[941]mnist数据集问题

raise IOError, ‘Not a gzipped file’

There is an error:

File "tensorflow/models/image/mnist/convolutional.py", line 59, in extract_data
    bytestream.read(16)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py", line 268, in read
    self._read(readsize)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py", line 303, in _read
    self._read_gzip_header()
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py", line 197, in _read_gzip_header
    raise IOError, 'Not a gzipped file'

解决方法：

The code attempts to download the data files from the MNIST web site, and assumes it’s properly downloaded if the file is present locally on your system. You might have a corrupted file, in which case deleting it and retrying might help. Otherwise, try to get the data via your browser directly from:

下载后替换原来的文件就没有问题了

http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz 
http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz 
http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz 
http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz

from tensorflow.examples.tutorials.mnist import input_data在未来的版本中将被移除解决方法

在学习神经网络时，经常会用到MNIST数据集，使用Tensorflow导入数据集的时候，使用以下方法有时会出现警告

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

解决方法是修改为以下代码

from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
import tensorflow as tf
mnist = read_data_sets("MNIST_data/", one_hot=True)

成功导入结果

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz

参考：https://blog.csdn.net/Julialove102123/article/details/70226249/
https://blog.csdn.net/qq1440643730/article/details/104122320