forked from taki0112/SENet-Tensorflow
/
SE_Inception_v4.py
381 lines (270 loc) · 15.8 KB
/
SE_Inception_v4.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
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
import tensorflow as tf
from tflearn.layers.conv import global_avg_pool
from tensorflow.contrib.layers import batch_norm, flatten
from tensorflow.contrib.framework import arg_scope
from cifar10 import *
import numpy as np
weight_decay = 0.0005
momentum = 0.9
init_learning_rate = 0.1
reduction_ratio = 4
batch_size = 128
iteration = 391
# 128 * 391 ~ 50,000
test_iteration = 10
total_epochs = 100
def conv_layer(input, filter, kernel, stride=1, padding='SAME', layer_name="conv"):
with tf.name_scope(layer_name):
network = tf.layers.conv2d(inputs=input, use_bias=True, filters=filter, kernel_size=kernel, strides=stride, padding=padding)
network = Relu(network)
return network
def Fully_connected(x, units=class_num, layer_name='fully_connected') :
with tf.name_scope(layer_name) :
return tf.layers.dense(inputs=x, use_bias=True, units=units)
def Relu(x):
return tf.nn.relu(x)
def Sigmoid(x):
return tf.nn.sigmoid(x)
def Global_Average_Pooling(x):
return global_avg_pool(x, name='Global_avg_pooling')
def Max_pooling(x, pool_size=[3,3], stride=2, padding='VALID') :
return tf.layers.max_pooling2d(inputs=x, pool_size=pool_size, strides=stride, padding=padding)
def Avg_pooling(x, pool_size=[3,3], stride=1, padding='SAME') :
return tf.layers.average_pooling2d(inputs=x, pool_size=pool_size, strides=stride, padding=padding)
def Batch_Normalization(x, training, scope):
with arg_scope([batch_norm],
scope=scope,
updates_collections=None,
decay=0.9,
center=True,
scale=True,
zero_debias_moving_mean=True) :
return tf.cond(training,
lambda : batch_norm(inputs=x, is_training=training, reuse=None),
lambda : batch_norm(inputs=x, is_training=training, reuse=True))
def Concatenation(layers) :
return tf.concat(layers, axis=3)
def Dropout(x, rate, training) :
return tf.layers.dropout(inputs=x, rate=rate, training=training)
def Evaluate(sess):
test_acc = 0.0
test_loss = 0.0
test_pre_index = 0
add = 1000
for it in range(test_iteration):
test_batch_x = test_x[test_pre_index: test_pre_index + add]
test_batch_y = test_y[test_pre_index: test_pre_index + add]
test_pre_index = test_pre_index + add
test_feed_dict = {
x: test_batch_x,
label: test_batch_y,
learning_rate: epoch_learning_rate,
training_flag: False
}
loss_, acc_ = sess.run([cost, accuracy], feed_dict=test_feed_dict)
test_loss += loss_
test_acc += acc_
test_loss /= test_iteration # average loss
test_acc /= test_iteration # average accuracy
summary = tf.Summary(value=[tf.Summary.Value(tag='test_loss', simple_value=test_loss),
tf.Summary.Value(tag='test_accuracy', simple_value=test_acc)])
return test_acc, test_loss, summary
class SE_Inception_v4():
def __init__(self, x, training):
self.training = training
self.model = self.Build_SEnet(x)
def Stem(self, x, scope):
with tf.name_scope(scope) :
x = conv_layer(x, filter=32, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_conv1')
x = conv_layer(x, filter=32, kernel=[3,3], padding='VALID', layer_name=scope+'_conv2')
block_1 = conv_layer(x, filter=64, kernel=[3,3], layer_name=scope+'_conv3')
split_max_x = Max_pooling(block_1)
split_conv_x = conv_layer(block_1, filter=96, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv1')
