基于Tensorflow读取MNIST数据集时网络超时的解决方式

最近在学习TensorFlow，比较烦人的是使用tensorflow.examples.tutorials.mnist.input_data读取数据

from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('/temp/mnist_data/')
X = mnist.test.images.reshape(-1, n_steps, n_inputs)
y = mnist.test.labels

时，经常出现网络连接错误

解决方法其实很简单，这里我们可以看一下input_data.py的源代码（这里截取关键部分）

def maybe_download(filename, work_directory):
 """Download the data from Yann's website, unless it's already here."""
 if not os.path.exists(work_directory):
 os.mkdir(work_directory)
 filepath = os.path.join(work_directory, filename)
 if not os.path.exists(filepath):
 filepath, _ = urllib.request.urlretrieve(SOURCE_URL + filename, filepath)
 statinfo = os.stat(filepath)
 print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
return filepath

可以看到，代码会先检查文件是否存在，如果不存在再进行下载，那么我是不是自己下载数据不就行了？

MNIST的数据集是从Yann LeCun教授的官网下载，下载完成之后修改一下我们读取数据的代码，加上我们下载的路径即可

from tensorflow.examples.tutorials.mnist import input_data
import os

data_path = os.path.join('.', 'temp', 'data')
mnist = input_data.read_data_sets(datapath)
X = mnist.test.images.reshape(-1, n_steps, n_inputs)
y = mnist.test.labels

测试一下

成功！

补充知识：在tensorflow的使用中，from tensorflow.examples.tutorials.mnist import input_data报错

最近在学习使用python的tensorflow的使用，使用编辑器为spyder,在输入以下代码时会报错：

from tensorflow.examples.tutorials.mnist import input_data

报错内容如下：

from tensorflow.python.autograph.lang.special_functions import stack ImportError: cannot import name ‘stack’

为了解决这个问题，在

File “K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\autograph_init_.py”文件中直接把 from tensorflow.python.autograph.lang.special_functions import stack

这一行注释掉了，问题并没有解决。然后又把下面一行注释掉了：

from tensorflow.python.autograph.lang.special_functions import tensor_list

问题解决，但报了一大顿warning：

WARNING:tensorflow:From C:/Users/phmnku/.spyder-py3/tensorflow_prac/classification.py:4: read_data_sets (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version. Instructions for updating: Please use alternatives such as official/mnist/dataset.py from tensorflow/models. WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:260: maybe_download (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version. Instructions for updating: Please write your own downloading logic. WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:262: extract_images (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version. Instructions for updating: Please use tf.data to implement this functionality. Extracting MNIST_data\train-images-idx3-ubyte.gz WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:267: extract_labels (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version. Instructions for updating: Please use tf.data to implement this functionality. Extracting MNIST_data\train-labels-idx1-ubyte.gz WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:110: dense_to_one_hot (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version. Instructions for updating: Please use tf.one_hot on tensors. Extracting MNIST_data\t10k-images-idx3-ubyte.gz Extracting MNIST_data\t10k-labels-idx1-ubyte.gz WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\mnist.py:290: DataSet.__init__ (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version. Instructions for updating: Please use alternatives such as official/mnist/dataset.py from tensorflow/models. WARNING:tensorflow:From K:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\tf_should_use.py:189: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02. Instructions for updating: Use `tf.global_variables_initializer` instead.

但是程序好歹能用了

以上这篇基于Tensorflow读取MNIST数据集时网络超时的解决方式就是小编分享给大家的全部内容了，希望能给大家一个参考。