def disc_mutual_info_loss(c_disc, aux_dist):
"""
Mutual Information lower bound loss for discrete distribution.
"""
reg_disc_dim = aux_dist.get_shape().as_list()[-1]
cross_ent = -K.mean(K.sum(K.log(aux_dist + EPSILON) * c_disc, axis=1))
ent = -K.mean(K.sum(K.log(1. / reg_disc_dim + EPSILON) * c_disc, axis=1))
return -(ent - cross_ent)
def poisson(y_true, y_pred): return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def kullback_leibler_divergence(y_true, y_pred): y_true = K.clip(y_true, K.epsilon(), 1) y_pred = K.clip(y_pred, K.epsilon(), 1) return K.sum(y_true * K.log(y_true / y_pred), axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred): first_log = K.log(K.clip(y_pred, K.epsilon(), None) + 1.) second_log = K.log(K.clip(y_true, K.epsilon(), None) + 1.) return K.mean(K.square(first_log - second_log), axis=-1)
def logcosh(y_true, y_pred):
def cosh(x):
return (K.exp(x) + K.exp(-x)) / 2
return K.mean(K.log(cosh(y_pred - y_true)), axis=-1)
def poisson(y_true, y_pred): return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def kullback_leibler_divergence(y_true, y_pred): y_true = K.clip(y_true, K.epsilon(), 1) y_pred = K.clip(y_pred, K.epsilon(), 1) return K.sum(y_true * K.log(y_true / y_pred), axis=-1)
def logcosh(y_true, y_pred):
def cosh(x):
return (K.exp(x) + K.exp(-x)) / 2
return K.mean(K.log(cosh(y_pred - y_true)), axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred): first_log = K.log(K.clip(y_pred, K.epsilon(), None) + 1.) second_log = K.log(K.clip(y_true, K.epsilon(), None) + 1.) return K.mean(K.square(first_log - second_log), axis=-1)
