eval_output_embeddings.py 文件源码

def run():
    if len(sys.argv) < 4:
        print("** Usage: python3 " + sys.argv[0] + " <<Model Directory>> <<Everything Set>> <<Test Set>>")
        sys.exit(1)

    np.random.seed(42)
    model_dir = sys.argv[1]
    config = Config.load(['./default.conf', os.path.join(model_dir, 'model.conf')])
    model = create_model(config)

    everything_labels, everything_label_lengths = load_programs(config, sys.argv[2])
    test_labels, test_label_lengths = load_programs(config, sys.argv[3])
    #test_labels, test_label_lengths = sample(config.grammar, test_labels, test_label_lengths)
    print("unknown", unknown_tokens)

    with tf.Graph().as_default():
        tf.set_random_seed(1234)
        model.build()
        loader = tf.train.Saver()

        train_bag_of_tokens = bag_of_tokens(config, everything_labels, everything_label_lengths)
        V, mean = pca_fit(train_bag_of_tokens, n_components=2)

        eval_bag_of_tokens = bag_of_tokens(config, test_labels, test_label_lengths)
        transformed = pca_transform(eval_bag_of_tokens, V, mean)

        with tf.Session() as sess:
            loader.restore(sess, os.path.join(model_dir, 'best'))
            transformed = transformed.eval(session=sess)

        programs = reconstruct_programs(test_labels, test_label_lengths, config.grammar.tokens)
        show_pca(transformed, programs)