forked from DavideA/dilation-keras
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dilation_net.py
326 lines (282 loc) · 16.5 KB
/
dilation_net.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
import warnings
from keras import backend as K
from keras.models import Model
from keras.layers import Convolution2D, MaxPooling2D, Input, AtrousConvolution2D
from keras.layers import Dropout, UpSampling2D, ZeroPadding2D
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from datasets import CONFIG
from utils import softmax
# CITYSCAPES MODEL
def get_dilation_model_cityscapes(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, name='final')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_2')(h)
h = ZeroPadding2D(padding=(2, 2))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ctx_conv2_1')(h)
h = ZeroPadding2D(padding=(4, 4))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ctx_conv3_1')(h)
h = ZeroPadding2D(padding=(8, 8))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ctx_conv4_1')(h)
h = ZeroPadding2D(padding=(16, 16))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(16, 16), activation='relu', name='ctx_conv5_1')(h)
h = ZeroPadding2D(padding=(32, 32))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(32, 32), activation='relu', name='ctx_conv6_1')(h)
h = ZeroPadding2D(padding=(64, 64))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(64, 64), activation='relu', name='ctx_conv7_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_fc1')(h)
h = Convolution2D(classes, 1, 1, name='ctx_final')(h)
# the following two layers pretend to be a Deconvolution with grouping layer.
# never managed to implement it in Keras
# since it's just a gaussian upsampling trainable=False is recommended
h = UpSampling2D(size=(8, 8))(h)
logits = Convolution2D(classes, 16, 16, border_mode='same', bias=False, trainable=False, name='ctx_upsample')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_cityscapes')
return model
# PASCAL VOC MODEL
def get_dilation_model_voc(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, activation='relu', name='fc-final')(h)
h = ZeroPadding2D(padding=(33, 33))(h)
h = Convolution2D(2 * classes, 3, 3, activation='relu', name='ct_conv1_1')(h)
h = Convolution2D(2 * classes, 3, 3, activation='relu', name='ct_conv1_2')(h)
h = AtrousConvolution2D(4 * classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ct_conv2_1')(h)
h = AtrousConvolution2D(8 * classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ct_conv3_1')(h)
h = AtrousConvolution2D(16 * classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ct_conv4_1')(h)
h = AtrousConvolution2D(32 * classes, 3, 3, atrous_rate=(16, 16), activation='relu', name='ct_conv5_1')(h)
h = Convolution2D(32 * classes, 3, 3, activation='relu', name='ct_fc1')(h)
logits = Convolution2D(classes, 1, 1, name='ct_final')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_voc12')
return model
# KITTI MODEL
def get_dilation_model_kitti(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, name='final')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_2')(h)
h = ZeroPadding2D(padding=(2, 2))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ctx_conv2_1')(h)
h = ZeroPadding2D(padding=(4, 4))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ctx_conv3_1')(h)
h = ZeroPadding2D(padding=(8, 8))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ctx_conv4_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_fc1')(h)
logits = Convolution2D(classes, 1, 1, name='ctx_final')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_kitti')
return model
# CAMVID MODEL
def get_dilation_model_camvid(input_shape, apply_softmax, input_tensor, classes):
if input_tensor is None:
model_in = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
model_in = Input(tensor=input_tensor, shape=input_shape)
else:
model_in = input_tensor
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_1')(model_in)
h = Convolution2D(64, 3, 3, activation='relu', name='conv1_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_1')(h)
h = Convolution2D(128, 3, 3, activation='relu', name='conv2_2')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_1')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_2')(h)
h = Convolution2D(256, 3, 3, activation='relu', name='conv3_3')(h)
h = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), name='pool3')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_1')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_2')(h)
h = Convolution2D(512, 3, 3, activation='relu', name='conv4_3')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_1')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_2')(h)
h = AtrousConvolution2D(512, 3, 3, atrous_rate=(2, 2), activation='relu', name='conv5_3')(h)
h = AtrousConvolution2D(4096, 7, 7, atrous_rate=(4, 4), activation='relu', name='fc6')(h)
h = Dropout(0.5, name='drop6')(h)
h = Convolution2D(4096, 1, 1, activation='relu', name='fc7')(h)
h = Dropout(0.5, name='drop7')(h)
h = Convolution2D(classes, 1, 1, name='final')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_conv1_2')(h)
h = ZeroPadding2D(padding=(2, 2))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(2, 2), activation='relu', name='ctx_conv2_1')(h)
h = ZeroPadding2D(padding=(4, 4))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(4, 4), activation='relu', name='ctx_conv3_1')(h)
h = ZeroPadding2D(padding=(8, 8))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(8, 8), activation='relu', name='ctx_conv4_1')(h)
h = ZeroPadding2D(padding=(16, 16))(h)
h = AtrousConvolution2D(classes, 3, 3, atrous_rate=(16, 16), activation='relu', name='ctx_conv5_1')(h)
h = ZeroPadding2D(padding=(1, 1))(h)
h = Convolution2D(classes, 3, 3, activation='relu', name='ctx_fc1')(h)
logits = Convolution2D(classes, 1, 1, name='ctx_final')(h)
if apply_softmax:
model_out = softmax(logits)
else:
model_out = logits
model = Model(input=model_in, output=model_out, name='dilation_camvid')
return model
# model function
def DilationNet(dataset, input_shape=None, apply_softmax=True, pretrained=True,
input_tensor=None, classes=None):
""" Instantiate the Dilation network architecture, optionally loading weights
pre-trained on a dataset in the set (cityscapes, voc12, kitti, camvid).
Note that pre-trained model is only available for Theano dim ordering.
The model and the weights should be compatible with both
TensorFlow and Theano backends.
# Arguments
dataset: choose among (cityscapes, voc12, kitti, camvid).
input_shape: shape tuple. It should have exactly 3 inputs channels,
and the axis ordering should be coherent with what specified in
your keras.json (e.g. use (3, 512, 512) for 'th' and (512, 512, 3)
for 'tf'). None will default to dataset specific sizes.
apply_softmax: whether to apply softmax or return logits.
pretrained: boolean. If `True`, loads weights coherently with
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: optional number of segmentation classes. If pretrained is True,
it should be coherent with the dataset chosen.
# Returns
A Keras model instance.
"""
if dataset not in {'cityscapes', 'voc12', 'kitti', 'camvid'}:
raise ValueError('The `dataset` argument should be one among '
'(cityscapes, voc12, kitti, camvid)')
if classes is not None:
if classes != CONFIG[dataset]['classes'] and pretrained:
raise ValueError('Cannot load pretrained model for dataset `{}` '
'with {} classes'.format(dataset, classes))
else:
classes = CONFIG[dataset]['classes']
if input_shape is None:
input_shape = CONFIG[dataset]['input_shape']
# get the model
if dataset == 'cityscapes':
model = get_dilation_model_cityscapes(input_shape=input_shape, apply_softmax=apply_softmax,
input_tensor=input_tensor, classes=classes)
elif dataset == 'voc12':
model = get_dilation_model_voc(input_shape=input_shape, apply_softmax=apply_softmax,
input_tensor=input_tensor, classes=classes)
elif dataset == 'kitti':
model = get_dilation_model_kitti(input_shape=input_shape, apply_softmax=apply_softmax,
input_tensor=input_tensor, classes=classes)
elif dataset == 'camvid':
model = get_dilation_model_camvid(input_shape=input_shape, apply_softmax=apply_softmax,
input_tensor=input_tensor, classes=classes)
# load weights
if pretrained:
if K.image_dim_ordering() == 'th':
weights_path = get_file(CONFIG[dataset]['weights_file'],
CONFIG[dataset]['weights_url'],
cache_subdir='models')
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:
raise NotImplementedError('Pretrained DilationNet model is not available with '
'tensorflow dim ordering')
return model