Deep MNIST for Experts - 전체 코드 (1)

In [1]:

import tensorflow as tf
sess = tf.InteractiveSession()

In [ ]:

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)

In [3]:

x = tf.placeholder(tf.float32, [None, 784])

In [4]:

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

In [5]:

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')

In [6]:

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

In [7]:

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

In [8]:

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

In [9]:

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)

In [10]:

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)

In [11]:

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

In [12]:

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
 
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

In [13]:

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

In [14]:

y_ = tf.placeholder(tf.float32, [None, 10])

In [15]:

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))

In [16]:

train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

In [17]:

correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))

In [18]:

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

In [19]:

init = tf.initialize_all_variables().run()

In [20]:

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

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

In [21]:

# Summary
summary_writer = tf.train.SummaryWriter('/tmp/tf_logs/mnist_for_expert', graph=sess.graph)

In [22]:

for i in range(1000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(session=sess, 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})

step 0, training accuracy 0.16
step 100, training accuracy 0.82
step 200, training accuracy 0.92
step 300, training accuracy 0.86
step 400, training accuracy 1
step 500, training accuracy 0.94
step 600, training accuracy 1
step 700, training accuracy 0.98
step 800, training accuracy 0.86
step 900, training accuracy 1

In [23]:

for i in xrange(10):
    testSet = mnist.test.next_batch(50)
    print("test accuracy %g"%accuracy.eval(feed_dict={ x: testSet[0], y_: testSet[1], keep_prob: 1.0}))

test accuracy 0.98
test accuracy 1
test accuracy 1
test accuracy 1
test accuracy 0.98
test accuracy 0.98
test accuracy 0.94
test accuracy 0.96
test accuracy 0.92
test accuracy 0.98