2 "2021-09-22T19:38:43Z")

</div>

@KFrank shared an implementation for “soft-labels” [here](https://discuss.pytorch.org/t/soft-cross-entropy-loss-tf-has-it-does-pytorch-have-it/69501/2).

---

_[View the full topic](https://discuss.pytorch.org/t/vector-output-summing-to-one-best-loss-function/132584)._