Hi, thanks for your good work. I have two questions:
Is the tanh activation function of logvar required? Can you remove it or just replace it with any other activations？
During training, I encountered a problem: the logvar prediction network, whose last layer is 'tanh', always output the '-1', no matter what the input is. And the overall CLUB MI prediction network seems to lose effect (fail to be updated), giving negative MI estimation.
Hi, thanks for your good work. I have two questions:
Is the tanh activation function of logvar required? Can you remove it or just replace it with any other activations？
During training, I encountered a problem: the logvar prediction network, whose last layer is 'tanh', always output the '-1', no matter what the input is. And the overall CLUB MI prediction network seems to lose effect (fail to be updated), giving negative MI estimation.