data.py 文件源码

def input_stream(record_path, scope=None):
  """
  Input data stream
  ARGS
    `record_path`: tf records file path
  RETURN
    `streams`: data streams
  """
  with tf.device('/cpu:0'):
    with tf.variable_scope(scope or 'input_stream'):
      reader = tf.TFRecordReader()
      filename_queue = tf.train.string_input_producer([record_path], None)
      _, record_value = reader.read(filename_queue)
      features = tf.parse_single_example(record_value,
        {
          'image_jpeg': tf.FixedLenFeature([], tf.string),
          'image_name': tf.FixedLenFeature([], tf.string),
          'word_polygons': tf.VarLenFeature(tf.float32),
          # 'words': tf.VarLenFeature(tf.string) // FIXME: problem with parsing words
        })
      # decode jpeg image
      image = tf.cast(tf.image.decode_jpeg(features['image_jpeg'], channels=3), tf.float32)

      # extract bounding polygons
      word_polygons = tf.sparse_tensor_to_dense(features['word_polygons'])
      word_polygons = tf.reshape(word_polygons, [-1, WORD_POLYGON_DIM])

      # extract words
      # words = tf.sparse_tensor_to_dense(features['words'])

      # output streams
      streams = {'image': image,
                 'image_name': features['image_name'],
                 'image_jpeg': features['image_jpeg'],
                 'word_polygons': word_polygons}
      return streams