-
Notifications
You must be signed in to change notification settings - Fork 6
/
inception_v3.py
327 lines (270 loc) · 12.7 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
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
# -*- coding: utf-8 -*-
'''Inception V3 model for Keras.
Note that the ImageNet weights provided are from a model that had not fully converged.
Inception v3 should be able to reach 6.9% top-5 error, but our model
only gets to 7.8% (same as a fully-converged ResNet 50).
For comparison, VGG16 only gets to 9.9%, quite a bit worse.
Also, do note that the input image format for this model is different than for
other models (299x299 instead of 224x224), and that the input preprocessing function
is also different.
# Reference:
- [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
'''
from __future__ import print_function
import numpy as np
import warnings
from keras.models import Model
from keras.layers import Flatten, Dense, Input, BatchNormalization, merge
from keras.layers import Convolution2D, MaxPooling2D, AveragePooling2D
from keras.preprocessing import image
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from keras import backend as K
from imagenet_utils import decode_predictions
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_th_dim_ordering_th_kernels.h5'
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_tf_dim_ordering_tf_kernels.h5'
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_th_dim_ordering_th_kernels_notop.h5'
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5'
def conv2d_bn(x, nb_filter, nb_row, nb_col,
border_mode='same', subsample=(1, 1),
name=None):
'''Utility function to apply conv + BN.
'''
if name is not None:
bn_name = name + '_bn'
conv_name = name + '_conv'
else:
bn_name = None
conv_name = None
if K.image_dim_ordering() == 'th':
bn_axis = 1
else:
bn_axis = 3
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 InceptionV3(include_top=True, weights='imagenet',
input_tensor=None):
'''Instantiate the Inception v3 architecture,
optionally loading weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_dim_ordering="tf"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
# Returns
A Keras model instance.
'''
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
# Determine proper input shape
if K.image_dim_ordering() == 'th':
if include_top:
input_shape = (3, 299, 299)
else:
input_shape = (3, None, None)
else:
if include_top:
input_shape = (299, 299, 3)
else:
input_shape = (None, None, 3)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor)
else:
img_input = input_tensor
if K.image_dim_ordering() == 'th':
channel_axis = 1
else:
channel_axis = 3
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))
if include_top:
# Classification block
x = AveragePooling2D((8, 8), strides=(8, 8), name='avg_pool')(x)
x = Flatten(name='flatten')(x)
x = Dense(1000, activation='softmax', name='predictions')(x)
# Create model
model = Model(img_input, x)
# load weights
if weights == 'imagenet':
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='b3baf3070cc4bf476d43a2ea61b0ca5f')
else:
weights_path = get_file('inception_v3_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='79aaa90ab4372b4593ba3df64e142f05')
model.load_weights(weights_path)
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image dimension ordering convention '
'(`image_dim_ordering="th"`). '
'For best performance, set '
'`image_dim_ordering="tf"` in '
'your Keras config '
'at ~/.keras/keras.json.')
convert_all_kernels_in_model(model)
else:
if include_top:
weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='fe114b3ff2ea4bf891e9353d1bbfb32f')
else:
weights_path = get_file('inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='2f3609166de1d967d1a481094754f691')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def preprocess_input(x):
x /= 255.
x -= 0.5
x *= 2.
return x
if __name__ == '__main__':
model = InceptionV3(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))