Hey Luxonis Team!
I am using a Luxonis Oak-D Pro and was wondering if it is possible to add a neural network to the pipeline of the camera but only run inference on the model on demand (e.g. when a certain condition is fulfilled). The problem is that my NN reduces the FPS quite a bit because it is so heavy, so this would be a potential workaround.
I'm looking forward to your reply!
All the best,
Magnus
