# Use YuNet with CUDA

**URL:** <https://forum.opencv.org/t/use-yunet-with-cuda/17109>\
**Category:** Python\
**Tags:** dnn, cuda, videoio\
**Created:** [April 2, 2024, 9:19am UTC](https://forum.opencv.org/t/use-yunet-with-cuda/17109 "2024-04-02T09:19:23Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![AKSHAT\_DOGRA](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/akshat_dogra/32/8254_2.png) [@AKSHAT\_DOGRA](https://forum.opencv.org/u/AKSHAT_DOGRA)\
**Post date:** [April 2, 2024, 9:19am UTC](https://forum.opencv.org/t/use-yunet-with-cuda/17109/1 "2024-04-02T09:19:23Z")

</div>

Hi, I have a large stack of videos(~95gb). Each video is around 20 minutes long in which there are faces in every frame. The aspect ratio is consistent in each video. I was trying to get faces from YuNet but it is terribly slow for this large corpus of data. Can anyone tell me how can I increase the detection speed? I looked at the opencv cuda documentation but couldn’t find any cuda support for YuNet. Should I just make it parallel using python’s multiprocessing library?

---

<div class="post-metadata">

**Author:** ![amandeep\_jamwal](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/amandeep_jamwal/32/9913_2.png) [@amandeep\_jamwal](https://forum.opencv.org/u/amandeep_jamwal)\
**Post date:** [June 11, 2024, 5:38am UTC](https://forum.opencv.org/t/use-yunet-with-cuda/17109/2 "2024-06-11T05:38:20Z")

</div>

Hey @AKSHAT_DOGRA did you find any solution for that? I am stuck on same problem.
