1

4 チャンネル以上の情報を持つ画像 (Github: https://github.com/tensorflow/models/tree/master/research/deeplab with tensorflow version 1.14.0)を分類するために、deeplab フレームワークを使用しています。

個別のチャネルを .gif ファイルに入れ、変更されたbuild_voc_2012.pybuild_data.py、および変更されたdata_generator.pyを使用してそれらを読み取るという考えがありました。他のすべてはレポにそのまま残されます。

shard 生成と train.py は正常に動作しているようです。この問題は、エラーがスローされる eval.py で発生します。

これは、シャードが生成される場所のコードです。


"""Contains common utility functions and classes for building dataset.

This script contains utility functions and classes to converts dataset to
TFRecord file format with Example protos.

The Example proto contains the following fields:

  image/encoded: encoded image content.
  image/filename: image filename.
  image/format: image file format.
  image/height: image height.
  image/width: image width.
  image/channels: image channels.
  image/segmentation/class/encoded: encoded semantic segmentation content.
  image/segmentation/class/format: semantic segmentation file format.
"""
import collections
import six
import tensorflow as tf

FLAGS = tf.app.flags.FLAGS

tf.app.flags.DEFINE_enum('image_format', 'png', ['jpg', 'jpeg', 'png', 'gif'],
                         'Image format.')

tf.app.flags.DEFINE_enum('label_format', 'png', ['png'],
                         'Segmentation label format.')

# A map from image format to expected data format.
_IMAGE_FORMAT_MAP = {
    'jpg': 'jpeg',
    'jpeg': 'jpeg',
    'png': 'png',
    'gif': 'gif'
}


class ImageReader(object):
    """Helper class that provides TensorFlow image coding utilities."""

    def __init__(self, image_format = "jpeg", channels=3):
        """Class constructor.

        Args:
          image_format: Image format. Only 'jpeg', 'jpg', or 'png' are supported.
          channels: Image channels.
        """
        with tf.Graph().as_default():
            self._decode_data = tf.placeholder(dtype=tf.string)
            self._image_format = image_format
            self._session = tf.Session()
            self.channels = channels
            if self._image_format in ('jpeg', 'jpg'):
                self._decode = tf.image.decode_jpeg(self._decode_data,channels)
            elif self._image_format == 'png':
                self._decode = tf.image.decode_png(self._decode_data,channels)
            elif self._image_format == 'gif':
                self._decode = tf.image.decode_gif(self._decode_data)


    def read_image_dims_gif(self, gif_data):
        """Reads the image dimensions.

        Args:
            image_data: numpy array of image data.

        Returns:
            image_height and image_width.
        """

        image = self.decode_gif(gif_data)
        return image.shape[:4]

    def decode_gif(self, image_data):
        """Decodes the image data string.

        Args:
          image_data: string of image data.

        Returns:
          Decoded image data.

        Raises:
          ValueError: Value of image channels not supported.
        """
        image = self._session.run(self._decode,
                                  feed_dict={self._decode_data: image_data})

        return image


def _float64_list_feature(values):
    """Returns a TF-Feature of float_list.

    Args:
      values: A scalar or list of values.

    Returns:
      A TF-Feature.
    """

    if not isinstance(values, collections.Iterable):
        values = [values]

    return tf.train.Feature(float_list=tf.train.FloatList(value=values))


def _int64_list_feature(values):
    """Returns a TF-Feature of int64_list.

    Args:
      values: A scalar or list of values.

    Returns:
      A TF-Feature.
    """
    if not isinstance(values, collections.Iterable):
        values = [values]

    return tf.train.Feature(int64_list=tf.train.Int64List(value=values))


def _bytes_list_feature(values):
    """Returns a TF-Feature of bytes.

    Args:
      values: A string.

    Returns:
      A TF-Feature.
    """

    def norm2bytes(value):
        return value.encode() if isinstance(value, str) and six.PY3 else value

    return tf.train.Feature(
        bytes_list=tf.train.BytesList(value=[norm2bytes(values)]))


def image_seg_to_tfexample_gif(image_data, filename, height, width, seg_data, channels, frames):
    """Converts one image/segmentation pair to tf example.

    Args
     image_data: encoded image data
     filename: image filename.
     height: image height.
     width: image width.
     frames: number of frames in gif
     seg_data: string of semantic segmentation data.
     channels: int of number of image channels
    Returns:
     tf example of one image/segmentation pair.
    """
    return tf.train.Example(features=tf.train.Features(feature={
        'image/encoded': _bytes_list_feature(image_data),
        'image/filename': _bytes_list_feature(filename),
        'image/format': _bytes_list_feature(
            _IMAGE_FORMAT_MAP[FLAGS.image_format]),
        'image/height': _int64_list_feature(height),
        'image/width': _int64_list_feature(width),
        'image/channels': _float64_list_feature(channels),
        'image/segmentation/class/encoded': (
            _bytes_list_feature(seg_data)),
        'image/segmentation/class/format': _bytes_list_feature(
            FLAGS.label_format),
        }))

eval.py では、このコードはエラーを生成しているようです:

tf.contrib.training.evaluate_repeatedly(
        master=FLAGS.master,
        checkpoint_dir=FLAGS.checkpoint_dir,
        eval_ops=[update_op],
        max_number_of_evaluations=num_eval_iters,
        hooks=hooks,
        eval_interval_secs=FLAGS.eval_interval_secs)

エラーメッセージは次のとおりです。

Traceback (most recent call last):
  File "/home/user/models-master/research/deeplab/eval.py", line 188, in <module>
    tf.app.run()
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/home/user/.local/lib/python2.7/site-packages/absl/app.py", line 300, in run
    _run_main(main, args)
  File "/home/user/.local/lib/python2.7/site-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "/home/user/models-master/research/deeplab/eval.py", line 181, in main
    eval_interval_secs=FLAGS.eval_interval_secs)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/contrib/training/python/training/evaluation.py", line 453, in evaluate_repeatedly
    session.run(eval_ops, feed_dict)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 754, in run
    run_metadata=run_metadata)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1252, in run
    run_metadata=run_metadata)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1353, in run
    raise six.reraise(*original_exc_info)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1338, in run
    return self._sess.run(*args, **kwargs)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1411, in run
    run_metadata=run_metadata)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 1169, in run
    return self._sess.run(*args, **kwargs)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1173, in _run
    feed_dict_tensor, options, run_metadata)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1350, in _do_run
    run_metadata)
  File "/home/user/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1370, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
  (0) Invalid argument: Got 3 frames, but animated gifs can only be decoded by tf.image.decode_gif or tf.image.decode_image
     [[{{node cond/else/_1/DecodePng}}]]
     [[IteratorGetNext]]
  (1) Invalid argument: Got 3 frames, but animated gifs can only be decoded by tf.image.decode_gif or tf.image.decode_image
     [[{{node cond/else/_1/DecodePng}}]]
     [[IteratorGetNext]]
     [[mean_iou/confusion_matrix/assert_less_1/Assert/AssertGuard/Assert/data_1/_2007]]
0 successful operations.
0 derived errors ignored.

私のリポジトリへのリンクは次のとおりです: https://github.com/michael-ross-scott/DeeplabV3

4

1 に答える 1