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


I re-trained the SSD network for people detection, and when I did an evaluation with 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


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?


I use jetson inference for training


Please see my follow-up from

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