MOSAIC-22/architecture.py at main · nisarg-a19/MOSAIC-22 · GitHub

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
from keras.layers import *
from keras.models import Model
import tensorflow as tf
import numpy as np
import struct
import numpy as np
from keras.layers import Conv2D
from keras.layers import Input
from keras.layers import BatchNormalization
from keras.layers import LeakyReLU
from keras.layers import ZeroPadding2D
from keras.layers import UpSampling2D
from keras.layers.merge import add, concatenate
from keras.models import Model

IMAGE_H, IMAGE_W = 416, 416
GRID_H,  GRID_W  = 13 , 13
BOX = 5
CLASS =1


# Full model of yolo v2
def create_model():

    # the function to implement the organization layer (thanks to github.com/allanzelener/YAD2K)
    def space_to_depth_x2(x):
        return tf.nn.space_to_depth(x, block_size=2)

    # Define input
    x_input = Input([IMAGE_H, IMAGE_W, 3])

    # Layer 1
    x = Conv2D(32, (3, 3), strides=(1, 1), padding='same', name='conv_1', use_bias=False)(x_input)
    x = BatchNormalization(name='norm_1')(x)
    x = LeakyReLU(alpha=0.1)(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Layer 2
    x = Conv2D(64, (3, 3), strides=(1, 1), padding='same', name='conv_2', use_bias=False)(x)
    x = BatchNormalization(name='norm_2')(x)
    x = LeakyReLU(alpha=0.1)(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Layer 3
    x = Conv2D(128, (3, 3), strides=(1, 1), padding='same', name='conv_3', use_bias=False)(x)
    x = BatchNormalization(name='norm_3')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 4
    x = Conv2D(64, (1, 1), strides=(1, 1), padding='same', name='conv_4', use_bias=False)(x)
    x = BatchNormalization(name='norm_4')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 5
    x = Conv2D(128, (3, 3), strides=(1, 1), padding='same', name='conv_5', use_bias=False)(x)
    x = BatchNormalization(name='norm_5')(x)
    x = LeakyReLU(alpha=0.1)(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Layer 6
    x = Conv2D(256, (3, 3), strides=(1, 1), padding='same', name='conv_6', use_bias=False)(x)
    x = BatchNormalization(name='norm_6')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 7
    x = Conv2D(128, (1, 1), strides=(1, 1), padding='same', name='conv_7', use_bias=False)(x)
    x = BatchNormalization(name='norm_7')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 8
    x = Conv2D(256, (3, 3), strides=(1, 1), padding='same', name='conv_8', use_bias=False)(x)
    x = BatchNormalization(name='norm_8')(x)
    x = LeakyReLU(alpha=0.1)(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Layer 9
    x = Conv2D(512, (3, 3), strides=(1, 1), padding='same', name='conv_9', use_bias=False)(x)
    x = BatchNormalization(name='norm_9')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 10
    x = Conv2D(256, (1, 1), strides=(1, 1), padding='same', name='conv_10', use_bias=False)(x)
    x = BatchNormalization(name='norm_10')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 11
    x = Conv2D(512, (3, 3), strides=(1, 1), padding='same', name='conv_11', use_bias=False)(x)
    x = BatchNormalization(name='norm_11')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 12
    x = Conv2D(256, (1, 1), strides=(1, 1), padding='same', name='conv_12', use_bias=False)(x)
    x = BatchNormalization(name='norm_12')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 13
    x = Conv2D(512, (3, 3), strides=(1, 1), padding='same', name='conv_13', use_bias=False)(x)
    x = BatchNormalization(name='norm_13')(x)
    x = LeakyReLU(alpha=0.1)(x)

    skip_connection = x

    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Layer 14
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_14', use_bias=False)(x)
    x = BatchNormalization(name='norm_14')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 15
    x = Conv2D(512, (1, 1), strides=(1, 1), padding='same', name='conv_15', use_bias=False)(x)
    x = BatchNormalization(name='norm_15')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 16
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_16', use_bias=False)(x)
    x = BatchNormalization(name='norm_16')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 17
    x = Conv2D(512, (1, 1), strides=(1, 1), padding='same', name='conv_17', use_bias=False)(x)
    x = BatchNormalization(name='norm_17')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 18
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_18', use_bias=False)(x)
    x = BatchNormalization(name='norm_18')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 19
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_19', use_bias=False)(x)
    x = BatchNormalization(name='norm_19')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 20
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_20', use_bias=False)(x)
    x = BatchNormalization(name='norm_20')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 21
    skip_connection = Conv2D(64, (1, 1), strides=(1, 1), padding='same', name='conv_21', use_bias=False)(
        skip_connection)
    skip_connection = BatchNormalization(name='norm_21')(skip_connection)
    skip_connection = LeakyReLU(alpha=0.1)(skip_connection)
    skip_connection = Lambda(space_to_depth_x2)(skip_connection)

    x = concatenate([skip_connection, x])

    # Layer 22
    x = Conv2D(1024, (3, 3), strides=(1, 1), padding='same', name='conv_22', use_bias=False)(x)
    x = BatchNormalization(name='norm_22')(x)
    x = LeakyReLU(alpha=0.1)(x)

    # Layer 23
    x = Conv2D(BOX * (4 + 1 + CLASS), (1, 1), strides=(1, 1), padding='same', name='conv_23')(x)


    output = Reshape([GRID_H, GRID_W, BOX, 4 + 1 + CLASS])(x)

    model = Model(x_input, output)


    return model


LABELS = ['pool']


# ANCHORS = np.array([[0.57273, 0.677385],
#                     [1.87446, 2.06253],
#                     [3.33843, 5.47434],
#                     [7.88282, 3.52778],
#                     [9.77052, 9.16828]])
# ANCHORS = np.array([[10,13],
#                     [16,30],
#                     [33,23],
#                     [30,61],
#                     [62,45],
#                     [59,119],
#                     [116,90],
#                     [156,198],
#                     [373,326]])


ANCHORS = [[116,90, 156,198, 373,326], [30,61, 62,45, 59,119], [10,13, 16,30, 33,23]]