object detection API（训练自己的数据模型发生报错）（寻求高手指教）

xml-->csv-->.record均成功，在训练时发生错误。

使用命令行在dos下运行：

python model_main.py --logtostderr --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --model_dir=training/ --num_train_steps=50000 --num_eval_steps=2000

发生如下错误：

Traceback (most recent call last):
  File "model_main.py", line 110, in <module>
    tf.app.run()
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
    _sys.exit(main(argv))
  File "model_main.py", line 71, in main
    FLAGS.sample_1_of_n_eval_on_train_examples)
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\model_lib.py", line 589, in create_estimator_and_inputs
    pipeline_config_path, config_override=config_override)
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\utils\config_util.py", line 97, in get_configs_from_pipeline_file
    proto_str = f.read()
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 132, in read
    pywrap_tensorflow.ReadFromStream(self._read_buf, length, status))
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 100, in _prepare_value
    return compat.as_str_any(val)
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\util\compat.py", line 107, in as_str_any
    return as_str(value)
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\util\compat.py", line 80, in as_text
    return bytes_or_text.decode(encoding)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 332: invalid continuation byte

目前还没有找到原因和解决办法，求高手指教