使用tensorflow DataSet实现高效加载变长文本输入

def writedata():
 xlist = [[1,2,3],[4,5,6,8]]
 ylist = [1,2]
 #这里的数据只是举个例子来说明样本的文本长度不一样，第一个样本3个词标签1，第二个样本4个词标签2
 writer = tf.python_io.TFRecordWriter("train.tfrecords")
 for i in range(2):
  x = xlist[i]
  y = ylist[i]
  example = tf.train.Example(features=tf.train.Features(feature={
   "y": tf.train.Feature(int64_list=tf.train.Int64List(value=[y])),
   'x': tf.train.Feature(int64_list=tf.train.Int64List(value=x))
  }))
  writer.write(example.SerializeToString())
 writer.close()

feature_names = ['x']
 
def my_input_fn(file_path, perform_shuffle=False, repeat_count=1):
 def parse(example_proto):
  features = {"x": tf.VarLenFeature(tf.int64),
    "y": tf.FixedLenFeature([1], tf.int64)}
  parsed_features = tf.parse_single_example(example_proto, features)
  x = tf.sparse_tensor_to_dense(parsed_features["x"])
  x = tf.cast(x, tf.int32)
  x = dict(zip(feature_names, [x]))
  y = tf.cast(parsed_features["y"], tf.int32)
  return x, y
 
 dataset = (tf.contrib.data.TFRecordDataset(file_path)
    .map(parse))
 if perform_shuffle:
  dataset = dataset.shuffle(buffer_size=256)
 dataset = dataset.repeat(repeat_count)
 dataset = dataset.padded_batch(2, padded_shapes=({'x':[6]},[1])) #batch size为2，并且x按maxlen=6来做padding
 iterator = dataset.make_one_shot_iterator()
 batch_features, batch_labels = iterator.get_next()
 return batch_features, batch_labels
 
next_batch = my_input_fn('train.tfrecords', True)
init = tf.initialize_all_variables()
with tf.Session() as sess:
 sess.run(init)
 for i in range(1):
  xs, y =sess.run(next_batch)
  print(xs['x'])
  print(y)