#载入MNIST数据集，创建默认的Interactive Session。
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()
 
#定义初始化函数，以便重复使用创建权重、偏置、卷积层、池化层。
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):
 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') 
 
#在设计卷积神经网络结构之前，定义输入的placeholder，x是特征，y_是真实Label。
#由于卷积神经网络会使用到空间结构信息，所以，需要将1D的输入向量转为2D图片结构，即从1*784的形式转换为原始的28*28结构。
#因为只有一个颜色通道，所以最终尺寸为[-1,28,28,1]，其中‘-1'代表样本数量不固定，'1'代表颜色通道数量。
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
#定义第一个卷积层。
#先使用前面函数进行初始化，包括weights和bias。其中[5,5,1,32]代表卷积核尺寸为5**5，1个颜色通道，32个不同的卷积核。
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)
#定义第二个卷积层。
#基本与第一个卷积层一样，只是其中的卷积核数量变成64.
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)
 
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)
#为了减轻过拟合，使用一个Dropout层，其用法是通过一个placeholder传入keep_prob比率来控制。
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
 
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)
#定义损失函数cross_entropy，这里选择Adam优化器。
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#继续定义评测准确率操作。
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
 
#开始训练过程。
tf.global_variables_initializer().run()
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})
#全部训练完毕，在最终的测试集上进行全面测试，得到整体的分类准确率。
print("test accuracy %g"%accuracy.eval(feed_dict={
 x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
step 0, training accuracy 0.1
step 100, training accuracy 0.82
step 200, training accuracy 0.9
step 300, training accuracy 0.9
step 400, training accuracy 0.96
step 500, training accuracy 0.9
step 600, training accuracy 0.94
step 700, training accuracy 0.96
step 800, training accuracy 0.94
step 900, training accuracy 0.98
.  .  .  .  .
 
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 1
step 19900, training accuracy 1
test accuracy 0.9929

#载入数据
import cifar10,cifar10_input
import tensorflow as tf
import numpy as np
import time
 
max_steps = 3000 #训练轮数
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'#下载数据默认路径。
 
 
def variable_with_weight_loss(shape, stddev, wl):
 var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
 if wl is not None:
  weight_loss = tf.multiply(tf.nn.l2_loss(var), wl, name='weight_loss')
  tf.add_to_collection('losses', weight_loss)
 return var
 
#计算CNN的损失。
def loss(logits, labels):
 
 labels = tf.cast(labels, tf.int64)
 cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
  logits=logits, labels=labels, name='cross_entropy_per_example')
 cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
 tf.add_to_collection('losses', cross_entropy_mean)
 
 return tf.add_n(tf.get_collection('losses'), name='total_loss') 
 
cifar10.maybe_download_and_extract()
 
images_train, labels_train = cifar10_input.distorted_inputs(data_dir=data_dir,
               batch_size=batch_size)
 
images_test, labels_test = cifar10_input.inputs(eval_data=True,
            data_dir=data_dir,
            batch_size=batch_size)            
 
image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])
 
#创建第一个卷积层。
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=0.0)
kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME')
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
      padding='SAME')
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
 
#创建第二个卷积层。
weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64], stddev=5e-2, wl=0.0)
kernel2 = tf.nn.conv2d(norm1, weight2, [1, 1, 1, 1], padding='SAME')
bias2 = tf.Variable(tf.constant(0.1, shape=[64]))
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2))
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
      padding='SAME')
#使用一个全连接层，先把第二个卷积层的输出结果flatten,将每个样本都变成一维向量。
reshape = tf.reshape(pool2, [batch_size, -1])
dim = reshape.get_shape()[1].value
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, wl=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3)
#下面这个使用的全连接层，其隐含节点数下降了一半。
weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, wl=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))          
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)
 
weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/192.0, wl=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
logits = tf.add(tf.matmul(local4, weight5), bias5)
loss = loss(logits, label_holder)
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) #0.72
top_k_op = tf.nn.in_top_k(logits, label_holder, 1)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
tf.train.start_queue_runners()
#正式开始训练。
for step in range(max_steps):
 start_time = time.time()
 image_batch,label_batch = sess.run([images_train,labels_train])
 _, loss_value = sess.run([train_op, loss],feed_dict={image_holder: image_batch,
               label_holder:label_batch})
 duration = time.time() - start_time
 if step % 10 == 0:
  examples_per_sec = batch_size / duration
  sec_per_batch = float(duration)
  
  format_str = ('step %d, loss = %.2f (%.1f examples/sec; %.3f sec/batch)')
  print(format_str % (step, loss_value, examples_per_sec, sec_per_batch))
  
#评测模型在测试集上的准确率。
num_examples = 10000
import math
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0 
total_sample_count = num_iter * batch_size
step = 0
while step < num_iter:
 image_batch,label_batch = sess.run([images_test,labels_test])
 predictions = sess.run([top_k_op],feed_dict={image_holder: image_batch,
             label_holder:label_batch})
 true_count += np.sum(predictions)
 step += 1
#最后，将准确率的评测结果计算并输出。
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)