How to use recon about multi-domain-learning-fas HOT 4 CLOSED

@angelabr
I am sorry for the late response. We want to obtain the trace by subtracting a spoof image and its corresponding live image. However, we do not have the corresponding live image, so we use recon to micmic the corresponding live image. This imitation is the purpose to have recon.

from multi-domain-learning-fas.

Then how can we use the recon and d_total_loss for live and spoof classification?

from multi-domain-learning-fas.

I think I have found it. Can refer to source_SiW_Mv2/inference.py for final score and decision.

from multi-domain-learning-fas.

But may need some adjustment with the hyper parameters.

from multi-domain-learning-fas.