# Question regarding confidence

**URL:** <https://forums.developer.nvidia.com/t/question-regarding-confidence/167511>\
**Category:** DeepStream SDK\
**Created:** [February 3, 2021, 10:24am UTC](https://forums.developer.nvidia.com/t/question-regarding-confidence/167511 "2021-02-03T10:24:29Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![foreverneilyoung](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@foreverneilyoung](https://forums.developer.nvidia.com/u/foreverneilyoung)\
**Post date:** [February 7, 2021, 11:32am UTC](https://forums.developer.nvidia.com/t/question-regarding-confidence/167511/7 "2021-02-07T11:32:12Z")

</div>

I have tried to check this sample [deepstream\_python\_apps/apps/deepstream-imagedata-multistream at master · NVIDIA-AI-IOT/deepstream\_python\_apps · GitHub](https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/tree/master/apps/deepstream-imagedata-multistream). I got confidence values by specifying cluster-mode != 0 in my config. I understand, that a grouped detection indication cannot have a common confidence.

With cluster-mode=1 I’m getting a lot of detections, all drawn overlayed as red rectangles around me. cluster-mode=2 returns again to the well known single rectangle and there is a confidence != -0.1

What cluster mode would I have to chose in order to enable myself to walk over all detections and sort out everything below a given threshold, say 0.5 or 0.6?

---

_[View the full topic](https://forums.developer.nvidia.com/t/question-regarding-confidence/167511)._