Suppose I have a pre-trained classic CNN model (e.g., ResNet which is trained on a dataset) in MXNet. Now, I want to convert this model to C++ (fro some reasons like better performance). Could you help me please to do that?
This should help you out:
Loads the inception model and the predicts the contents in a main driver, uses OpenCV, but this morning I hacked around that and replaced it with another library.
What I am confused about is a GAN model rather than a predictor.
I was wanting to make this into a feedforward in C++ CPU only, so I can access large amounts of memory.