seq2seq 实例

在https://github.com/tensorflow/models/blob/master/tutorials/rnn/translate/translate.py
加入这两个函数

def self_test_predict():
    """Test the translation model."""
    with tf.Session() as sess:
        print("Self-test for neural translation model.")
        # Create model with vocabularies of 10, 2 small buckets, 2 layers of 32.
        model = seq2seq_model.Seq2SeqModel(10, 10, [(3, 3), (6, 6)], 32, 2,
                                           5.0, 1, 0.3, 0.99, num_samples=8,forward_only=True)
        sess.run(tf.global_variables_initializer())
        ckpt = tf.train.get_checkpoint_state(".\\tmp")
        if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path):
            print("Reading model parameters from %s" % ckpt.model_checkpoint_path)
            model.saver.restore(sess, ckpt.model_checkpoint_path)
        # Fake data set for both the (3, 3) and (6, 6) bucket.
        data_set = ([([1, 1], [2, 2]), ([3, 3], [4]), ([5], [6])],
                    [([1, 1, 1, 1, 1], [2, 2, 2, 2, 2]), ([3, 3, 3], [5, 6])])
        for _ in xrange(5):  # Train the fake model for 5 steps.
            bucket_id = random.choice([0, 1])
            encoder_inputs, decoder_inputs, target_weights = model.get_batch(
                data_set, bucket_id)
            print(encoder_inputs)
            _, eval_loss, output_logits = model.step(sess, encoder_inputs, decoder_inputs, target_weights,
                                                     bucket_id, True)

            outputs = [np.argmax(logit, axis=1) for logit in output_logits]
            print(outputs)

def self_test_train():
    """Test the translation model."""
    with tf.Session() as sess:
        print("Self-test for neural translation model.")
        # Create model with vocabularies of 10, 2 small buckets, 2 layers of 32.
        model = seq2seq_model.Seq2SeqModel(10, 10, [(3, 3), (6, 6)], 32, 2,
                                           5.0, 16, 0.3, 0.99, num_samples=8)

        sess.run(tf.global_variables_initializer())

        # Fake data set for both the (3, 3) and (6, 6) bucket.
        data_set = ([([1, 1], [2, 2]), ([3, 3], [4]), ([5], [6])],
                    [([1, 1, 1, 1, 1], [2, 2, 2, 2, 2]), ([3, 3, 3], [5, 6])])
        for step in xrange(501):  # Train the fake model for 5 steps.
            bucket_id = random.choice([0, 1])
            encoder_inputs, decoder_inputs, target_weights = model.get_batch(
                data_set, bucket_id)
            loss,_,_ = model.step(sess, encoder_inputs, decoder_inputs, target_weights,
                       bucket_id, False)
            if step % 100 == 0:
                print(step,loss)
                checkpoint_path = os.path.join(".\\tmp", "translate_example.ckpt")
                model.saver.save(sess, checkpoint_path, global_step=model.global_step)