forked from wdzyh/SegNet_keras
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmdoel_segnet.py
205 lines (169 loc) · 9.54 KB
/
mdoel_segnet.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
# -*- coding: utf-8 -*-
"""
Created on Fri Apr 19 16:33:17 2019
@author: zhangyonghui
"""
from keras.models import Model
from keras.layers import Conv2D
from keras.layers import BatchNormalization, Activation, Input
from keras.optimizers import Adam
from keras import backend as K
from keras.layers.core import Layer
from keras.layers.convolutional import Convolution2D
class MaxPoolingWithArgmax2D(Layer):
def __init__(self, pool_size=(2, 2), strides=(2, 2), padding='same', **kwargs):
super(MaxPoolingWithArgmax2D, self).__init__(**kwargs)
self.padding = padding
self.pool_size = pool_size
self.strides = strides
def call(self, inputs, **kwargs):
padding = self.padding
pool_size = self.pool_size
strides = self.strides
if K.backend() == 'tensorflow':
ksize = [1, pool_size[0], pool_size[1], 1]
padding = padding.upper()
strides = [1, strides[0], strides[1], 1]
output, argmax = K.tf.nn.max_pool_with_argmax(inputs, ksize=ksize, strides=strides, padding=padding)
else:
errmsg = '{} backend is not supported for layer {}'.format(K.backend(), type(self).__name__)
raise NotImplementedError(errmsg)
argmax = K.cast(argmax, K.floatx())
return [output, argmax]
def compute_output_shape(self, input_shape):
ratio = (1, 2, 2, 1)
output_shape = [dim // ratio[idx] if dim is not None else None for idx, dim in enumerate(input_shape)]
output_shape = tuple(output_shape)
return [output_shape, output_shape]
def compute_mask(self, inputs, mask=None):
return 2 * [None]
class MaxUnpooling2D(Layer):
def __init__(self, size=(2, 2), **kwargs):
super(MaxUnpooling2D, self).__init__(**kwargs)
self.size = size
def call(self, inputs, output_shape=None):
updates, mask = inputs[0], inputs[1]
with K.tf.variable_scope(self.name):
mask = K.cast(mask, 'int32')
input_shape = K.tf.shape(updates, out_type='int32')
# calculation new shape
if output_shape is None:
output_shape = (input_shape[0], input_shape[1] * self.size[0], input_shape[2] * self.size[1], input_shape[3])
self.output_shape1 = output_shape
# calculation indices for batch, height, width and feature maps
one_like_mask = K.ones_like(mask, dtype='int32')
batch_shape = K.concatenate([[input_shape[0]], [1], [1], [1]], axis=0)
batch_range = K.reshape(K.tf.range(output_shape[0], dtype='int32'), shape=batch_shape)
b = one_like_mask * batch_range
y = mask // (output_shape[2] * output_shape[3])
x = (mask // output_shape[3]) % output_shape[2]
feature_range = K.tf.range(output_shape[3], dtype='int32')
f = one_like_mask * feature_range
# transpose indices & reshape update values to one dimension
updates_size = K.tf.size(updates)
indices = K.transpose(K.reshape(K.stack([b, y, x, f]), [4, updates_size]))
values = K.reshape(updates, [updates_size])
ret = K.tf.scatter_nd(indices, values, output_shape)
return ret
def compute_output_shape(self, input_shape):
mask_shape = input_shape[1]
return mask_shape[0], mask_shape[1] * self.size[0], mask_shape[2] * self.size[1], mask_shape[3]
def SegNet(input_shape, n_labels=2, kernel=3, pool_size=(2, 2), output_mode="softmax", model_summary=None):
# encoder
inputs = Input(shape=input_shape)
conv_1 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(inputs)
conv_1 = BatchNormalization()(conv_1)
conv_1 = Activation("relu")(conv_1)
conv_2 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_1)
conv_2 = BatchNormalization()(conv_2)
conv_2 = Activation("relu")(conv_2)
pool_1, mask_1 = MaxPoolingWithArgmax2D(pool_size)(conv_2)
conv_3 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(pool_1)
conv_3 = BatchNormalization()(conv_3)
conv_3 = Activation("relu")(conv_3)
conv_4 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_3)
conv_4 = BatchNormalization()(conv_4)
conv_4 = Activation("relu")(conv_4)
pool_2, mask_2 = MaxPoolingWithArgmax2D(pool_size)(conv_4)
conv_5 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(pool_2)
