Tensorflow学习笔记(三)MNIST初探

写在前面

上一篇笔记里面已经介绍了MNIST数据集使用Softmax回归进行处理的基本框架，这篇笔记会记录更多实践的过程。（适合python初学者）
因为Docker安装的tensorflow是最小包，所以教程上提到的文件没有找到有效的运行方法，就干脆抽取了项目核心部分的代码单独拿出来运行实验。

1. 文件准备

首先到MNIST官网上下载了四个gz数据文件，放入mnist_data文件夹中，然后找到tensorflow/python/platform/gfile.py放到需要运行的文件夹下面。（如果直接去git上下载了tensorflow-r.010是不能直接运行其中的文件的，因为里面的python路径冲突的缘故。）

---

2. 导入必要的模块

在文件一开始就导入tensorflow程序必要的一些模块和接下来解压文件需要的一些模块。

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os
import tempfile
import gfile
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf

3. 数据导入

对这四个文件的解压和读取主要调用：
1) _read32(bytestream)用于读取二进制文件

def _read32(bytestream):
  dt = numpy.dtype(numpy.uint32).newbyteorder('>')
  return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]

2)extract_images解压图片文件

def extract_images(filename):
  """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
  print('Extracting', filename)
  with gfile.Open(filename, 'rb') as f, gzip.GzipFile(fileobj=f) 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

3)extract_labels解压标签文件

def extract_labels(filename, one_hot=False, num_classes=10):
  """Extract the labels into a 1D uint8 numpy array [index]."""
  print('Extracting', filename)
  with gfile.Open(filename, 'rb') as f, gzip.GzipFile(fileobj=f) 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, num_classes)
    return labels

4)dense_to_one_hot将标签数据转换成one-hot向量

def dense_to_one_hot(labels_dense, num_classes):
  """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

4.辅助数据集定义Dataset

在这个类里会用到一个dtype的模块，我查了一下这个模块似乎是将所有数据类型都放进了枚举类型里blabla……从函数内容来看并不重要，所以我直接把dtype.***改成了直接使用tensorflow的数据类型tf.***来表示。

class DataSet(object):

  def __init__(self,
               images,
               labels,
               fake_data=False,
               one_hot=False,
               dtype=tf.float32,
               reshape=True):
    """Construct a DataSet.
    one_hot arg is used only if fake_data is true.  `dtype` can be either
    `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
    `[0, 1]`.
    """
    if dtype not in (tf.uint8, tf.float32):
      raise TypeError('Invalid image dtype %r, expected uint8 or float32' %
                      dtype)
    if fake_data:
      self._num_examples = 10000
      self.one_hot = one_hot
    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)
      if reshape:
        assert images.shape[3] == 1
        images = images.reshape(images.shape[0],
                                images.shape[1] * images.shape[2])
      if dtype == tf.float32:
        # 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] * 784
      if self.one_hot:
        fake_label = [1] + [0] * 9
      else:
        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]

5.文件读取

终于到了文件读取的部分啦！前面坐的那么多准备函数都是为了在这里被调用哒！这也是官方教程里input_data.py最重要的最后一行里要用的函数！

//定义一个Dataset
Dataset = collections.namedtuple('Dataset', ['data', 'target'])
Datasets = collections.namedtuple('Datasets', ['train', 'validation', 'test'])

def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=tf.float32,
                   reshape=True):
  if fake_data:

    def fake():
      return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)

    train = fake()
    validation = fake()
    test = fake()
    return base.Datasets(train=train, validation=validation, test=test)

  TRAIN_IMAGES = train_dir+'train-images-idx3-ubyte.gz'
  TRAIN_LABELS = train_dir+'train-labels-idx1-ubyte.gz'
  TEST_IMAGES = train_dir+'t10k-images-idx3-ubyte.gz'
  TEST_LABELS = train_dir+'t10k-labels-idx1-ubyte.gz'
  VALIDATION_SIZE = 5000

  train_images = extract_images(TRAIN_IMAGES)

  train_labels = extract_labels(TRAIN_LABELS, one_hot=one_hot)

  test_images = extract_images(TEST_IMAGES)

  test_labels = extract_labels(TEST_LABELS, 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:]

  train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)
  validation = DataSet(validation_images,
                       validation_labels,
                       dtype=dtype,
                       reshape=reshape)
  test = DataSet(test_images, test_labels, dtype=dtype, reshape=reshape)

  return Datasets(train=train, validation=validation, test=test)

6.softmax回归实现

现在，就可以根据上一篇博客中提到的softmax回归来实现对MNIST数据集的处理啦！

//准备数据
mnist = read_data_sets("mnist_data/", one_hot=True)
//完成数据准备，使用softmax回归模型训练数据
sess = tf.InteractiveSession()

# Create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)

# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

# Train
tf.initialize_all_variables().run()
for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  train_step.run({x: batch_xs, y_: batch_ys})

# Test trained model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels}))

第一次运行得到了0.9204的正确率，看起来还不错嘛~
但是教程中也提到了这个正确率并不算高呢~所以我们接下来就要对这个简单的softmax模型进行一些改进！