Deep Learning——TensorFlow平台下MNIST的实现（基于shallow learning）

***下面操作都是基于/tensorflow/models/image/mnist目录下***  大家可自行选择
1.下载input_data.py文件 （此文件代码主要是实现下载数据集）
  文件内容：

"""Functions for downloading and reading MNIST data."""

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

import gzip

import os

import numpy

from six.moves import urllib

from six.moves import xrange  # pylint: disable=redefined-builtin

SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'

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

def _read32(bytestream):

  dt = numpy.dtype(numpy.uint32).newbyteorder('>')

  return numpy.frombuffer(bytestream.read(4), dtype=dt)

def extract_images(filename):

  """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""

  print('Extracting', filename)

  with gzip.open(filename) as bytestream:

    magic = _read32(bytestream)

    if magic != 2051:

      raise ValueError(

          'Invalid magic number %d in MNIST image file: %s' %

          (magic, filename))

    num_images = _read32(bytestream)

    rows = _read32(bytestream)

    cols = _read32(bytestream)

    buf = bytestream.read(rows * cols * num_images)

    data = numpy.frombuffer(buf, dtype=numpy.uint8)

    data = data.reshape(num_images, rows, cols, 1)

    return data

def dense_to_one_hot(labels_dense, num_classes=10):

  """Convert class labels from scalars to one-hot vectors."""

  num_labels = labels_dense.shape[0]

  index_offset = numpy.arange(num_labels) * num_classes

  labels_one_hot = numpy.zeros((num_labels, num_classes))

  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1

  return labels_one_hot

def extract_labels(filename, one_hot=False):

  """Extract the labels into a 1D uint8 numpy array [index]."""

  print('Extracting', filename)

  with gzip.open(filename) as bytestream:

    magic = _read32(bytestream)

    if magic != 2049:

      raise ValueError(

          'Invalid magic number %d in MNIST label file: %s' %

          (magic, filename))

    num_items = _read32(bytestream)

    buf = bytestream.read(num_items)

    labels = numpy.frombuffer(buf, dtype=numpy.uint8)

    if one_hot:

      return dense_to_one_hot(labels)

    return labels

class DataSet(object):

  def __init__(self, images, labels, fake_data=False):

    if fake_data:

      self._num_examples = 10000

    else:

      assert images.shape[0] == labels.shape[0], (

          "images.shape: %s labels.shape: %s" % (images.shape,

                                                 labels.shape))

      self._num_examples = images.shape[0]

      # Convert shape from [num examples, rows, columns, depth]

      # to [num examples, rows*columns] (assuming depth == 1)

      assert images.shape[3] == 1

      images = images.reshape(images.shape[0],

                              images.shape[1] * images.shape[2])

      # Convert from [0, 255] -> [0.0, 1.0].

      images = images.astype(numpy.float32)

      images = numpy.multiply(images, 1.0 / 255.0)

    self._images = images

    self._labels = labels

    self._epochs_completed = 0

    self._index_in_epoch = 0

  @property

  def images(self):

    return self._images

  @property

  def labels(self):

    return self._labels

  @property

  def num_examples(self):

    return self._num_examples

  @property

  def epochs_completed(self):

    return self._epochs_completed

  def next_batch(self, batch_size, fake_data=False):

    """Return the next `batch_size` examples from this data set."""

    if fake_data:

      fake_image = [1.0 for _ in xrange(784)]

      fake_label = 0

      return [fake_image for _ in xrange(batch_size)], [

          fake_label for _ in xrange(batch_size)]

    start = self._index_in_epoch

    self._index_in_epoch += batch_size

    if self._index_in_epoch > self._num_examples:

      # Finished epoch

      self._epochs_completed += 1

      # Shuffle the data

      perm = numpy.arange(self._num_examples)

      numpy.random.shuffle(perm)

      self._images = self._images[perm]

      self._labels = self._labels[perm]

      # Start next epoch

      start = 0

      self._index_in_epoch = batch_size

      assert batch_size <= self._num_examples

    end = self._index_in_epoch

    return self._images[start:end], self._labels[start:end]

def read_data_sets(train_dir, fake_data=False, one_hot=False):

  class DataSets(object):

    pass

  data_sets = DataSets()

  if fake_data:

    data_sets.train = DataSet([], [], fake_data=True)

    data_sets.validation = DataSet([], [], fake_data=True)

    data_sets.test = DataSet([], [], fake_data=True)

    return data_sets

  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'

  TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'

  TEST_IMAGES = 't10k-images-idx3-ubyte.gz'

  TEST_LABELS = 't10k-labels-idx1-ubyte.gz'

  VALIDATION_SIZE = 5000

  local_file = maybe_download(TRAIN_IMAGES, train_dir)

  train_images = extract_images(local_file)

  local_file = maybe_download(TRAIN_LABELS, train_dir)

  train_labels = extract_labels(local_file, one_hot=one_hot)

  local_file = maybe_download(TEST_IMAGES, train_dir)

  test_images = extract_images(local_file)

  local_file = maybe_download(TEST_LABELS, train_dir)

  test_labels = extract_labels(local_file, one_hot=one_hot)

  validation_images = train_images[:VALIDATION_SIZE]

  validation_labels = train_labels[:VALIDATION_SIZE]

  train_images = train_images[VALIDATION_SIZE:]

  train_labels = train_labels[VALIDATION_SIZE:]

  data_sets.train = DataSet(train_images, train_labels)

  data_sets.validation = DataSet(validation_images, validation_labels)

  data_sets.test = DataSet(test_images, test_labels)

  return data_sets

2.切换到python命令模式下
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)  #这里的第一个参数是下载的文件所放的位置

3.下载完成之后，建一个文件test_tensor_flow_mnist.py

#!/usr/bin/env python 

import input_data
import tensorflow as tf

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #这里的第一个参数要和刚刚所放的文件地址一样（相对位置），如果程序找不到也会自动重新下载

x = tf.placeholder("float", [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})

然后在Linux命令模式下执行该程序

python test_tensor_flow_mnist.py

得出的结果基本都在91%   (我的是0.9173)