forked from GKalliatakis/Keras-VGG16-places365
-
Notifications
You must be signed in to change notification settings - Fork 0
/
vgg16_hybrid_places_1365.py
322 lines (242 loc) · 11.8 KB
/
vgg16_hybrid_places_1365.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
# -*- coding: utf-8 -*-
'''VGG-ImageNetPlaces365-hybrid model for Keras
1000 classes from the ImageNet and the 365 classes from
the Places365-Standard were merged to train a VGG16-based model (Hybrid1365-VGG)
# Reference:
- [Places: A 10 million Image Database for Scene Recognition](http://places2.csail.mit.edu/PAMI_places.pdf)
'''
from __future__ import division, print_function
import os
import warnings
from keras import backend as K
from keras.layers import Input
from keras.layers.core import Activation, Dense, Flatten
from keras.layers.pooling import MaxPooling2D
from keras.models import Model
from keras.layers import Conv2D
from keras.regularizers import l2
from keras.layers.core import Dropout
from keras.layers import GlobalAveragePooling2D
from keras.layers import GlobalMaxPooling2D
from keras_applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs
from keras.utils.data_utils import get_file
from keras.utils import layer_utils
WEIGHTS_PATH = 'https://github.com/GKalliatakis/Keras-VGG16-places365/releases/download/v1.0/vgg16-hybrid1365_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/GKalliatakis/Keras-VGG16-places365/releases/download/v1.0/vgg16-hybrid1365_weights_tf_dim_ordering_tf_kernels_notop.h5'
def VGG16_Hybrid_1365(include_top=True, weights='places',
input_tensor=None, input_shape=None,
pooling=None,
classes=1365):
"""Instantiates the VGG-ImageNetPlaces365-hybrid architecture.
Optionally loads weights pre-trained
on Places. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
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),
'places' (pre-training on Places),
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, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
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 layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, 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.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`, or invalid input shape
"""
if not (weights in {'places', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `places` '
'(pre-training on Places), '
'or the path to the weights file to be loaded.')
if weights == 'places' and include_top and classes != 1365:
raise ValueError('If using `weights` as places with `include_top`'
' as true, `classes` should be 1365')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
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, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(filters=64, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block1_conv1')(img_input)
x = Conv2D(filters=64, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block1_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block1_pool", padding='valid')(x)
# Block 2
x = Conv2D(filters=128, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block2_conv1')(x)
x = Conv2D(filters=128, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block2_conv2')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block2_pool", padding='valid')(x)
# Block 3
x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block3_conv1')(x)
x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block3_conv2')(x)
x = Conv2D(filters=256, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block3_conv3')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block3_pool", padding='valid')(x)
# Block 4
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block4_conv1')(x)
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block4_conv2')(x)
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block4_conv3')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block4_pool", padding='valid')(x)
# Block 5
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block5_conv1')(x)
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block5_conv2')(x)
x = Conv2D(filters=512, kernel_size=3, strides=(1, 1), padding='same',
kernel_regularizer=l2(0.0002),
activation='relu', name='block5_conv3')(x)
x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name="block5_pool", padding='valid')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dropout(0.5, name='drop_fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dropout(0.5, name='drop_fc2')(x)
x = Dense(1365, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16-hybrid1365')
# load weights
if weights == 'places':
if include_top:
weights_path = get_file('vgg16-hybrid1365_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg16-hybrid1365_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif weights is not None:
model.load_weights(weights)
return model
if __name__ == '__main__':
import urllib2
import numpy as np
from PIL import Image
from cv2 import resize
TEST_IMAGE_URL = 'http://places2.csail.mit.edu/imgs/demo/6.jpg'
image = Image.open(urllib2.urlopen(TEST_IMAGE_URL))
image = np.array(image, dtype=np.uint8)
image = resize(image, (224, 224))
image = np.expand_dims(image, 0)
model = VGG16_Hybrid_1365(weights='places')
predictions_to_return = 5
preds = model.predict(image)[0]
top_preds = np.argsort(preds)[::-1][0:predictions_to_return]
# load the class label
file_name = 'categories_hybrid1365.txt'
if not os.access(file_name, os.W_OK):
synset_url = 'https://raw.githubusercontent.com/csailvision/places365/master/categories_hybrid1365.txt'
os.system('wget ' + synset_url)
classes = list()
counter = 0
with open(file_name) as class_file:
for line in class_file:
if counter <=999:
tmp = line[9:]
if 0 <= counter <= 9:
tmp = tmp[:-2]
elif 10 <= counter <= 99:
tmp = tmp[:-3]
elif 100 <= counter <= 999:
tmp = tmp[:-4]
classes.append(tmp)
else:
classes.append(line.strip().split(' ')[0][3:])
counter +=1
classes = tuple(classes)
print('--PREDICTED SCENE CATEGORIES:')
# output the prediction
for i in range(0, 5):
print(classes[top_preds[i]])
# --PREDICTED SCENE CATEGORIES:
# restaurant, eating house, eating place, eatery
# folding chair
# patio, terrace
# food_court
# cafeteria