NotFoundError：NewRandomAccessFile创建/打开失败：

Question

我刚刚在GitHub下载了Google-研究Bert的tensorflow版本。修改run_classifier.py之后，我在cmd中键入了以下命令，但似乎出了点问题。我在Windows 10中运行代码，而python版本为3.6，这是问题吗？

(tensorflowgpu) D:\pyproject\bert-master\bert-master>python run_classifier.py --data_dir=/dataset/ --task_name=zw --vocab_file=/chinese_L-12_H-768_A-12/vocab.txt --bert_config_file=/chinese_L-12_H-768_A-12/bert_config.json --do_train=true --do_eval=true --init_checkpoint=/chinese_L-12_H-768_A-12/bert.model.ckpt --max_seq_length=128 --train_batch_size=32 --learning_rate=5e-5 --num_train_epochs=10.0 --do_predict=true --output_dir=/tmp/
Traceback (most recent call last):
  File "run_classifier.py", line 1018, in <module>
    tf.app.run()
  File "C:\Users\zhiwei\AppData\Local\conda\conda\envs\tensorflowgpu\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
    _sys.exit(main(argv))
  File "run_classifier.py", line 837, in main
    bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)
  File "D:\pyproject\bert-master\bert-master\modeling.py", line 94, in from_json_file
    text = reader.read()
  File "C:\Users\zhiwei\AppData\Local\conda\conda\envs\tensorflowgpu\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 125, in read
    self._preread_check()
  File "C:\Users\zhiwei\AppData\Local\conda\conda\envs\tensorflowgpu\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 85, in _preread_check
    compat.as_bytes(self.__name), 1024 * 512, status)
  File "C:\Users\zhiwei\AppData\Local\conda\conda\envs\tensorflowgpu\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: /chinese_L-12_H-768_A-12/bert_config.json : ϵͳ\udcd5Ҳ\udcbb\udcb5\udcbdָ\udcb6\udca8\udcb5\udcc4·\udcbe\udcb6\udca1\udca3
; No such process