-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathconv_net.py
230 lines (183 loc) · 7.34 KB
/
conv_net.py
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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
'''
A Convolutional Network implementation example using TensorFlow library.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''
import tensorflow as tf
# 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 conv2d_tanh(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.tanh(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, height, width, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, height, width, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
conv1 = tf.nn.dropout(conv1, dropout)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
conv2 = tf.nn.dropout(conv2, dropout)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# Max Pooling (down-sampling)
conv3 = maxpool2d(conv3, k=2)
conv3 = tf.nn.dropout(conv3, dropout)
# Convolution Layer
conv4 = conv2d(conv3, weights['wc4'], biases['bc4'])
# Max Pooling (not down-sampling)
conv4 = maxpool2d(conv4, k=1)
conv4 = tf.nn.dropout(conv4, dropout)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv4, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.tanh(fc1) # changed to tanh for decoder!
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return conv4, out
def conv_net3(x, height, width, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, height, width, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
conv1 = tf.nn.dropout(conv1, dropout)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
conv2 = tf.nn.dropout(conv2, dropout)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# Max Pooling (down-sampling)
conv3 = maxpool2d(conv3, k=1)
conv3 = tf.nn.dropout(conv3, dropout)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv3, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.tanh(fc1) # changed to tanh for decoder!
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return conv3, out
def conv_net4(x, height, width, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, height, width, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
conv1 = tf.nn.dropout(conv1, dropout)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
conv2 = tf.nn.dropout(conv2, dropout)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# Max Pooling (down-sampling)
conv3 = maxpool2d(conv3, k=1)
conv3 = tf.nn.dropout(conv3, dropout)
# Convolution Layer
conv4 = conv2d(conv3, weights['wc4'], biases['bc4'])
# Max Pooling (down-sampling)
conv4 = maxpool2d(conv4, k=1)
conv4 = tf.nn.dropout(conv4, dropout)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv4, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.tanh(fc1) # changed to tanh for decoder!
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return conv4, out
def conv_net5(x, height, width, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, height, width, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=1)
conv1 = tf.nn.dropout(conv1, dropout)
# Convolution Layer
conv2 = conv2d_tanh(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
conv2 = tf.nn.dropout(conv2, dropout)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# Max Pooling (down-sampling)
conv3 = maxpool2d(conv3, k=1)
conv3 = tf.nn.dropout(conv3, dropout)
# Convolution Layer
conv4 = conv2d_tanh(conv3, weights['wc4'], biases['bc4'])
# Max Pooling (down-sampling)
conv4 = maxpool2d(conv4, k=2)
conv4 = tf.nn.dropout(conv4, dropout)
# Convolution Layer
conv5 = conv2d(conv4, weights['wc5'], biases['bc5'])
# Max Pooling (down-sampling)
conv5 = maxpool2d(conv5, k=1)
conv5 = tf.nn.dropout(conv5, dropout)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv5, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.tanh(fc1) # changed to tanh for decoder!
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return conv4, 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))
"""