You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, in line 78~80 of VAE.py, when calculating the KL divergence of VampPrior p(z) and posterior q(z|x), we put z_q into N(z_p_mean, z_p_logvar) and N(z_q_mean, z_q_logvar) then calculate the difference of log outputs of two Gaussian function.
Hi, in line 78~80 of VAE.py, when calculating the KL divergence of VampPrior p(z) and posterior q(z|x), we put
z_q
intoN(z_p_mean, z_p_logvar)
andN(z_q_mean, z_q_logvar)
then calculate the difference of log outputs of two Gaussian function.vae_vampprior/models/VAE.py
Line 78 in bb6ff3e
vae_vampprior/models/VAE.py
Line 79 in bb6ff3e
vae_vampprior/models/VAE.py
Line 80 in bb6ff3e
Since we have already get mean and variance of prior and posterior, can we directly calculate KL divergence of two Gaussian distribution? i.e.
This is because in line 226,
z_q
is just drawn fromN(z_q_mean, z_q_logvar)
:vae_vampprior/models/VAE.py
Line 226 in bb6ff3e
So can we skip this step? Thanks!
The text was updated successfully, but these errors were encountered: