File "C:\Anaconda3\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 78, in _preread_check
compat.as_bytes(self.__name), 1024 * 512, status)
File "C:\Anaconda3\lib\contextlib.py", line 88, in __exit__
next(self.gen)
File "C:\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: ./..\vocab : ϵͳ\udcd5Ҳ\udcbb\udcb5\udcbdָ\udcb6\udca8\udcb5\udcc4\udcceļ\udcfe\udca1\udca3
出错代码：
vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab")
vocab_processor = learn.preprocessing.VocabularyProcessor.restore(vocab_path)
找了好久也没找到解决方法T T

有可能是权限不够，或者路径不对，仔细检查一下

你这是在加载模型吧？有可能是模型目录下checkpoint文件中的路径不对

我也遇到了，我是这样解决的
tf.flags.DEFINE_string("checkpoint_dir", "runs/1551860826/checkpoints", "Checkpoint directory from training run")把这个路径"runs/1551860826/checkpoints"改成你自己代码里checkpoints的路径
我原先下载是这样的tf.flags.DEFINE_string("checkpoint_dir", " ", "Checkpoint directory from training run")就会出现跟你一样的错误

路径不要有中文