readers.py 文件源码

def prepare_serialized_examples(self, serialized_example,
      max_quantized_value=2, min_quantized_value=-2):

    contexts, features = tf.parse_single_sequence_example(
        serialized_example,
        context_features={"video_id": tf.FixedLenFeature(
            [], tf.string),
                          "labels": tf.VarLenFeature(tf.int64)},
        sequence_features={
            feature_name : tf.FixedLenSequenceFeature([], dtype=tf.string)
            for feature_name in self.feature_names
        })

    # read ground truth labels
    labels = (tf.cast(
        tf.sparse_to_dense(contexts["labels"].values, (self.num_classes,), 1,
            validate_indices=False),
        tf.bool))

    # loads (potentially) different types of features and concatenates them
    num_features = len(self.feature_names)
    assert num_features > 0, "No feature selected: feature_names is empty!"

    assert len(self.feature_names) == len(self.feature_sizes), \
    "length of feature_names (={}) != length of feature_sizes (={})".format( \
    len(self.feature_names), len(self.feature_sizes))

    num_frames = -1  # the number of frames in the video
    feature_matrices = [None] * num_features  # an array of different features
    for feature_index in range(num_features):
      feature_matrix, num_frames_in_this_feature = self.get_video_matrix(
          features[self.feature_names[feature_index]],
          self.feature_sizes[feature_index],
          self.max_frames,
          max_quantized_value,
          min_quantized_value)
      if num_frames == -1:
        num_frames = num_frames_in_this_feature
      else:
        tf.assert_equal(num_frames, num_frames_in_this_feature)

      feature_matrices[feature_index] = feature_matrix

    # cap the number of frames at self.max_frames
    num_frames = tf.minimum(num_frames, self.max_frames)

    # concatenate different features
    video_matrix = tf.concat(feature_matrices, 1)

    # convert to batch format.
    # TODO: Do proper batch reads to remove the IO bottleneck.
    batch_video_ids = tf.expand_dims(contexts["video_id"], 0)
    batch_video_matrix = tf.expand_dims(video_matrix, 0)
    batch_labels = tf.expand_dims(labels, 0)
    batch_frames = tf.expand_dims(num_frames, 0)

    return batch_video_ids, batch_video_matrix, batch_labels, batch_frames