单条文本预测？

[liutianling]

非常感谢您的开源精神！ 我想利用您的项目尝试单条文本预测？该如何做？ 我尝试改了下run_multiple_relations_extraction.py代码，最后再这个函数的时候，对单条文本这里要怎么输入？ d = tf.data.TFRecordDataset(input_file)

def input_fn(params):
    """The actual input function."""
    batch_size = params["batch_size"]

    # For training, we want a lot of parallel reading and shuffling.
    # For eval, we want no shuffling and parallel reading doesn't matter.
    d = tf.data.TFRecordDataset(input_file)
    if is_training:
        d = d.repeat()
        d = d.shuffle(buffer_size=100)

    d = d.apply(
        tf.contrib.data.map_and_batch(
            lambda record: _decode_record(record, name_to_features),
            batch_size=batch_size,
            drop_remainder=drop_remainder))

    return d

[yuanxiaosc]

@liutianling 最简单的方法就是把单条样本扩充成minibatch条样本

[liutianling]

@yuanxiaosc 谢谢，这个办法还是想过的，哈哈