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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
| from __future__ import print_function
import shutil
import os.path
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
EXPORT_DIR = './model'
if os.path.exists(EXPORT_DIR):
shutil.rmtree(EXPORT_DIR)
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 128
display_step = 10
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create Model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7 * 7 * 64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: 1.})
print("Iter " + str(step * batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print("Optimization Finished!")
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))
WC1 = weights['wc1'].eval(sess)
BC1 = biases['bc1'].eval(sess)
WC2 = weights['wc2'].eval(sess)
BC2 = biases['bc2'].eval(sess)
WD1 = weights['wd1'].eval(sess)
BD1 = biases['bd1'].eval(sess)
W_OUT = weights['out'].eval(sess)
B_OUT = biases['out'].eval(sess)
# Create new graph for exporting
g = tf.Graph()
with g.as_default():
x_2 = tf.placeholder("float", shape=[None, 784], name="input")
WC1 = tf.constant(WC1, name="WC1")
BC1 = tf.constant(BC1, name="BC1")
x_image = tf.reshape(x_2, [-1, 28, 28, 1])
CONV1 = conv2d(x_image, WC1, BC1)
MAXPOOL1 = maxpool2d(CONV1, k=2)
WC2 = tf.constant(WC2, name="WC2")
BC2 = tf.constant(BC2, name="BC2")
CONV2 = conv2d(MAXPOOL1, WC2, BC2)
MAXPOOL2 = maxpool2d(CONV2, k=2)
WD1 = tf.constant(WD1, name="WD1")
BD1 = tf.constant(BD1, name="BD1")
FC1 = tf.reshape(MAXPOOL2, [-1, WD1.get_shape().as_list()[0]])
FC1 = tf.add(tf.matmul(FC1, WD1), BD1)
FC1 = tf.nn.relu(FC1)
W_OUT = tf.constant(W_OUT, name="W_OUT")
B_OUT = tf.constant(B_OUT, name="B_OUT")
# skipped dropout for exported graph as there
# is no need for already calculated weights
OUTPUT = tf.nn.softmax(tf.matmul(FC1, W_OUT) + B_OUT, name="output")
sess = tf.Session()
init = tf.initialize_all_variables()
sess.run(init)
graph_def = g.as_graph_def()
tf.train.write_graph(graph_def, EXPORT_DIR, 'mnist_model_graph.pb', as_text=False)
# Test trained model
y_train = tf.placeholder("float", [None, 10])
correct_prediction = tf.equal(tf.argmax(OUTPUT, 1), tf.argmax(y_train, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("check accuracy %g" % accuracy.eval(
{x_2: mnist.test.images, y_train: mnist.test.labels}, sess))
|
