When talking about VAE
(and viewing VAE
implementations), the Encoder outputs:
μ, log(variance)
when we train the model (the part of the decoder model)
, we convert the log(variance)
to Standard deviation:
std = exp(0.5 * logvar)
(I took the example from here: PyTorch-VAE/vanilla_vae.py at master · AntixK/PyTorch-VAE · GitHub)
If we need to convert the log(variance)
to Standard deviation,
why won’t we output the Standard deviation from the encoder instead of making calculation to convert it to Standard deviation ?