tensorflow_addons/optimizers/adabelief.py [180:200]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        beta_1_t = self._get_hyper("beta_1", var_dtype)
        beta_2_t = self._get_hyper("beta_2", var_dtype)
        epsilon_t = tf.convert_to_tensor(self.epsilon, var_dtype)
        local_step = tf.cast(self.iterations + 1, var_dtype)
        beta_1_power = tf.pow(beta_1_t, local_step)
        beta_2_power = tf.pow(beta_2_t, local_step)

        if self._initial_total_steps > 0:
            total_steps = self._get_hyper("total_steps", var_dtype)
            warmup_steps = total_steps * self._get_hyper("warmup_proportion", var_dtype)
            min_lr = self._get_hyper("min_lr", var_dtype)
            decay_steps = tf.maximum(total_steps - warmup_steps, 1)
            decay_rate = (min_lr - lr_t) / decay_steps
            lr_t = tf.where(
                local_step <= warmup_steps,
                lr_t * (local_step / warmup_steps),
                lr_t + decay_rate * tf.minimum(local_step - warmup_steps, decay_steps),
            )

        sma_inf = 2.0 / (1.0 - beta_2_t) - 1.0
        sma_t = sma_inf - 2.0 * local_step * beta_2_power / (1.0 - beta_2_power)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_addons/optimizers/adabelief.py [246:266]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        beta_1_t = self._get_hyper("beta_1", var_dtype)
        beta_2_t = self._get_hyper("beta_2", var_dtype)
        epsilon_t = tf.convert_to_tensor(self.epsilon, var_dtype)
        local_step = tf.cast(self.iterations + 1, var_dtype)
        beta_1_power = tf.pow(beta_1_t, local_step)
        beta_2_power = tf.pow(beta_2_t, local_step)

        if self._initial_total_steps > 0:
            total_steps = self._get_hyper("total_steps", var_dtype)
            warmup_steps = total_steps * self._get_hyper("warmup_proportion", var_dtype)
            min_lr = self._get_hyper("min_lr", var_dtype)
            decay_steps = tf.maximum(total_steps - warmup_steps, 1)
            decay_rate = (min_lr - lr_t) / decay_steps
            lr_t = tf.where(
                local_step <= warmup_steps,
                lr_t * (local_step / warmup_steps),
                lr_t + decay_rate * tf.minimum(local_step - warmup_steps, decay_steps),
            )

        sma_inf = 2.0 / (1.0 - beta_2_t) - 1.0
        sma_t = sma_inf - 2.0 * local_step * beta_2_power / (1.0 - beta_2_power)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -