第一阶段-入门详细图文讲解tensorflow1.4 -（五）MNIST-CNN

在第一阶段-入门详细图文讲解tensorflow1.4 -（四）新手MNIST上只有91%正确率，实在太糟糕。在本博客里，我们用一个稍微复杂的模型：a small convolutional neural network 卷积神经网络来改善效果。这会达到大概99.2%的准确率。

直接跳过，数据载入，构建softmax模型，训练模型，评估模型。不明白请阅读：
第一阶段-入门详细图文讲解tensorflow1.4 -（四）新手MNIST

先看一张图。这是我们构建CNN的蓝图。

表述一：权重初始化 Weight Initialization

在神经网络中会创建大量的权重和偏置值。如何初始化这些variables。
为避免零梯度，我们使用tf.truncated_normal(shape, mean, stddev)生成正态分布的值。shape表示生成张量的维度，mean是均值，stddev是标准差。这样聚能保证随机初始化的权重，偏置值不同。
正态分布：统计样本常见的一种数值分布。自然情况下，人的身高是属于正态分布的。

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)

表述二：卷积和池化 Convolution and Pooling

tensorflow提供非常灵活的卷积，池化操作。
TensorFlow also gives us a lot of flexibility in convolution and pooling operations.
卷积使用1步长（stride size），0边距（padding size）的模板，保证输出和输入是同一个大小。
池化用简单传统的2x2大小的模板做max pooling。

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')

明白上述两点，下面开始构建人工神经网络。

step1，输入层

x_image = tf.reshape(x, [-1,28,28,1])

tf.reshape(tensor, shape, name=None)调整tensor形状。

step2，第一层卷积和池化

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

step3，第二层卷积和池化

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)

step4，全连接层

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)

step5，优化层

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

step6，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

step7，评估和训练

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.initialize_all_variables())
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})

合并上述代码如下：

# -*- coding: utf-8 -*-
# load MNIST data
import input_data
mnist = input_data.read_data_sets("Mnist_data/", one_hot=True)

# start tensorflow interactiveSession
import tensorflow as tf
sess = tf.InteractiveSession()

# weight initialization
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)

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

# Create the model
# placeholder
x = tf.placeholder("float", [None, 784])
y_ = tf.placeholder("float", [None, 10])
# variables
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

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

# first convolutinal layer
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)

# second convolutional layer
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)

# densely connected layer
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)

# dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# readout layer
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)

# train and evaluate the model
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)
#train_step = tf.train.AdagradOptimizer(1e-5).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.initialize_all_variables())
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, train 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}))

run result：

本教程完。