#載入MNIST數(shù)據(jù)集，創(chuàng)建默認(rèn)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()
 
#定義初始化函數(shù)，以便重復(fù)使用創(chuàng)建權(quán)重、偏置、卷積層、池化層。
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') 
 
#在設(shè)計(jì)卷積神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)之前，定義輸入的placeholder，x是特征，y_是真實(shí)Label。
#由于卷積神經(jīng)網(wǎng)絡(luò)會(huì)使用到空間結(jié)構(gòu)信息，所以，需要將1D的輸入向量轉(zhuǎn)為2D圖片結(jié)構(gòu)，即從1*784的形式轉(zhuǎn)換為原始的28*28結(jié)構(gòu)。
#因?yàn)橹挥幸粋€(gè)顏色通道，所以最終尺寸為[-1,28,28,1]，其中‘-1'代表樣本數(shù)量不固定，'1'代表顏色通道數(shù)量。
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1,28,28,1])
#定義第一個(gè)卷積層。
#先使用前面函數(shù)進(jìn)行初始化，包括weights和bias。其中[5,5,1,32]代表卷積核尺寸為5**5，1個(gè)顏色通道，32個(gè)不同的卷積核。
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)
#定義第二個(gè)卷積層。
#基本與第一個(gè)卷積層一樣，只是其中的卷積核數(shù)量變成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)
#為了減輕過(guò)擬合，使用一個(gè)Dropout層，其用法是通過(guò)一個(gè)placeholder傳入keep_prob比率來(lái)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)
#定義損失函數(shù)cross_entropy，這里選擇Adam優(yōu)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)
#繼續(xù)定義評(píng)測(cè)準(zhǔn)確率操作。
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
 
#開(kāi)始訓(xùn)練過(guò)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})
#全部訓(xùn)練完畢，在最終的測(cè)試集上進(jìn)行全面測(cè)試，得到整體的分類(lèi)準(zhǔn)確率。
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

#載入數(shù)據(jù)
import cifar10,cifar10_input
import tensorflow as tf
import numpy as np
import time
 
max_steps = 3000 #訓(xùn)練輪數(shù)
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'#下載數(shù)據(jù)默認(rèn)路徑。
 
 
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
 
#計(jì)算CNN的損失。
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])
 
#創(chuàng)建第一個(gè)卷積層。
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)
 
#創(chuàng)建第二個(gè)卷積層。
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')
#使用一個(gè)全連接層，先把第二個(gè)卷積層的輸出結(jié)果flatten,將每個(gè)樣本都變成一維向量。
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)
#下面這個(gè)使用的全連接層，其隱含節(jié)點(diǎn)數(shù)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()
#正式開(kāi)始訓(xùn)練。
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))
  
#評(píng)測(cè)模型在測(cè)試集上的準(zhǔn)確率。
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，將準(zhǔn)確率的評(píng)測(cè)結(jié)果計(jì)算并輸出。
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)