forked from fchollet/deep-learning-models
-
Notifications
You must be signed in to change notification settings - Fork 0
/
resnet50.py
254 lines (212 loc) · 10.9 KB
/
resnet50.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
# -*- coding: utf-8 -*-
'''ResNet50 model for Keras.
# Reference:
- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
Adapted from code contributed by BigMoyan.
'''
from __future__ import print_function
import numpy as np
import warnings
from keras.layers import merge, Input
from keras.layers import Dense, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D, ZeroPadding2D, AveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from imagenet_utils import decode_predictions, preprocess_input
TH_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_th_dim_ordering_th_kernels.h5'
TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
TH_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_th_dim_ordering_th_kernels_notop.h5'
TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
def identity_block(input_tensor, kernel_size, filters, stage, block, bn_mode=0):
'''The identity_block is the block that has no conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
bn_mode: default 0, the mode for BatchNormalization
'''
nb_filter1, nb_filter2, nb_filter3 = filters
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Convolution2D(nb_filter1, 1, 1, name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a', mode=bn_mode)(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter2, kernel_size, kernel_size,
border_mode='same', name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b', mode=bn_mode)(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c', mode=bn_mode)(x)
x = merge([x, input_tensor], mode='sum')
x = Activation('relu')(x)
return x
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2), bn_mode=0):
'''conv_block is the block that has a conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
bn_mode: default 0, the mode for BatchNormalization
Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
And the shortcut should have subsample=(2,2) as well
'''
nb_filter1, nb_filter2, nb_filter3 = filters
if K.image_dim_ordering() == 'tf':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Convolution2D(nb_filter1, 1, 1, subsample=strides,
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a', mode=bn_mode)(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter2, kernel_size, kernel_size, border_mode='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b', mode=bn_mode)(x)
x = Activation('relu')(x)
x = Convolution2D(nb_filter3, 1, 1, name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c', mode=bn_mode)(x)
shortcut = Convolution2D(nb_filter3, 1, 1, subsample=strides,
name=conv_name_base + '1')(input_tensor)
shortcut = BatchNormalization(axis=bn_axis, name=bn_name_base + '1', mode=bn_mode)(shortcut)
x = merge([x, shortcut], mode='sum')
x = Activation('relu')(x)
return x
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, bn_mode = 0):
'''Instantiate the ResNet50 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.
# 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. xput of `layers.Input()`)
to use as image input for the model.
bn_mode: default 0, the mode for BatchNormalization
# 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, 224, 224)
else:
input_shape = (3, None, None)
else:
if include_top:
input_shape = (224, 224, 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() == 'tf':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Convolution2D(64, 7, 7, subsample=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1', mode=bn_mode)(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), bn_mode=bn_mode)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', bn_mode=bn_mode)
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', bn_mode=bn_mode)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', bn_mode=bn_mode)
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e', bn_mode=bn_mode)
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f', bn_mode=bn_mode)
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', bn_mode=bn_mode)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', bn_mode=bn_mode)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', bn_mode=bn_mode)
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(1000, activation='softmax', name='fc1000')(x)
model = Model(img_input, x)
# load weights
if weights == 'imagenet':
print('K.image_dim_ordering:', K.image_dim_ordering())
if K.image_dim_ordering() == 'th':
if include_top:
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels.h5',
TH_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='1c1f8f5b0c8ee28fe9d950625a230e1c')
else:
weights_path = get_file('resnet50_weights_th_dim_ordering_th_kernels_notop.h5',
TH_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='f64f049c92468c9affcd44b0976cdafe')
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('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
if __name__ == '__main__':
model = ResNet50(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print('Input image shape:', x.shape)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))