forward_model is created by deep copying incoming model
However, it's not deployed in any gpu devices.
It's time-consuming to calculate mean and variance by forwarding batch of images using cpu.
I think it's better to assign default device and deploy the copied one on it.
forward_model is created by deep copying incoming model However, it's not deployed in any gpu devices. It's time-consuming to calculate mean and variance by forwarding batch of images using cpu. I think it's better to assign default device and deploy the copied one on it.