I am looking to add class to segnet fcn-18-deep-scene. We want to detect solar panels while outside and need to add a class for this. How can this network be extended? Can Pytorch be used for this? If so, how?
It doesn’t seems to be TRT optimization related issue. Could you please elaborate more about the error you are getting while running TensorRT?
Yes, I may have tagged it incorrectly. I want to add a new class to segnet to classify a new object and I am trying to get information on how to do that using Pytorch.
This doesn’t look like TensorRT related issue. We recommend you to please post your concern on related platform.