I’m sorry if I was not clear enough but I meant I don’t want to use DetectNet model. The problem is that only DetectNet implementation is available for detection model.
I made my own model written in keras with tensorflow backend, made an uff file from this network and now I would like to create an engine from the uff file.
Sorry about the misunderstanding. I think you are looking for examples creating TRT engine from UFF using C++?
Please take a look at ~/samples/sampleUffMNIST/sampleUffMNIST.cpp (comes with your TRT installation).
For a more general sample of inference with TensorRT C++ API, see this (some parts are outdated, but still serves as good reference): http://github.com/dusty-nv/jetson-inference
Note sure if this is off-topic, but many of the answers to my questions are always based on the little Jetson toys, I bought a RTX 3080 TI specfically for learning and deploying AI tasks, so with this said, is it possible that I can follow the “Hello AI World guide” to deploy on a RTX 3080 TI?
“Hello AI World guide” seems to be targeting for Jetson toys.
BTW (If you ask why did I bought such beefy GPU, it’s because I also happen to play CoD).