tensorflow实现一个神经网络简单CNN网络

本例子用到了minst数据库，通过训练CNN网络，实现手写数字的预测。

首先先把数据集读取到程序中（MNIST数据集大约12MB，如果没在文件夹中找到就会自动下载）：

mnist = input_data.read_data_sets('data/MNIST_data', one_hot=True)

Extracting data/MNIST/train-images-idx3-ubyte.gz
Extracting data/MNIST/train-labels-idx1-ubyte.gz
Extracting data/MNIST/t10k-images-idx3-ubyte.gz
Extracting data/MNIST/t10k-labels-idx1-ubyte.gz

print("Size of:")
print("- Training-set:\t\t{}".format(len(mnist.train.labels)))
print("- Test-set:\t\t{}".format(len(mnist.test.labels)))
print("- Validation-set:\t{}".format(len(mnist.validation.labels)))

Size of:
- Training-set: 55000
- Test-set: 10000

- Validation-set: 5000

然后开始定义输入数据，利用占位符

• # define placeholder for inputs to network
  xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
  ys = tf.placeholder(tf.float32, [None, 10])
  keep_prob = tf.placeholder(tf.float32)
  x_image = tf.reshape(xs, [-1, 28, 28, 1])
  # print(x_image.shape)  # [n_samples, 28,28,1]

minst数据集中是28*28大小的图片，784就是一张展平的图片（28*28=784）。None表示输入图片的数量不定。类别是0-9总共10个类别，并定义了后面dropout的占位符。x_image又把展平的图片reshape成了28*28*1的形状，因为是灰色图片，所以通道是1.

然后定义几个函数来方便构造网络：

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)

def conv2d(x, W):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

truncated_normal函数使得W呈正态分布，标准差为0.1。初始化b为0.1。定义卷积层步数为1，并且周围补0。池化层采用kernel大小为2*2，步数也为2，周围补0。

然后定义CNN神经网络：

• ## conv1 layer ##
  W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
  b_conv1 = bias_variable([32])
  h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
  h_pool1 = max_pool_2x2(h_conv1)                                         # output size 14x14x32
  
  ## conv2 layer ##
  W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
  b_conv2 = bias_variable([64])
  h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
  h_pool2 = max_pool_2x2(h_conv2)                                         # output size 7x7x64
  
  ## func1 layer ##
  W_fc1 = weight_variable([7*7*64, 1024])
  b_fc1 = bias_variable([1024])
  # [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
  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)
  h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
  
  ## func2 layer ##
  W_fc2 = weight_variable([1024, 10])
  b_fc2 = bias_variable([10])
  prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

最后计算损失，使得损失最小。

# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1]))       # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

reduce_mean用于计算均值，用法如下： 
tf.reduce_mean(input_tensor, reduction_indices=None, keep_dims=False, name=None)

Computes the mean of elements across dimensions of a tensor.

# 'x' is [[1., 1.]
#         [2., 2.]]
tf.reduce_mean(x) ==> 1.5
tf.reduce_mean(x, 0) ==> [1.5, 1.5]
tf.reduce_mean(x, 1) ==> [1.,  2.]

完整代码如下：

from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('data/MNIST_data', one_hot=True)
def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
    return result

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)

def conv2d(x, W):
    # stride [1, x_movement, y_movement, 1]
    # Must have strides[0] = strides[3] = 1
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    # stride [1, x_movement, y_movement, 1]
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape)  # [n_samples, 28,28,1]

## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1)                                         # output size 14x14x32

## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2)                                         # output size 7x7x64

## func1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
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)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

## func2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))       # loss
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

sess = tf.Session()
# important step
sess.run(tf.initialize_all_variables())

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
    if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))