快捷導(dǎo)航

基于Tensorflow讀取MNIST數(shù)據(jù)集時網(wǎng)絡(luò)超時的解決方式

更新時間：2020年06月22日 14:19:12 作者：sdoddyjm68

這篇文章主要介紹了基于Tensorflow讀取MNIST數(shù)據(jù)集時網(wǎng)絡(luò)超時的解決方式，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

最近在學習TensorFlow，比較煩人的是使用tensorflow.examples.tutorials.mnist.input_data讀取數(shù)據(jù)

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

時，經(jīng)常出現(xiàn)網(wǎng)絡(luò)連接錯誤

解決方法其實很簡單，這里我們可以看一下input_data.py的源代碼（這里截取關(guān)鍵部分）

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，代碼會先檢查文件是否存在，如果不存在再進行下載，那么我是不是自己下載數(shù)據(jù)不就行了？

MNIST的數(shù)據(jù)集是從Yann LeCun教授的官網(wǎng)下載，下載完成之后修改一下我們讀取數(shù)據(jù)的代碼，加上我們下載的路徑即可

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

測試一下

成功！

補充知識：在tensorflow的使用中，from tensorflow.examples.tutorials.mnist import input_data報錯

最近在學習使用python的tensorflow的使用，使用編輯器為spyder,在輸入以下代碼時會報錯：

from tensorflow.examples.tutorials.mnist import input_data

報錯內(nèi)容如下：

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

為了解決這個問題，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

這一行注釋掉了，問題并沒有解決。然后又把下面一行注釋掉了：

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

問題解決，但報了一大頓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.