코딩로그
11. Convolutional Neural Networks(실습) 본문
1. mnist-cnn
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
|
import tensorflow as tf
import random
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
tf.set_random_seed(777) # reproducibility
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# hyper parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
# input place holders
X = tf.placeholder(tf.float32, [None, 784])
X_img = tf.reshape(X, [-1, 28, 28, 1]) # img 28x28x1 (black/white)
Y = tf.placeholder(tf.float32, [None, 10])
# L1 ImgIn shape=(?, 28, 28, 1)
W1 = tf.Variable(tf.random_normal([3, 3, 1, 32], stddev=0.01))
# Conv -> (?, 28, 28, 32)
# Pool -> (?, 14, 14, 32)
L1 = tf.nn.conv2d(X_img, W1, strides=[1, 1, 1, 1], padding='SAME')
L1 = tf.nn.relu(L1)
L1 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
'''
Tensor("Conv2D:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("Relu:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("MaxPool:0", shape=(?, 14, 14, 32), dtype=float32)
'''
# L2 ImgIn shape=(?, 14, 14, 32)
W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01))
# Conv ->(?, 14, 14, 64)
# Pool ->(?, 7, 7, 64)
L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME')
L2 = tf.nn.relu(L2)
L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
L2_flat = tf.reshape(L2, [-1, 7 * 7 * 64])
'''
Tensor("Conv2D_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("Relu_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("MaxPool_1:0", shape=(?, 7, 7, 64), dtype=float32)
Tensor("Reshape_1:0", shape=(?, 3136), dtype=float32)
'''
# Final FC 7x7x64 inputs -> 10 outputs
W3 = tf.get_variable("W3", shape=[7 * 7 * 64, 10],
initializer=tf.contrib.layers.xavier_initializer())
b = tf.Variable(tf.random_normal([10]))
logits = tf.matmul(L2_flat, W3) + b
# define cost/loss & optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# initialize
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train my model
print('Learning started. It takes sometime.')
for epoch in range(training_epochs):
avg_cost = 0
total_batch = int(mnist.train.num_examples / batch_size)
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
feed_dict = {X: batch_xs, Y: batch_ys}
c, _ = sess.run([cost, optimizer], feed_dict=feed_dict)
avg_cost += c / total_batch
print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finished!')
# Test model and check accuracy
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Accuracy:', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(
tf.argmax(logits, 1), feed_dict={X: mnist.test.images[r:r + 1]}))
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Epoch: 0001 cost = 0.340291267
Epoch: 0002 cost = 0.090731326
Epoch: 0003 cost = 0.064477619
Epoch: 0004 cost = 0.050683064
Epoch: 0005 cost = 0.041864835
Epoch: 0006 cost = 0.035760704
Epoch: 0007 cost = 0.030572132
Epoch: 0008 cost = 0.026207981
Epoch: 0009 cost = 0.022622454
Epoch: 0010 cost = 0.019055919
Epoch: 0011 cost = 0.017758641
Epoch: 0012 cost = 0.014156652
Epoch: 0013 cost = 0.012397016
Epoch: 0014 cost = 0.010693789
Epoch: 0015 cost = 0.009469977
Learning Finished!
Accuracy: 0.9885
'''
|
cs |
2. mnist-deepcnn
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
|
import tensorflow as tf
import random
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
tf.set_random_seed(777) # reproducibility
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# hyper parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
# dropout (keep_prob) rate 0.7~0.5 on training, but should be 1 for testing
keep_prob = tf.placeholder(tf.float32)
# input place holders
X = tf.placeholder(tf.float32, [None, 784])
X_img = tf.reshape(X, [-1, 28, 28, 1]) # img 28x28x1 (black/white)
Y = tf.placeholder(tf.float32, [None, 10])
# L1 ImgIn shape=(?, 28, 28, 1)
W1 = tf.Variable(tf.random_normal([3, 3, 1, 32], stddev=0.01))
# Conv -> (?, 28, 28, 32)
# Pool -> (?, 14, 14, 32)
L1 = tf.nn.conv2d(X_img, W1, strides=[1, 1, 1, 1], padding='SAME')
L1 = tf.nn.relu(L1)
L1 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
L1 = tf.nn.dropout(L1, keep_prob=keep_prob)
'''
Tensor("Conv2D:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("Relu:0", shape=(?, 28, 28, 32), dtype=float32)
Tensor("MaxPool:0", shape=(?, 14, 14, 32), dtype=float32)
Tensor("dropout/mul:0", shape=(?, 14, 14, 32), dtype=float32)
'''
# L2 ImgIn shape=(?, 14, 14, 32)
W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01))
# Conv ->(?, 14, 14, 64)
# Pool ->(?, 7, 7, 64)
L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME')
L2 = tf.nn.relu(L2)
L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
L2 = tf.nn.dropout(L2, keep_prob=keep_prob)
'''
Tensor("Conv2D_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("Relu_1:0", shape=(?, 14, 14, 64), dtype=float32)
Tensor("MaxPool_1:0", shape=(?, 7, 7, 64), dtype=float32)
Tensor("dropout_1/mul:0", shape=(?, 7, 7, 64), dtype=float32)
'''
# L3 ImgIn shape=(?, 7, 7, 64)
W3 = tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.01))
# Conv ->(?, 7, 7, 128)
# Pool ->(?, 4, 4, 128)
# Reshape ->(?, 4 * 4 * 128) # Flatten them for FC
L3 = tf.nn.conv2d(L2, W3, strides=[1, 1, 1, 1], padding='SAME')
L3 = tf.nn.relu(L3)
L3 = tf.nn.max_pool(L3, ksize=[1, 2, 2, 1], strides=[
1, 2, 2, 1], padding='SAME')
L3 = tf.nn.dropout(L3, keep_prob=keep_prob)
L3_flat = tf.reshape(L3, [-1, 128 * 4 * 4])
'''
Tensor("Conv2D_2:0", shape=(?, 7, 7, 128), dtype=float32)
Tensor("Relu_2:0", shape=(?, 7, 7, 128), dtype=float32)
Tensor("MaxPool_2:0", shape=(?, 4, 4, 128), dtype=float32)
Tensor("dropout_2/mul:0", shape=(?, 4, 4, 128), dtype=float32)
Tensor("Reshape_1:0", shape=(?, 2048), dtype=float32)
'''
# L4 FC 4x4x128 inputs -> 625 outputs
W4 = tf.get_variable("W4", shape=[128 * 4 * 4, 625],
initializer=tf.contrib.layers.xavier_initializer())
b4 = tf.Variable(tf.random_normal([625]))
L4 = tf.nn.relu(tf.matmul(L3_flat, W4) + b4)
L4 = tf.nn.dropout(L4, keep_prob=keep_prob)
'''
Tensor("Relu_3:0", shape=(?, 625), dtype=float32)
Tensor("dropout_3/mul:0", shape=(?, 625), dtype=float32)
'''
# L5 Final FC 625 inputs -> 10 outputs
W5 = tf.get_variable("W5", shape=[625, 10],
initializer=tf.contrib.layers.xavier_initializer())
b5 = tf.Variable(tf.random_normal([10]))
logits = tf.matmul(L4, W5) + b5
'''
Tensor("add_1:0", shape=(?, 10), dtype=float32)
'''
# define cost/loss & optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# initialize
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train my model
print('Learning started. It takes sometime.')
for epoch in range(training_epochs):
avg_cost = 0
total_batch = int(mnist.train.num_examples / batch_size)
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
feed_dict = {X: batch_xs, Y: batch_ys, keep_prob: 0.7}
c, _ = sess.run([cost, optimizer], feed_dict=feed_dict)
avg_cost += c / total_batch
print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finished!')
# Test model and check accuracy
# if you have a OOM error, please refer to lab-11-X-mnist_deep_cnn_low_memory.py
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Accuracy:', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels, keep_prob: 1}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(
tf.argmax(logits, 1), feed_dict={X: mnist.test.images[r:r + 1], keep_prob: 1}))
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Learning stared. It takes sometime.
Epoch: 0001 cost = 0.385748474
Epoch: 0002 cost = 0.092017397
Epoch: 0003 cost = 0.065854684
Epoch: 0004 cost = 0.055604566
Epoch: 0005 cost = 0.045996377
Epoch: 0006 cost = 0.040913645
Epoch: 0007 cost = 0.036924479
Epoch: 0008 cost = 0.032808939
Epoch: 0009 cost = 0.031791007
Epoch: 0010 cost = 0.030224456
Epoch: 0011 cost = 0.026849916
Epoch: 0012 cost = 0.026826763
Epoch: 0013 cost = 0.027188021
Epoch: 0014 cost = 0.023604777
Epoch: 0015 cost = 0.024607201
Learning Finished!
Accuracy: 0.9938
'''
|
cs |
3. mnist-cnn(class)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | import tensorflow as tf # import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data tf.set_random_seed(777) # reproducibility mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # hyper parameters learning_rate = 0.001 training_epochs = 15 batch_size = 100 class Model: def __init__(self, sess, name): self.sess = sess self.name = name self._build_net() def _build_net(self): with tf.variable_scope(self.name): # dropout (keep_prob) rate 0.7~0.5 on training, but should be 1 # for testing self.keep_prob = tf.placeholder(tf.float32) # input place holders self.X = tf.placeholder(tf.float32, [None, 784]) # img 28x28x1 (black/white) X_img = tf.reshape(self.X, [-1, 28, 28, 1]) self.Y = tf.placeholder(tf.float32, [None, 10]) # L1 ImgIn shape=(?, 28, 28, 1) W1 = tf.Variable(tf.random_normal([3, 3, 1, 32], stddev=0.01)) # Conv -> (?, 28, 28, 32) # Pool -> (?, 14, 14, 32) L1 = tf.nn.conv2d(X_img, W1, strides=[1, 1, 1, 1], padding='SAME') L1 = tf.nn.relu(L1) L1 = tf.nn.max_pool(L1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') L1 = tf.nn.dropout(L1, keep_prob=self.keep_prob) ''' Tensor("Conv2D:0", shape=(?, 28, 28, 32), dtype=float32) Tensor("Relu:0", shape=(?, 28, 28, 32), dtype=float32) Tensor("MaxPool:0", shape=(?, 14, 14, 32), dtype=float32) Tensor("dropout/mul:0", shape=(?, 14, 14, 32), dtype=float32) ''' # L2 ImgIn shape=(?, 14, 14, 32) W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01)) # Conv ->(?, 14, 14, 64) # Pool ->(?, 7, 7, 64) L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding='SAME') L2 = tf.nn.relu(L2) L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') L2 = tf.nn.dropout(L2, keep_prob=self.keep_prob) ''' Tensor("Conv2D_1:0", shape=(?, 14, 14, 64), dtype=float32) Tensor("Relu_1:0", shape=(?, 14, 14, 64), dtype=float32) Tensor("MaxPool_1:0", shape=(?, 7, 7, 64), dtype=float32) Tensor("dropout_1/mul:0", shape=(?, 7, 7, 64), dtype=float32) ''' # L3 ImgIn shape=(?, 7, 7, 64) W3 = tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.01)) # Conv ->(?, 7, 7, 128) # Pool ->(?, 4, 4, 128) # Reshape ->(?, 4 * 4 * 128) # Flatten them for FC L3 = tf.nn.conv2d(L2, W3, strides=[1, 1, 1, 1], padding='SAME') L3 = tf.nn.relu(L3) L3 = tf.nn.max_pool(L3, ksize=[1, 2, 2, 1], strides=[ 1, 2, 2, 1], padding='SAME') L3 = tf.nn.dropout(L3, keep_prob=self.keep_prob) L3_flat = tf.reshape(L3, [-1, 128 * 4 * 4]) ''' Tensor("Conv2D_2:0", shape=(?, 7, 7, 128), dtype=float32) Tensor("Relu_2:0", shape=(?, 7, 7, 128), dtype=float32) Tensor("MaxPool_2:0", shape=(?, 4, 4, 128), dtype=float32) Tensor("dropout_2/mul:0", shape=(?, 4, 4, 128), dtype=float32) Tensor("Reshape_1:0", shape=(?, 2048), dtype=float32) ''' # L4 FC 4x4x128 inputs -> 625 outputs W4 = tf.get_variable("W4", shape=[128 * 4 * 4, 625], initializer=tf.contrib.layers.xavier_initializer()) b4 = tf.Variable(tf.random_normal([625])) L4 = tf.nn.relu(tf.matmul(L3_flat, W4) + b4) L4 = tf.nn.dropout(L4, keep_prob=self.keep_prob) ''' Tensor("Relu_3:0", shape=(?, 625), dtype=float32) Tensor("dropout_3/mul:0", shape=(?, 625), dtype=float32) ''' # L5 Final FC 625 inputs -> 10 outputs W5 = tf.get_variable("W5", shape=[625, 10], initializer=tf.contrib.layers.xavier_initializer()) b5 = tf.Variable(tf.random_normal([10])) self.logits = tf.matmul(L4, W5) + b5 ''' Tensor("add_1:0", shape=(?, 10), dtype=float32) ''' # define cost/loss & optimizer self.cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits( logits=self.logits, labels=self.Y)) self.optimizer = tf.train.AdamOptimizer( learning_rate=learning_rate).minimize(self.cost) correct_prediction = tf.equal( tf.argmax(self.logits, 1), tf.argmax(self.Y, 1)) self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) def predict(self, x_test, keep_prop=1.0): return self.sess.run(self.logits, feed_dict={self.X: x_test, self.keep_prob: keep_prop}) def get_accuracy(self, x_test, y_test, keep_prop=1.0): return self.sess.run(self.accuracy, feed_dict={self.X: x_test, self.Y: y_test, self.keep_prob: keep_prop}) def train(self, x_data, y_data, keep_prop=0.7): return self.sess.run([self.cost, self.optimizer], feed_dict={ self.X: x_data, self.Y: y_data, self.keep_prob: keep_prop}) # initialize sess = tf.Session() m1 = Model(sess, "m1") sess.run(tf.global_variables_initializer()) print('Learning Started!') # train my model for epoch in range(training_epochs): avg_cost = 0 total_batch = int(mnist.train.num_examples / batch_size) for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) c, _ = m1.train(batch_xs, batch_ys) avg_cost += c / total_batch print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost)) print('Learning Finished!') # Test model and check accuracy print('Accuracy:', m1.get_accuracy(mnist.test.images, mnist.test.labels)) | cs |
4. mnist-cnn(layers)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | import tensorflow as tf # import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data tf.set_random_seed(777) # reproducibility mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # hyper parameters learning_rate = 0.001 training_epochs = 15 batch_size = 100 class Model: def __init__(self, sess, name): self.sess = sess self.name = name self._build_net() def _build_net(self): with tf.variable_scope(self.name): # dropout (keep_prob) rate 0.7~0.5 on training, but should be 1 # for testing self.training = tf.placeholder(tf.bool) # input place holders self.X = tf.placeholder(tf.float32, [None, 784]) # img 28x28x1 (black/white), Input Layer X_img = tf.reshape(self.X, [-1, 28, 28, 1]) self.Y = tf.placeholder(tf.float32, [None, 10]) # Convolutional Layer #1 conv1 = tf.layers.conv2d(inputs=X_img, filters=32, kernel_size=[3, 3], padding="SAME", activation=tf.nn.relu) # Pooling Layer #1 pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], padding="SAME", strides=2) dropout1 = tf.layers.dropout(inputs=pool1, rate=0.3, training=self.training) # Convolutional Layer #2 and Pooling Layer #2 conv2 = tf.layers.conv2d(inputs=dropout1, filters=64, kernel_size=[3, 3], padding="SAME", activation=tf.nn.relu) pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], padding="SAME", strides=2) dropout2 = tf.layers.dropout(inputs=pool2, rate=0.3, training=self.training) # Convolutional Layer #2 and Pooling Layer #2 conv3 = tf.layers.conv2d(inputs=dropout2, filters=128, kernel_size=[3, 3], padding="same", activation=tf.nn.relu) pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], padding="same", strides=2) dropout3 = tf.layers.dropout(inputs=pool3, rate=0.3, training=self.training) # Dense Layer with Relu flat = tf.reshape(dropout3, [-1, 128 * 4 * 4]) dense4 = tf.layers.dense(inputs=flat, units=625, activation=tf.nn.relu) dropout4 = tf.layers.dropout(inputs=dense4, rate=0.5, training=self.training) # Logits (no activation) Layer: L5 Final FC 625 inputs -> 10 outputs self.logits = tf.layers.dense(inputs=dropout4, units=10) # define cost/loss & optimizer self.cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits( logits=self.logits, labels=self.Y)) self.optimizer = tf.train.AdamOptimizer( learning_rate=learning_rate).minimize(self.cost) correct_prediction = tf.equal( tf.argmax(self.logits, 1), tf.argmax(self.Y, 1)) self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) def predict(self, x_test, training=False): return self.sess.run(self.logits, feed_dict={self.X: x_test, self.training: training}) def get_accuracy(self, x_test, y_test, training=False): return self.sess.run(self.accuracy, feed_dict={self.X: x_test, self.Y: y_test, self.training: training}) def train(self, x_data, y_data, training=True): return self.sess.run([self.cost, self.optimizer], feed_dict={ self.X: x_data, self.Y: y_data, self.training: training}) # initialize sess = tf.Session() m1 = Model(sess, "m1") sess.run(tf.global_variables_initializer()) print('Learning Started!') # train my model for epoch in range(training_epochs): avg_cost = 0 total_batch = int(mnist.train.num_examples / batch_size) for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) c, _ = m1.train(batch_xs, batch_ys) avg_cost += c / total_batch print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost)) print('Learning Finished!') # Test model and check accuracy print('Accuracy:', m1.get_accuracy(mnist.test.images, mnist.test.labels)) | cs |
5. mnist-cnn(ensembles)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data tf.set_random_seed(777) # reproducibility mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # hyper parameters learning_rate = 0.001 training_epochs = 20 batch_size = 100 class Model: def __init__(self, sess, name): self.sess = sess self.name = name self._build_net() def _build_net(self): with tf.variable_scope(self.name): # dropout (keep_prob) rate 0.7~0.5 on training, but should be 1 # for testing self.training = tf.placeholder(tf.bool) # input place holders self.X = tf.placeholder(tf.float32, [None, 784]) # img 28x28x1 (black/white), Input Layer X_img = tf.reshape(self.X, [-1, 28, 28, 1]) self.Y = tf.placeholder(tf.float32, [None, 10]) # Convolutional Layer #1 conv1 = tf.layers.conv2d(inputs=X_img, filters=32, kernel_size=[3, 3], padding="SAME", activation=tf.nn.relu) # Pooling Layer #1 pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], padding="SAME", strides=2) dropout1 = tf.layers.dropout(inputs=pool1, rate=0.3, training=self.training) # Convolutional Layer #2 and Pooling