# Bad accurancy , re-trained the SSD network for people detection #1172

**URL:** <https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356>\
**Category:** Jetson Nano\
**Tags:** ai-training\
**Created:** [August 2, 2021, 8:12am UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356 "2021-08-02T08:12:49Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![sylia](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@sylia](https://forums.developer.nvidia.com/u/sylia)\
**Post date:** [August 2, 2021, 8:12am UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356/1 "2021-08-02T08:12:49Z")

</div>

Hello,

I re-trained the SSD network for people detection, and when I did an evaluation with eval-ssd.py I got only 41% accuracy,  
batch size = 4,  
epoch = 108,  
Is there a way to have better accuracy in detection of people?

the retraining was performed on a PC ( GPU NVIDIA GeForce RTX 2060 )  
Thank you

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [August 2, 2021, 9:11am UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356/3 "2021-08-02T09:11:29Z")

</div>

Hi,

This is the Jetson Nano board.  
Do you use jetson-inference for re-training?  
If not, would you mind filing a topic on a desktop-related board to get the support?

Thanks.

---

<div class="post-metadata">

**Author:** ![sylia](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@sylia](https://forums.developer.nvidia.com/u/sylia)\
**Post date:** [August 2, 2021, 9:54am UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356/4 "2021-08-02T09:54:03Z")

</div>

I use jetson inference for training

> <https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-ssd.md>

Thanks

---

<div class="post-metadata">

**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\
**Post date:** [August 2, 2021, 2:28pm UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356/5 "2021-08-02T14:28:40Z")

</div>

Please see my follow-up from [https://github.com/dusty-nv/jetson-inference/issues/1172](https://github.com/dusty-nv/jetson-inference/issues/1172)

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [October 10, 2021, 3:41am UTC](https://forums.developer.nvidia.com/t/bad-accurancy-re-trained-the-ssd-network-for-people-detection-1172/185356/7 "2021-10-10T03:41:52Z")

</div>

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.