/
vgg16.py
243 lines (211 loc) · 9.34 KB
/
vgg16.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
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
# pylint: disable=invalid-name
"""VGG16 model for Keras.
Reference paper:
- [Very Deep Convolutional Networks for Large-Scale Image Recognition]
(https://arxiv.org/abs/1409.1556) (ICLR 2015)
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from tensorflow.python.keras import backend
from tensorflow.python.keras.applications import imagenet_utils
from tensorflow.python.keras.engine import training
from tensorflow.python.keras.layers import VersionAwareLayers
from tensorflow.python.keras.utils import data_utils
from tensorflow.python.keras.utils import layer_utils
from tensorflow.python.lib.io import file_io
from tensorflow.python.util.tf_export import keras_export
WEIGHTS_PATH = ('https://storage.googleapis.com/tensorflow/keras-applications/'
'vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5')
WEIGHTS_PATH_NO_TOP = ('https://storage.googleapis.com/tensorflow/'
'keras-applications/vgg16/'
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5')
layers = VersionAwareLayers()
@keras_export('keras.applications.vgg16.VGG16', 'keras.applications.VGG16')
def VGG16(
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000,
classifier_activation='softmax'):
"""Instantiates the VGG16 model.
Reference paper:
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](
https://arxiv.org/abs/1409.1556) (ICLR 2015)
By default, it loads weights pre-trained on ImageNet. Check 'weights' for
other options.
This model can be built both with 'channels_first' data format
(channels, height, width) or 'channels_last' data format
(height, width, channels).
The default input size for this model is 224x224.
Caution: Be sure to properly pre-process your inputs to the application.
Please see `applications.vgg16.preprocess_input` for an example.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor
(i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)`
(with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 input channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional block.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional block, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
classifier_activation: A `str` or callable. The activation function to use
on the "top" layer. Ignored unless `include_top=True`. Set
`classifier_activation=None` to return the logits of the "top" layer.
Returns:
A `keras.Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
ValueError: if `classifier_activation` is not `softmax` or `None` when
using a pretrained top layer.
"""
if not (weights in {'imagenet', None} or file_io.file_exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = imagenet_utils.obtain_input_shape(
input_shape,
default_size=224,
min_size=32,
data_format=backend.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = layers.Input(shape=input_shape)
else:
if not backend.is_keras_tensor(input_tensor):
img_input = layers.Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = layers.Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
img_input)
x = layers.Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = layers.Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = layers.Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = layers.Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = layers.Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = layers.Flatten(name='flatten')(x)
x = layers.Dense(4096, activation='relu', name='fc1')(x)
x = layers.Dense(4096, activation='relu', name='fc2')(x)
imagenet_utils.validate_activation(classifier_activation, weights)
x = layers.Dense(classes, activation=classifier_activation,
name='predictions')(x)
else:
if pooling == 'avg':
x = layers.GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = layers.GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = training.Model(inputs, x, name='vgg16')
# Load weights.
if weights == 'imagenet':
if include_top:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='64373286793e3c8b2b4e3219cbf3544b')
else:
weights_path = data_utils.get_file(
'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='6d6bbae143d832006294945121d1f1fc')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
@keras_export('keras.applications.vgg16.preprocess_input')
def preprocess_input(x, data_format=None):
return imagenet_utils.preprocess_input(
x, data_format=data_format, mode='caffe')
@keras_export('keras.applications.vgg16.decode_predictions')
def decode_predictions(preds, top=5):
return imagenet_utils.decode_predictions(preds, top=top)
preprocess_input.__doc__ = imagenet_utils.PREPROCESS_INPUT_DOC.format(
mode='',
ret=imagenet_utils.PREPROCESS_INPUT_RET_DOC_CAFFE,
error=imagenet_utils.PREPROCESS_INPUT_ERROR_DOC)
decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__