x = Concatenation([split_max_x,split_conv_x])
split_conv_x1 = conv_layer(x, filter=64, kernel=[1,1], layer_name=scope+'_split_conv2')
split_conv_x1 = conv_layer(split_conv_x1, filter=96, kernel=[3,3], padding='VALID', layer_name=scope+'_split_conv3')
split_conv_x2 = conv_layer(x, filter=64, kernel=[1,1], layer_name=scope+'_split_conv4')
split_conv_x2 = conv_layer(split_conv_x2, filter=64, kernel=[7,1], layer_name=scope+'_split_conv5')
split_conv_x2 = conv_layer(split_conv_x2, filter=64, kernel=[1,7], layer_name=scope+'_split_conv6')
split_conv_x2 = conv_layer(split_conv_x2, filter=96, kernel=[3,3], padding='VALID', layer_name=scope+'_split_conv7')
x = Concatenation([split_conv_x1,split_conv_x2])
split_conv_x = conv_layer(x, filter=192, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv8')
split_max_x = Max_pooling(x)
x = Concatenation([split_conv_x, split_max_x])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Inception_A(self, x, scope):
with tf.name_scope(scope) :
split_conv_x1 = Avg_pooling(x)
split_conv_x1 = conv_layer(split_conv_x1, filter=96, kernel=[1,1], layer_name=scope+'_split_conv1')
split_conv_x2 = conv_layer(x, filter=96, kernel=[1,1], layer_name=scope+'_split_conv2')
split_conv_x3 = conv_layer(x, filter=64, kernel=[1,1], layer_name=scope+'_split_conv3')
split_conv_x3 = conv_layer(split_conv_x3, filter=96, kernel=[3,3], layer_name=scope+'_split_conv4')
split_conv_x4 = conv_layer(x, filter=64, kernel=[1,1], layer_name=scope+'_split_conv5')
split_conv_x4 = conv_layer(split_conv_x4, filter=96, kernel=[3,3], layer_name=scope+'_split_conv6')
split_conv_x4 = conv_layer(split_conv_x4, filter=96, kernel=[3,3], layer_name=scope+'_split_conv7')
x = Concatenation([split_conv_x1, split_conv_x2, split_conv_x3, split_conv_x4])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Inception_B(self, x, scope):
with tf.name_scope(scope) :
init = x
split_conv_x1 = Avg_pooling(x)
split_conv_x1 = conv_layer(split_conv_x1, filter=128, kernel=[1,1], layer_name=scope+'_split_conv1')
split_conv_x2 = conv_layer(x, filter=384, kernel=[1,1], layer_name=scope+'_split_conv2')
split_conv_x3 = conv_layer(x, filter=192, kernel=[1,1], layer_name=scope+'_split_conv3')
split_conv_x3 = conv_layer(split_conv_x3, filter=224, kernel=[1,7], layer_name=scope+'_split_conv4')
split_conv_x3 = conv_layer(split_conv_x3, filter=256, kernel=[1,7], layer_name=scope+'_split_conv5')
split_conv_x4 = conv_layer(x, filter=192, kernel=[1,1], layer_name=scope+'_split_conv6')
split_conv_x4 = conv_layer(split_conv_x4, filter=192, kernel=[1,7], layer_name=scope+'_split_conv7')
split_conv_x4 = conv_layer(split_conv_x4, filter=224, kernel=[7,1], layer_name=scope+'_split_conv8')
split_conv_x4 = conv_layer(split_conv_x4, filter=224, kernel=[1,7], layer_name=scope+'_split_conv9')
split_conv_x4 = conv_layer(split_conv_x4, filter=256, kernel=[7,1], layer_name=scope+'_split_connv10')
x = Concatenation([split_conv_x1, split_conv_x2, split_conv_x3, split_conv_x4])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Inception_C(self, x, scope):
with tf.name_scope(scope) :
split_conv_x1 = Avg_pooling(x)
split_conv_x1 = conv_layer(split_conv_x1, filter=256, kernel=[1,1], layer_name=scope+'_split_conv1')
split_conv_x2 = conv_layer(x, filter=256, kernel=[1,1], layer_name=scope+'_split_conv2')
split_conv_x3 = conv_layer(x, filter=384, kernel=[1,1], layer_name=scope+'_split_conv3')
split_conv_x3_1 = conv_layer(split_conv_x3, filter=256, kernel=[1,3], layer_name=scope+'_split_conv4')
split_conv_x3_2 = conv_layer(split_conv_x3, filter=256, kernel=[3,1], layer_name=scope+'_split_conv5')
split_conv_x4 = conv_layer(x, filter=384, kernel=[1,1], layer_name=scope+'_split_conv6')
split_conv_x4 = conv_layer(split_conv_x4, filter=448, kernel=[1,3], layer_name=scope+'_split_conv7')
split_conv_x4 = conv_layer(split_conv_x4, filter=512, kernel=[3,1], layer_name=scope+'_split_conv8')
split_conv_x4_1 = conv_layer(split_conv_x4, filter=256, kernel=[3,1], layer_name=scope+'_split_conv9')
split_conv_x4_2 = conv_layer(split_conv_x4, filter=256, kernel=[1,3], layer_name=scope+'_split_conv10')
x = Concatenation([split_conv_x1, split_conv_x2, split_conv_x3_1, split_conv_x3_2, split_conv_x4_1, split_conv_x4_2])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Reduction_A(self, x, scope):
with tf.name_scope(scope) :
k = 256
l = 256
m = 384
n = 384
split_max_x = Max_pooling(x)
split_conv_x1 = conv_layer(x, filter=n, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv1')
split_conv_x2 = conv_layer(x, filter=k, kernel=[1,1], layer_name=scope+'_split_conv2')
split_conv_x2 = conv_layer(split_conv_x2, filter=l, kernel=[3,3], layer_name=scope+'_split_conv3')
split_conv_x2 = conv_layer(split_conv_x2, filter=m, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv4')
x = Concatenation([split_max_x, split_conv_x1, split_conv_x2])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Reduction_B(self, x, scope):
with tf.name_scope(scope) :
split_max_x = Max_pooling(x)
split_conv_x1 = conv_layer(x, filter=256, kernel=[1,1], layer_name=scope+'_split_conv1')
split_conv_x1 = conv_layer(split_conv_x1, filter=384, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv2')
split_conv_x2 = conv_layer(x, filter=256, kernel=[1,1], layer_name=scope+'_split_conv3')
split_conv_x2 = conv_layer(split_conv_x2, filter=288, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv4')
split_conv_x3 = conv_layer(x, filter=256, kernel=[1,1], layer_name=scope+'_split_conv5')
split_conv_x3 = conv_layer(split_conv_x3, filter=288, kernel=[3,3], layer_name=scope+'_split_conv6')
split_conv_x3 = conv_layer(split_conv_x3, filter=320, kernel=[3,3], stride=2, padding='VALID', layer_name=scope+'_split_conv7')
x = Concatenation([split_max_x, split_conv_x1, split_conv_x2, split_conv_x3])
x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
x = Relu(x)
return x
def Squeeze_excitation_layer(self, input_x, out_dim, ratio, layer_name):
with tf.name_scope(layer_name) :
squeeze = Global_Average_Pooling(input_x)
excitation = Fully_connected(squeeze, units=out_dim / ratio, layer_name=layer_name+'_fully_connected1')
excitation = Relu(excitation)
excitation = Fully_connected(excitation, units=out_dim, layer_name=layer_name+'_fully_connected2')
excitation = Sigmoid(excitation)
excitation = tf.reshape(excitation, [-1,1,1,out_dim])
scale = input_x * excitation
return scale
def Build_SEnet(self, input_x):
input_x = tf.pad(input_x, [[0, 0], [32, 32], [32, 32], [0, 0]])
# size 32 -> 96
# only cifar10 architecture
x = self.Stem(input_x, scope='stem')
for i in range(4) :
x = self.Inception_A(x, scope='Inception_A'+str(i))
channel = int(np.shape(x)[-1])
x = self.Squeeze_excitation_layer(x, out_dim=channel, ratio=reduction_ratio, layer_name='SE_A'+str(i))
