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
I guess it is the number of times of weight sampling every feedforward iteration. I'm not sure on this cuz the config file sets both train_ens and valid_ens to 1 by default, and the default value of num_ens in the definition of train_model function is also 1, but the paper says sample size is 10~25.
Hello, what is the meaning of num_ens in the train_model function in main_bayesian
The text was updated successfully, but these errors were encountered: