# Cross entropy with logit targets **URL:** \ **Category:** Uncategorized\ **Created:** [October 12, 2021, 10:25pm UTC](https://discuss.pytorch.org/t/cross-entropy-with-logit-targets/134068 "2021-10-12T22:25:08Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![KFrank](https://discuss.pytorch.org/letter_avatar_proxy/v4/letter/k/ecb155/32.png) [@KFrank](https://discuss.pytorch.org/u/KFrank)\ **Post date:** [October 13, 2021, 2:00am UTC](https://discuss.pytorch.org/t/cross-entropy-with-logit-targets/134068/2 "2021-10-13T02:00:32Z")
Hi Haziq! > [@Haziq](#): > > each ground truth has some uncertainty and is thus a vector of probability scores e.g. `[0.1, 0, 0.7, 0, 0.2, 0, 0]` instead of `[0,0,1,0,0,0,0]`. (As an aside, your title for this thread, “Cross entropy with logit targets” should probably be “Cross entropy with probability targets,” since you ask about “probability scores” and use probabilities in the example you give.) Your ground-truth `target` probabilities are what are sometimes called “soft labels.” Pytorch’s `CrossEntropyLoss` does not support this kind of `target`, but you can write a version that does. For details, please see this post: > [@Soft Cross Entropy Loss (TF has it does Pytorch have it)](https://discuss.pytorch.org/t/soft-cross-entropy-loss-tf-has-it-does-pytorch-have-it/69501/2): > > Hello Raaj! I do not believe that pytorch has a “soft” cross-entropy function built in. But you can implement it using pytorch tensor operations, so you should get the full benefit of autograd and gpu acceleration. See this (pytorch version 0.3.0) script: import torch torch.\_\_version\_\_ # define "soft" cross-entropy with pytorch tensor operations def softXEnt (input, target): logprobs = torch.nn.functional.log\_softmax (input, dim = 1) return -(target \* logprobs).sum() / input.shap… Best. K. Frank --- _[View the full topic](https://discuss.pytorch.org/t/cross-entropy-with-logit-targets/134068)._