I notice that in gaussian_network.py, you use min_log_var in GaussianNetwork class to ensure the variance of z distribution not too low. However, not all subclass use this variable(e.g. GaussianBidirectionalNetwork). I am wondering why we need this variable and how this variable effect training?
Thank you :)
I notice that in
gaussian_network.py, you usemin_log_varinGaussianNetworkclass to ensure the variance of z distribution not too low. However, not all subclass use this variable(e.g. GaussianBidirectionalNetwork). I am wondering why we need this variable and how this variable effect training?Thank you :)