word_rnn.py 文件源码

def get_optimizer(self, learning_rate = 0.001):
        with tf.name_scope('loss'):
            input_shape = tf.shape(self.inputs)
            ones        = tf.ones([input_shape[0], input_shape[1]])
            loss = tf.contrib.seq2seq.sequence_loss(self.logits, self.targets,
                                                    ones)

        #-----------------------------------------------------------------------
        # Build the optimizer
        #-----------------------------------------------------------------------
        with tf.name_scope('optimizer'):
            optimizer = tf.train.AdamOptimizer(learning_rate)
            gradients = optimizer.compute_gradients(loss)
            capped_gradients = [(tf.clip_by_value(grad, -1., 1.), var) \
                                for grad, var in gradients if grad is not None]
            optimizer_op = optimizer.apply_gradients(capped_gradients)

        return optimizer_op, loss