-
Notifications
You must be signed in to change notification settings - Fork 1
/
inception_v3.py
292 lines (226 loc) · 10.9 KB
/
inception_v3.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
# -*- coding: utf-8 -*-
from keras.optimizers import SGD
from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, Flatten, merge
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.preprocessing.image import ImageDataGenerator
from keras import backend as K
K.set_image_dim_ordering('th')
from keras.callbacks import EarlyStopping,ModelCheckpoint
import time
def conv2d_bn(x, nb_filter, nb_row, nb_col,
border_mode='same', subsample=(1, 1),
name=None):
"""
a function that apply conv + BN for Inception V3.
"""
if name is not None:
bn_name = name + '_bn'
conv_name = name + '_conv'
else:
bn_name = None
conv_name = None
bn_axis = 1
x = Convolution2D(nb_filter, nb_row, nb_col,
subsample=subsample,
activation='relu',
border_mode=border_mode,
name=conv_name)(x)
x = BatchNormalization(axis=bn_axis, name=bn_name)(x)
return x
def inception_v3_model(img_rows, img_cols, channel=1, num_classes=None):
"""
Inception-V3 Model for Keras
Parameters:
img_rows, img_cols
channel - 1 for grayscale, 3 for color
num_classes - number of class labels for our classification task
"""
channel_axis = 1
img_input = Input(shape=(channel, img_rows, img_cols))
x = conv2d_bn(img_input, 32, 3, 3, subsample=(2, 2), border_mode='valid')
x = conv2d_bn(x, 32, 3, 3, border_mode='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, border_mode='valid')
x = conv2d_bn(x, 192, 3, 3, border_mode='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
for i in range(3):
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), border_mode='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = merge([branch1x1, branch5x5, branch3x3dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed' + str(i))
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, subsample=(2, 2), border_mode='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3,
subsample=(2, 2), border_mode='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = merge([branch3x3, branch3x3dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), border_mode='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), border_mode='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = merge([branch1x1, branch7x7, branch7x7dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
subsample=(2, 2), border_mode='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 3, 3,
subsample=(2, 2), border_mode='valid')
branch_pool = AveragePooling2D((3, 3), strides=(2, 2))(x)
x = merge([branch3x3, branch7x7x3, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = merge([branch3x3_1, branch3x3_2],
mode='concat', concat_axis=channel_axis,
name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = merge([branch3x3dbl_1, branch3x3dbl_2],
mode='concat', concat_axis=channel_axis)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), border_mode='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = merge([branch1x1, branch3x3, branch3x3dbl, branch_pool],
mode='concat', concat_axis=channel_axis,
name='mixed' + str(9 + i))
# Fully Connected Softmax Layer
x_fc = AveragePooling2D((8, 8), strides=(8, 8), name='avg_pool')(x)
x_fc = Flatten(name='flatten')(x_fc)
x_fc = Dense(1000, activation='softmax', name='predictions')(x_fc)
# Create model
model = Model(img_input, x_fc)
# Load ImageNet pre-trained data
model.load_weights('/imagenet_models_weights/inception_v3_weights_th_dim_ordering_th_kernels.h5')
# make all layers untrainable
for layer in model.layers:
layer.trainble = False
# Truncate and replace softmax layer for transfer learning
# Cannot use model.layers.pop() since model is not of Sequential() type
# The method below works since pre-trained weights are stored in layers but not in the model
x_newfc = AveragePooling2D((8, 8), strides=(8, 8), name='avg_pool')(x)
x_newfc = Flatten(name='flatten')(x_newfc)
x_newfc = Dense(num_classes, activation='sigmoid', name='predictions')(x_newfc)
# Create another model with our customized softmax
model = Model(img_input, x_newfc)
for layer in model.layers[:-3]:
layer.trainble = True
# Learning rate is changed to 0.001
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='binary_crossentropy', metrics=['accuracy'])
# model.summary()
return model
if __name__ == '__main__':
img_rows, img_cols = 299, 299 # Resolution of inputs
channel = 3
num_classes = 1
batch_size = 32
nb_epoch = 100
# specify the cat-dog directories
train_data_dir = ""
valid_data_dir = ""
# Load inception model
model = inception_v3_model(img_rows, img_cols, channel, num_classes)
# uncomment to print layers index and names
# for i,layer in enumerate(model.layers):
# print(i,layer)
# uncomment to print layers and training status
# for layer in model.layers:
# print(layer,layer.trainable)
#
datagen = ImageDataGenerator(rescale=1./255)
train_generator = datagen.flow_from_directory(directory=train_data_dir,
target_size=(img_rows,img_cols),
class_mode='binary',
batch_size=batch_size
)
validation_generator = datagen.flow_from_directory(directory=valid_data_dir,
target_size=(img_rows,img_cols),
class_mode='binary',
batch_size=batch_size)
train_images_num = len(train_generator.filenames)
valid_images_num = len(validation_generator.filenames)
file_path = "output_dir/inceptionv3.h5"
early_stopping = EarlyStopping(monitor='val_acc',patience=2,verbose=0,mode='auto')
checkpoint = ModelCheckpoint(file_path,monitor='val_acc',verbose=1,save_best_only=True,mode='max')
callbacks_list = [checkpoint,early_stopping]
# Start Fine-tuning
start = time.time()
model_history = model.fit_generator(generator=train_generator,
steps_per_epoch=train_images_num//batch_size,
epochs=nb_epoch,
callbacks = callbacks_list,
validation_data=validation_generator,
validation_steps=valid_images_num//batch_size)
end = time.time()
training_time = end - start
print(training_time)
# i used early stopping to save the best weights
#model.save_weights("/output_dir/inceptionv3_finetuning.h5")
print("all weights are saved properly")