# Compute total loss error

**URL:** <https://community.deeplearning.ai/t/compute-total-loss-error/425234>\
**Category:** Improving Deep Neural Networks: Hyperparameter tun\
**Tags:** coursera-platform\
**Created:** [August 22, 2023, 6:14pm UTC](https://community.deeplearning.ai/t/compute-total-loss-error/425234 "2023-08-22T18:14:54Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![paulinpaloalto](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/paulinpaloalto/32/187_2.png) [@paulinpaloalto](https://community.deeplearning.ai/u/paulinpaloalto)\
**Post date:** [March 10, 2025, 7:20pm UTC](https://community.deeplearning.ai/t/compute-total-loss-error/425234/6 "2025-03-10T19:20:58Z")

</div>

The inputs to the TF cost function need to be in “samples first” orientation. If the question is why it needs to be this way, please see [this thread.](https://community.deeplearning.ai/t/course-2-week-3-compute-total-loss-logits-labels/293215/4)

---

_[View the full topic](https://community.deeplearning.ai/t/compute-total-loss-error/425234)._