Question

我正在尝试将一个3D浮动列表写入TFrecord，所以我成功地通过首先展平它来编写它，我解析它但在重塑它时会引发错误。

错误：ValueError: Shapes () and (8,) are not compatible

这就是我写TFrecord文件的方式

def _floats_feature(value):
    return tf.train.Feature(float_list=tf.train.FloatList(value=value.flatten()))

def write(output_path, data_rgb, data_depth, data_decalib):
    with tf.python_io.TFRecordWriter(output_path) as writer:

        feature = {'data_rgb': _floats_feature(data_rgb),
                   'data_depth': _floats_feature(data_depth),
                   'data_decalib': _floats_feature(data_decalib)}
        sample = tf.train.Example(features=tf.train.Features(feature=feature))
        writer.write(sample.SerializeToString())

这就是我读TFrecord文件的方式

def get_batches(date, drives, batch_size=1):
    """
    Create a generator that returns batches of tuples
    rgb, depth and calibration
    :param date: date of the drive
    :param drives: array of the drive_numbers within the drive date
    :return: batch generator
    """

    filenames = get_paths_drives(date, drives)
    dataset = tf.data.TFRecordDataset(filenames)
    dataset = dataset.map(input_parser)  # Parse the record into tensors.
    dataset = dataset.repeat()  # Repeat the input indefinitely.
    dataset = dataset.batch(batch_size)

    return dataset

config = configparser.ConfigParser()
config.read(path_helpers.get_config_file_path())

IMAGE_WIDTH = int(config['DATA_INFORMATION']['IMAGE_WIDTH'])
IMAGE_HEIGHT = int(config['DATA_INFORMATION']['IMAGE_HEIGHT'])

INPUT_RGB_SHAPE = [IMAGE_HEIGHT, IMAGE_WIDTH, 3]
INPUT_DEPTH_SHAPE = [IMAGE_HEIGHT, IMAGE_WIDTH, 1]
LABEL_CALIB_SHAPE = [8]

def input_parser(example_proto):
    features = {'data_rgb': tf.FixedLenFeature([], tf.float32),
                'data_depth': tf.FixedLenFeature([], tf.float32),
                'data_decalib': tf.FixedLenFeature([], tf.float32)}
    parsed_features = tf.parse_single_example(example_proto, features)

    data_rgb = parsed_features['data_rgb']
    data_rgb.set_shape(np.prod(INPUT_RGB_SHAPE))
    img_rgb = tf.reshape(data_rgb, INPUT_RGB_SHAPE)

    data_depth = parsed_features['data_depth']
    data_depth.set_shape(np.prod(INPUT_DEPTH_SHAPE))
    img_depth = tf.reshape(data_depth, INPUT_DEPTH_SHAPE)

    data_decalib = parsed_features['data_decalib']
    data_decalib.set_shape(LABEL_CALIB_SHAPE)

    return img_rgb, img_depth, data_decalib

Answer 1

原来我需要按如下方式更改输入解析器：

def input_parser(example_proto):
    features = {'data_rgb': tf.FixedLenFeature(shape=[np.prod(INPUT_RGB_SHAPE)], dtype=tf.float32),
                'data_depth': tf.FixedLenFeature(shape=[np.prod(INPUT_DEPTH_SHAPE)], dtype=tf.float32),
                'data_decalib': tf.FixedLenFeature(shape=LABEL_CALIB_SHAPE, dtype=tf.float32)}
    parsed_features = tf.parse_single_example(example_proto, features)

作为tf.FixedLenFeature的文件规定。第一个参数是shape，我将其设置为[]，因此错误为ValueError: Shapes () and (8,) are not compatible。设定它们的真实价值就算了。

Tensorflow在Dataset.map（）中解析和重塑浮点列表

1 个答案: