# PyTorch model sensitivity analysis

**URL:** <https://discuss.pytorch.org/t/pytorch-model-sensitivity-analysis/159835>\
**Category:** autograd\
**Created:** [August 23, 2022, 8:49am UTC](https://discuss.pytorch.org/t/pytorch-model-sensitivity-analysis/159835 "2022-08-23T08:49:17Z")\
**Posts on this page:** 1\
**Showing post:** 7

<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:** [August 27, 2022, 4:34am UTC](https://discuss.pytorch.org/t/pytorch-model-sensitivity-analysis/159835/7 "2022-08-27T04:34:03Z")

</div>

Would [this approach](https://discuss.pytorch.org/t/derivative-of-model-outputs-w-r-t-input-features/95814/2) of looping through the inputs to calculate the gradients (or using `jacobian`) work for your use case?

---

_[View the full topic](https://discuss.pytorch.org/t/pytorch-model-sensitivity-analysis/159835)._