def kl(self, other):
a0 = self.logits - U.max(self.logits, axis=-1, keepdims=True)
a1 = other.logits - U.max(other.logits, axis=-1, keepdims=True)
ea0 = tf.exp(a0)
ea1 = tf.exp(a1)
z0 = U.sum(ea0, axis=-1, keepdims=True)
z1 = U.sum(ea1, axis=-1, keepdims=True)
p0 = ea0 / z0
return U.sum(p0 * (a0 - tf.log(z0) - a1 + tf.log(z1)), axis=-1)
def entropy(self):
a0 = self.logits - U.max(self.logits, axis=-1, keepdims=True)
ea0 = tf.exp(a0)
z0 = U.sum(ea0, axis=-1, keepdims=True)
p0 = ea0 / z0
return U.sum(p0 * (tf.log(z0) - a0), axis=-1)