TensorFlow 實戰(zhàn)之實現(xiàn)卷積神經(jīng)網(wǎng)絡的實例講解

#載入MNIST數(shù)據(jù)集，創(chuàng)建默認的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)，以便重復使用創(chuàng)建權重、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') 
 
#在設計卷積神經(jīng)網(wǎng)絡結構之前，定義輸入的placeholder，x是特征，y_是真實Label。
#由于卷積神經(jīng)網(wǎng)絡會使用到空間結構信息，所以，需要將1D的輸入向量轉為2D圖片結構，即從1*784的形式轉換為原始的28*28結構。
#因為只有一個顏色通道，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])
#定義第一個卷積層。
#先使用前面函數(shù)進行初始化，包括weights和bias。其中[5,5,1,32]代表卷積核尺寸為5**5，1個顏色通道，32個不同的卷積核。
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)
#定義第二個卷積層。
#基本與第一個卷積層一樣，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)
#為了減輕過擬合，使用一個Dropout層，其用法是通過一個placeholder傳入keep_prob比率來控制。
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)定義評測準確率操作。
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
 
#開始訓練過程。
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})
#全部訓練完畢，在最終的測試集上進行全面測試，得到整體的分類準確率。
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 #訓練輪數(shù)
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'#下載數(shù)據(jù)默認路徑。
 
 
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')
#使用一個全連接層，先把第二個卷積層的輸出結果flatten,將每個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)
#下面這個使用的全連接層，其隱含節(jié)點數(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()
#正式開始訓練。
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))
  
#評測模型在測試集上的準確率。
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，將準確率的評測結果計算并輸出。
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)