Layer #2 conv2 = tf.layers.conv2d(inputs=dropout1, filters=64, kernel_size=[3, 3], padding="SAME", activation=tf.nn.relu) pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], padding="SAME", strides=2) dropout2 = tf.layers.dropout(inputs=pool2, rate=0.3, training=self.training) # Convolutional Layer #3 and Pooling Layer #3 conv3 = tf.layers.conv2d(inputs=dropout2, filters=128, kernel_size=[3, 3], padding="SAME", activation=tf.nn.relu) pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], padding="SAME", strides=2) dropout3 = tf.layers.dropout(inputs=pool3, rate=0.3, training=self.training) # Dense Layer with Relu flat = tf.reshape(dropout3, [-1, 128 * 4 * 4]) dense4 = tf.layers.dense(inputs=flat, units=625, activation=tf.nn.relu) dropout4 = tf.layers.dropout(inputs=dense4, rate=0.5, training=self.training) # Logits (no activation) Layer: L5 Final FC 625 inputs -> 10 outputs self.logits = tf.layers.dense(inputs=dropout4, units=10) # define cost/loss & optimizer self.cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits( logits=self.logits, labels=self.Y)) self.optimizer = tf.train.AdamOptimizer( learning_rate=learning_rate).minimize(self.cost) correct_prediction = tf.equal( tf.argmax(self.logits, 1), tf.argmax(self.Y, 1)) self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) def predict(self, x_test, training=False): return self.sess.run(self.logits, feed_dict={self.X: x_test, self.training: training}) def get_accuracy(self, x_test, y_test, training=False): return self.sess.run(self.accuracy, feed_dict={self.X: x_test, self.Y: y_test, self.training: training}) def train(self, x_data, y_data, training=True): return self.sess.run([self.cost, self.optimizer], feed_dict={ self.X: x_data, self.Y: y_data, self.training: training}) # initialize sess = tf.Session() models = [] num_models = 2 for m in range(num_models): models.append(Model(sess, "model" + str(m))) sess.run(tf.global_variables_initializer()) print('Learning Started!') # train my model for epoch in range(training_epochs): avg_cost_list = np.zeros(len(models)) total_batch = int(mnist.train.num_examples / batch_size) for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) # train each model for m_idx, m in enumerate(models): c, _ = m.train(batch_xs, batch_ys) avg_cost_list[m_idx] += c / total_batch print('Epoch:', '%04d' % (epoch + 1), 'cost =', avg_cost_list) print('Learning Finished!') # Test model and check accuracy test_size = len(mnist.test.labels) predictions = np.zeros([test_size, 10]) for m_idx, m in enumerate(models): print(m_idx, 'Accuracy:', m.get_accuracy( mnist.test.images, mnist.test.labels)) p = m.predict(mnist.test.images) predictions += p ensemble_correct_prediction = tf.equal( tf.argmax(predictions, 1), tf.argmax(mnist.test.labels, 1)) ensemble_accuracy = tf.reduce_mean( tf.cast(ensemble_correct_prediction, tf.float32)) print('Ensemble accuracy:', sess.run(ensemble_accuracy)) ''' 0 Accuracy: 0.9933 1 Accuracy: 0.9946 2 Accuracy: 0.9934 3 Accuracy: 0.9935 4 Accuracy: 0.9935 5 Accuracy: 0.9949 6 Accuracy: 0.9941 Ensemble accuracy: 0.9952 ''' | cs |
'코딩로그 > 모두를 위한 딥러닝' 카테고리의 다른 글
| 12. Recurrent Neural Network(RNN) (0) | 2020.02.08 |
|---|---|
| 11. Convolutional Neural Networks (0) | 2020.02.01 |
| 10. Neural Network 2: ReLU and 초기값 정하기 (0) | 2020.02.01 |
| 9. Neural Network 1: XOR 문제와 학습방법, Backpropagation (0) | 2020.01.27 |
| 8. 딥러닝의 기본 개념과, 문제, 그리고 해결 (0) | 2020.01.11 |
'코딩로그/모두를 위한 딥러닝' Related Articles
more
