TensorFlow入门：Mnist数据集识别代码

TensorFlow中文社区：http://www.tensorfly.cn/tfdoc/get_started/introduction.html

以下代码来自中文社区：

1）input_data.py

#coding=utf-8

#input_data.py的详解
#学习读取数据文件的方法，以便读取自己需要的数据库文件（二进制文件）
"""Functions for downloading and reading MNIST data."""
from __future__ import print_function
import gzip
import os
import urllib
import numpy
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."""
  #判断目录文件是否存在，不存在则创建该目录
  if not os.path.exists(work_directory):
    os.mkdir(work_directory)
  #需要读取的文件路径
  filepath = os.path.join(work_directory, filename)
  if not os.path.exists(filepath):
    filepath, _ = urllib.urlretrieve(SOURCE_URL + filename, filepath)
    statinfo = os.stat(filepath)
    print('Succesfully 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
#将稠密标签向量变成稀疏的标签矩阵
#eg：若原向量的第i行为3，则对应稀疏矩阵的第i行下标为3的值为1，其余为0
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_dense.ravel()将整个数组展成一个一维数组
  #labels_dense.flat[i]即将labels_dense看成一个一维数组，取其第i个变量
  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1#报错？
  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
    #若当前训练读取的index>总体的images数时，则读取读取开始的batch_size大小的数据
    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）mnist.py

#coding=utf-8
import input_data
import tensorflow as tf

#【数据加载】：包括训练集与测试集
#加载Mnist训练集数据
mnist = input_data.read_data_sets("MnistData/", one_hot=True)

#【实现回归模型】
#784=28*28，表示一张图片的像素点数量
x = tf.placeholder("float", [None, 784])

#表示输入是784，输出是10（0~9）
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

#matmul+softmax
y = tf.nn.softmax(tf.matmul(x,W) + b)

#【训练模型】
#定义交叉熵，用来进行反向参数调节
y_ = tf.placeholder("float", [None,10])

#计算交叉熵
cross_entropy = -tf.reduce_sum(y_*tf.log(y))

#用梯度下降算法（gradient descent algorithm）以0.01的学习速率最小化交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

#初始化设置好了的模型
init = tf.global_variables_initializer()

#在一个Session里面启动我们的模型，并且初始化变量
sess = tf.InteractiveSession()
sess.run(init)

#训练模型，让模型循环训练1000次
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})

#【评估模型】
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})

3）mnist_pro.py

#coding=utf-8
import input_data
import tensorflow as tf

#【权值初始化】
#定义初始化权重函数
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

#定义初始化偏置函数
def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

#【卷积和池化】
#定义conv算子，使用1步长（stride size），0边距（padding size）的模板
def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

#定义pooling算子，使用2x2大小的模板做max pooling  
def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')

#【数据加载】：包括训练集与测试集
#加载Mnist训练集数据
mnist = input_data.read_data_sets("MnistData/", one_hot=True)

#【运行TensorFlow的InteractiveSession】
sess = tf.InteractiveSession()

#【占位符】
#我们通过为输入图像和目标输出类别创建节点，来开始构建计算图。
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])
						
#【第一层卷积】
#它由一个卷积接一个max pooling完成。
#卷积在每个5x5的patch中算出32个特征。卷积的权重张量形状是[5, 5, 1, 32]，前两个维度是patch的大小，接着是输入的通道数目，最后是输出的通道数目。 
#而对于每一个输出通道都有一个对应的偏置量。
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

#把x变成一个4d向量，其第2、第3维对应图片的宽、高，最后一维代表图片的颜色通道数(因为是灰度图所以这里的通道数为1，如果是rgb彩色图，则为3)。
x_image = tf.reshape(x, [-1,28,28,1])

#把x_image和权值向量进行卷积，加上偏置项，然后应用ReLU激活函数，最后进行max pooling。
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#【第二层卷积】
#第二层中，每个5x5的patch会得到64个特征。
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#现在，图片尺寸减小到7x7，我们加入一个有1024个神经元的全连接层，用于处理整个图片。
#我们把池化层输出的张量reshape成一些向量，乘上权重矩阵，加上偏置，然后对其使用ReLU。
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#为了减少过拟合，我们在输出层之前加入dropout。
#我们用一个placeholder来代表一个神经元的输出在dropout中保持不变的概率。
#这样我们可以在训练过程中启用dropout，在测试过程中关闭dropout。 
#TensorFlow的tf.nn.dropout操作除了可以屏蔽神经元的输出外，还会自动处理神经元输出值的scale。
#所以用dropout的时候可以不用考虑scale。
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#【输出层】
#添加一个softmax层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#【训练和评估模型】
#为了进行训练和评估，我们使用与之前简单的单层SoftMax神经网络模型几乎相同的一套代码，
#只是我们会用更加复杂的ADAM优化器来做梯度最速下降，在feed_dict中加入额外的参数keep_prob来控制dropout比例。
#然后每100次迭代输出一次日志。
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.global_variables_initializer())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print "step %d, training accuracy %g"%(i, train_accuracy)
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print "test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})

使用方法：python mnist_pro.py

注：python版本为2.7