x = self.Reduction_A(x, scope='Reduction_A')
for i in range(7) :
x = self.Inception_B(x, scope='Inception_B'+str(i))
channel = int(np.shape(x)[-1])
x = self.Squeeze_excitation_layer(x, out_dim=channel, ratio=reduction_ratio, layer_name='SE_B'+str(i))
x = self.Reduction_B(x, scope='Reduction_B')
for i in range(3) :
x = self.Inception_C(x, scope='Inception_C'+str(i))
channel = int(np.shape(x)[-1])
x = self.Squeeze_excitation_layer(x, out_dim=channel, ratio=reduction_ratio, layer_name='SE_C'+str(i))
x = Global_Average_Pooling(x)
x = Dropout(x, rate=0.2, training=self.training)
x = flatten(x)
x = Fully_connected(x, layer_name='final_fully_connected')
return x
train_x, train_y, test_x, test_y = prepare_data()
train_x, test_x = color_preprocessing(train_x, test_x)
# image_size = 32, img_channels = 3, class_num = 10 in cifar10
x = tf.placeholder(tf.float32, shape=[None, image_size, image_size, img_channels])
label = tf.placeholder(tf.float32, shape=[None, class_num])
training_flag = tf.placeholder(tf.bool)
learning_rate = tf.placeholder(tf.float32, name='learning_rate')
logits = SE_Inception_v4(x, training=training_flag).model
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=label, logits=logits))
l2_loss = tf.add_n([tf.nn.l2_loss(var) for var in tf.trainable_variables()])
optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate, momentum=momentum, use_nesterov=True)
train = optimizer.minimize(cost + l2_loss * weight_decay)
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(label, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state('./model')
if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path):
saver.restore(sess, ckpt.model_checkpoint_path)
else:
sess.run(tf.global_variables_initializer())
summary_writer = tf.summary.FileWriter('./logs', sess.graph)
epoch_learning_rate = init_learning_rate
for epoch in range(1, total_epochs + 1):
if epoch % 30 == 0 :
epoch_learning_rate = epoch_learning_rate / 10
pre_index = 0
train_acc = 0.0
train_loss = 0.0
for step in range(1, iteration + 1):
if pre_index + batch_size < 50000:
batch_x = train_x[pre_index: pre_index + batch_size]
batch_y = train_y[pre_index: pre_index + batch_size]
else:
batch_x = train_x[pre_index:]
batch_y = train_y[pre_index:]
batch_x = data_augmentation(batch_x)
train_feed_dict = {
x: batch_x,
label: batch_y,
learning_rate: epoch_learning_rate,
training_flag: True
}
_, batch_loss = sess.run([train, cost], feed_dict=train_feed_dict)
batch_acc = accuracy.eval(feed_dict=train_feed_dict)
train_loss += batch_loss
train_acc += batch_acc
pre_index += batch_size
train_loss /= iteration # average loss
train_acc /= iteration # average accuracy
train_summary = tf.Summary(value=[tf.Summary.Value(tag='train_loss', simple_value=train_loss),
tf.Summary.Value(tag='train_accuracy', simple_value=train_acc)])
test_acc, test_loss, test_summary = Evaluate(sess)
summary_writer.add_summary(summary=train_summary, global_step=epoch)
summary_writer.add_summary(summary=test_summary, global_step=epoch)
summary_writer.flush()
line = "epoch: %d/%d, train_loss: %.4f, train_acc: %.4f, test_loss: %.4f, test_acc: %.4f \n" % (
epoch, total_epochs, train_loss, train_acc, test_loss, test_acc)
print(line)
with open('logs.txt', 'a') as f:
f.write(line)
saver.save(sess=sess, save_path='./model/Inception_v4.ckpt')