TensorFlow 入门 Mnist 样例代码分析 ——– TensorFlow系列学习笔记（六）

TensorFlow 入门  Mnist 样例代码分析 

1.数据下载：

2.简单神经网络代码

获取mnist训练数据集input_data.py

3.卷积神经网络 CNN

---

TensorFlow 入门  Mnist 样例代码分析 

Mnist手写数字识别实例是深度学习的"Hello World"，每一个深度学习框架都有Mnist的入门例程。参考网上信息将此进行总结整理以便日后查阅。

1.数据下载：

从官网Yann LeCun's MNIST page 下载训练集与测试集数据，自动下载速度过慢，将下载好的数据放到Python code下，并新建文件夹MNIST_data。

文件	内容
train-images-idx3-ubyte.gz	训练集图片 - 55000 张 训练图片, 5000 张 验证图片
train-labels-idx1-ubyte.gz	训练集图片对应的数字标签
t10k-images-idx3-ubyte.gz	测试集图片 - 10000 张 图片
t10k-labels-idx1-ubyte.gz	测试集图片对应的数字标签

2.简单神经网络代码

理论部分可移步http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html，本文只针对简单神经网络构建代码进行分析解释。

# -*- coding: utf-8 -*-
#导入TensorFlow
import tensorflow as tf
#调用 input_data.py 如果此步骤发生错误，可在本博客复制input_data.py，新建python 文件到当前工程
from tensorflow.examples.tutorials.mnist import input_data

# 下载MINIST数据集
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)


# None表示输入任意数量的MNIST图像，每一张图展平成784维的向量
# placeholder是占位符，在训练时指定
x = tf.placeholder(tf.float32, [None, 784])

# 初始化W，b矩阵  W的维度是[784，10]，用784维的图片向量乘以它以得到一个10维的证据值向量，每一位对应不同数字类。b的形状是[10]，可以直接把它加到输出上面。
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

# 这里便是神经网络模型   tf.matmul(​​X，W)表示x乘以W
y = tf.nn.softmax(tf.matmul(x, W) + b)

# 为了计算交叉熵，我们首先需要添加一个新的占位符用于输入正确值
y_ = tf.placeholder("float", [None, 10])

# 交叉熵损失函数
cross_entropy = -tf.reduce_sum(y_*tf.log(y))

# 模型的训练，不断的降低成本函数
# 要求TensorFlow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)

# 在运行计算之前，需要添加一个操作来初始化我们创建的变量
init = tf.global_variables_initializer()


# 在Session里面启动我模型，并且初始化变量
sess = tf.Session()
sess.run(init)

# 开始训练模型,循环训练1000次
for i in range(50):
    # 随机抓取训练数据中的100个批处理数据点
    batch_xs, batch_ys = mnist.train.next_batch(100)
    # 然后我们用这些数据点作为参数替换之前的占位符来运行train_step
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})


# 检验真实标签与预测标签是否一致
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))

# 计算精确度，将true和false转化成相应的浮点数，求和取平均
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

# 计算所学习到的模型在测试数据集上面的正确率
print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

获取 Mnist 数据集 input_data.py

# Copyright 2015 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""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)[0]#新增加 [0]
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

3.卷积神经网络 CNN

理论部分可移步http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html，本文只针对卷积神经网络构建代码进行分析解释。

# -*- coding: utf-8 -*-
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
 
#最好填绝对路径
dir = '\MNIST_data'  
#导入数据  
mnist = input_data.read_data_sets(dir, one_hot=True)

#输出数据信息  
print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.train.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)
 
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
sess = tf.InteractiveSession()


#构建一个多层卷积网络

#权重初始化
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)
 
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

#卷积和池化
def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
 
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                          strides=[1, 2, 2, 1], padding='SAME')

#第一层卷积
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 28, 28, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

#第二层卷积
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)

#密集连接层
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)

#dropput 减少过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#输出层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

#训练和评估模型
cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=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, tf.float32))
sess.run(tf.global_variables_initializer())
for i in range(2000):
    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})