conv_5 = BatchNormalization()(conv_5)
conv_5 = Activation("relu")(conv_5)
conv_6 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_5)
conv_6 = BatchNormalization()(conv_6)
conv_6 = Activation("relu")(conv_6)
conv_7 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_6)
conv_7 = BatchNormalization()(conv_7)
conv_7 = Activation("relu")(conv_7)
pool_3, mask_3 = MaxPoolingWithArgmax2D(pool_size)(conv_7)
conv_8 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(pool_3)
conv_8 = BatchNormalization()(conv_8)
conv_8 = Activation("relu")(conv_8)
conv_9 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_8)
conv_9 = BatchNormalization()(conv_9)
conv_9 = Activation("relu")(conv_9)
conv_10 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_9)
conv_10 = BatchNormalization()(conv_10)
conv_10 = Activation("relu")(conv_10)
pool_4, mask_4 = MaxPoolingWithArgmax2D(pool_size)(conv_10)
conv_11 = Convolution2D(2160, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(pool_4)
conv_11 = BatchNormalization()(conv_11)
conv_11 = Activation("relu")(conv_11)
conv_12 = Convolution2D(2160, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_11)
conv_12 = BatchNormalization()(conv_12)
conv_12 = Activation("relu")(conv_12)
conv_13 = Convolution2D(2160, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_12)
conv_13 = BatchNormalization()(conv_13)
conv_13 = Activation("relu")(conv_13)
pool_5, mask_5 = MaxPoolingWithArgmax2D(pool_size)(conv_13)
print("Build enceder done..")
# decoder
unpool_1 = MaxUnpooling2D(pool_size)([pool_5, mask_5])
conv_14 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(unpool_1)
conv_14 = BatchNormalization()(conv_14)
conv_14 = Activation("relu")(conv_14)
conv_15 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_14)
conv_15 = BatchNormalization()(conv_15)
conv_15 = Activation("relu")(conv_15)
conv_16 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_15)
conv_16 = BatchNormalization()(conv_16)
conv_16 = Activation("relu")(conv_16)
unpool_2 = MaxUnpooling2D(pool_size)([conv_16, mask_4])
conv_17 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(unpool_2)
conv_17 = BatchNormalization()(conv_17)
conv_17 = Activation("relu")(conv_17)
conv_18 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_17)
conv_18 = BatchNormalization()(conv_18)
conv_18 = Activation("relu")(conv_18)
conv_19 = Convolution2D(1080, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_18)
conv_19 = BatchNormalization()(conv_19)
conv_19 = Activation("relu")(conv_19)
unpool_3 = MaxUnpooling2D(pool_size)([conv_19, mask_3])
conv_20 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(unpool_3)
conv_20 = BatchNormalization()(conv_20)
conv_20 = Activation("relu")(conv_20)
conv_21 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_20)
conv_21 = BatchNormalization()(conv_21)
conv_21 = Activation("relu")(conv_21)
conv_22 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_21)
conv_22 = BatchNormalization()(conv_22)
conv_22 = Activation("relu")(conv_22)
unpool_4 = MaxUnpooling2D(pool_size)([conv_22, mask_2])
conv_23 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(unpool_4)
conv_23 = BatchNormalization()(conv_23)
conv_23 = Activation("relu")(conv_23)
conv_24 = Convolution2D(540, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(conv_23)
conv_24 = BatchNormalization()(conv_24)
conv_24 = Activation("relu")(conv_24)
unpool_5 = MaxUnpooling2D(pool_size)([conv_24, mask_1])
conv_25 = Convolution2D(270, (kernel, kernel), padding="same", kernel_initializer = 'he_normal')(unpool_5)
conv_25 = BatchNormalization()(conv_25)
conv_25 = Activation("relu")(conv_25)
out=Conv2D(n_labels,1, activation = output_mode)(conv_25)
print("Build decoder done..")
model = Model(inputs=inputs, outputs=out, name="SegNet")
model.compile(optimizer = Adam(lr = 1e-4), loss = 'categorical_crossentropy', metrics = ['categorical_accuracy'])
if model_summary is True:
model.summary()
return model
if __name__ == '__main__':
SegNet(input_shape=(64, 64, 270), n_labels=4, model_summary=True)