Is there a way to retrain ssd-mobilenet v2 with my own data?

I’m using a jetson tx2.

Hi gpqls7669, please see this post for some suggestions of tutorials for re-training SSD-Mobilenet object detection models: https://devtalk.nvidia.com/default/topic/1070225/jetson-nano/digits-or-somthing-else/post/5421938/#5421938

You may want to do the training on a PC or cloud instance, as the object detection models can consume a lot of resources to train.