'utf-8' codec can't decode byte 0xd5 in position 182: invalid continuation byte

我在使用tensorflow糊出现该错误， 查了资料之后很多人说吧 tf.gfile.FastGFile（）中的‘r’改为‘rb’，但是我修改了之后仍然报错。

Traceback (most recent call last):
  File "D:/Deeplabv3+models-master/research/deeplab/datasets/build_voc2012_data.py", line 148, in <module>
    tf.app.run()
  File "F:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "F:\Anaconda\envs\tensorflow\lib\site-packages\absl\app.py", line 312, in run
    _run_main(main, args)
  File "F:\Anaconda\envs\tensorflow\lib\site-packages\absl\app.py", line 258, in _run_main
    sys.exit(main(argv))
  File "D:/Deeplabv3+models-master/research/deeplab/datasets/build_voc2012_data.py", line 144, in main
    _convert_dataset(dataset_split)
  File "D:/Deeplabv3+models-master/research/deeplab/datasets/build_voc2012_data.py", line 123, in _convert_dataset
    image_data = tf.gfile.FastGFile(image_filename, 'rb').read()
  File "F:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 117, in read
    self._preread_check()
  File "F:\Anaconda\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 80, in _preread_check
    compat.path_to_str(self.__name), 1024 * 512)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd5 in position 182: invalid continuation byte