Closed mrgloom closed 5 years ago
That's true; if you train a feed forward network to predict latents for a long time, it will slowly improve, but the job here is to serve as a good initial estimate, not a final prediction. (an example of this is in the banner at the top of this repo)
Is it true that model that predict W latent vector (i.e.
train_resnet.py
) can be only used as initial estimate of W latent vector in optimization process? i.e. it's not possible to directly use this model to predict W latent vector without optimization process(i.e. it looks like if it used like this it change person identity)?