Re-training DetectNet with a COCO dataset

How can I re-train the ssd-mobilenet model with a COCO dataset as opposed to using data from openimages? are openimages and COCO datasets in different file structure/annotation formats?

Have you tried this: jetson-inference/detectnet-training.md at master · dusty-nv/jetson-inference · GitHub

Yes but I am not sure if I can use DIGITS on the nano. Would I have to train the model on stronger hardware?

You can try. If it run out of memory, you can try to reduce the batch size.

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.