3533912016c64f1f03516657c1d93f02a11e5c67,keras/optimizers.py,Adamax,get_updates,#Adamax#Any#Any#Any#,379

Before Change

    def get_updates(self, params, constraints, loss):
        grads = self.get_gradients(loss, params)
        self.updates = [(self.iterations, self.iterations + 1)]

        t = self.iterations + 1
        lr_t = self.lr / (1. - K.pow(self.beta_1, t))

After Change

    def get_updates(self, params, constraints, loss):
        grads = self.get_gradients(loss, params)
        self.updates = [K.update_add(self.iterations, 1)]

        t = self.iterations + 1
        lr_t = self.lr / (1. - K.pow(self.beta_1, t))

        // zero init of 1st moment
        ms = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
        // zero init of exponentially weighted infinity norm
        us = [K.variable(np.zeros(K.get_value(p).shape)) for p in params]
        self.weights = ms + us

        for p, g, m, u in zip(params, grads, ms, us):

            m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
            u_t = K.maximum(self.beta_2 * u, K.abs(g))
            p_t = p - lr_t * m_t / (u_t + self.epsilon)

            self.updates.append(K.update(m, m_t))
            self.updates.append(K.update(u, u_t))

            new_p = p_t
            // apply constraints
            if p in constraints:
                c = constraints[p]
                new_p = c(new_p)
            self.updates.append(K.update(p, new_p))
        return self.updates

    def get_config(self):

Instances