knighthappy
Results
1
comments of
knighthappy
if ‘precision = K.exp(-log_var[0])’，then the network learning $\log{\sigma}^2$,'precision * (y_true - y_pred)**2. + log_var[0]' is $\frac{1}{\sigma ^ 2} L(w) + 2 * \log{\sigma}$; if ‘precision = K.exp(-log_var[0]) ** 2 /...