Multiple Class Object Detection on custom dataset

Hi,

I have trained a custom dataset with 5 classes on the jetson nano using jetson-inference. After the training I have successfully been able to detect the items/objects using imagenet-camera but now i would like to do the same using detectnet-camera as i want to detect all the custom classes at once in real time. I tried running the detectnet-camera code but it does not detect the objects. I would appreciate any help regarding this issue…

regards,
Shirish

Hi Shirish, please see this post for tutorial suggestions on re-training multi-class object detection model:

https://devtalk.nvidia.com/default/topic/1070225/jetson-nano/digits-or-somthing-else/post/5421938/#5421938