由于出现以下错误

所以怀疑是没有运行fully_connected_feed.py文件的问题。

错误：

不能运行fully_connected_feed.py

解决：

把克隆好的mnist数据集放入C:\Users\yyuqi\Anaconda3\Lib\site-packages\tensorflow\tensorflow\examples\tutorials\mnist中

运行python fully_connected_feed.py

又出现错误：

ModuleNotFoundError: No module named 'tensorflow.examples'

解决：

需要在创建的虚拟环境（Anaconda Prompt）中运行。

又出现错误：

C:\Users\yyuqi\Anaconda3\envs\tensorflow\lib\site-packages\h5py\__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import register_converters as _register_convertersTraceback (most recent call last): File "fully_connected_feed.py", line 279, in tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

File "C:\Users\yyuqi\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run

_sys.exit(main(_sys.argv[:1] + flags_passthrough))

File "fully_connected_feed.py", line 221, in main

tf.gfile.MakeDirs(FLAGS.log_dir)

File "C:\Users\yyuqi\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 367, in recursive_create_dir

pywrap_tensorflow.RecursivelyCreateDir(compat.as_bytes(dirname), status)

File "C:\Users\yyuqi\Anaconda3\envs\tensorflow\lib\contextlib.py", line 66, in __exit__

next(self.gen)

File "C:\Users\yyuqi\Anaconda3\envs\tensorflow\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: Failed to create a directory: /tmp\tensorflow