classic-convolution-network/InceptionResNetV2.py at master · bubbliiiing/classic-convolution-network · 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
import warnings

import numpy as np
from keras import backend as K
from keras.applications.imagenet_utils import decode_predictions
from keras.layers import (Activation, AveragePooling2D, BatchNormalization,
                          Concatenate, Conv2D, Dense, GlobalAveragePooling2D,
                          GlobalMaxPooling2D, Input, Lambda, MaxPooling2D)
from keras.models import Model
from keras.preprocessing import image
from keras.utils.data_utils import get_file

BASE_WEIGHT_URL = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.7/'

#---------------------------------------#
#   卷积块
#   卷积 + 标准化 + 激活函数
#---------------------------------------#
def conv2d_bn(x,filters,kernel_size,strides=1,padding='same',activation='relu',use_bias=False,name=None):
    x = Conv2D(filters,
               kernel_size,
               strides=strides,
               padding=padding,
               use_bias=use_bias,
               name=name)(x)
    if not use_bias:
        bn_name = None if name is None else name + '_bn'
        x = BatchNormalization(scale=False, name=bn_name)(x)
    if activation is not None:
        ac_name = None if name is None else name + '_ac'
        x = Activation(activation, name=ac_name)(x)
    return x

def inception_resnet_block(x, scale, block_type, block_idx, activation='relu'):
    if block_type == 'block35':
        branch_0 = conv2d_bn(x, 32, 1)

        branch_1 = conv2d_bn(x, 32, 1)
        branch_1 = conv2d_bn(branch_1, 32, 3)

        branch_2 = conv2d_bn(x, 32, 1)
        branch_2 = conv2d_bn(branch_2, 48, 3)
        branch_2 = conv2d_bn(branch_2, 64, 3)

        branches = [branch_0, branch_1, branch_2]
    elif block_type == 'block17':
        branch_0 = conv2d_bn(x, 192, 1)

        branch_1 = conv2d_bn(x, 128, 1)
        branch_1 = conv2d_bn(branch_1, 160, [1, 7])
        branch_1 = conv2d_bn(branch_1, 192, [7, 1])

        branches = [branch_0, branch_1]
    elif block_type == 'block8':
        branch_0 = conv2d_bn(x, 192, 1)

        branch_1 = conv2d_bn(x, 192, 1)
        branch_1 = conv2d_bn(branch_1, 224, [1, 3])
        branch_1 = conv2d_bn(branch_1, 256, [3, 1])

        branches = [branch_0, branch_1]
    else:
        raise ValueError('Unknown Inception-ResNet block type. '
                         'Expects "block35", "block17" or "block8", '
                         'but got: ' + str(block_type))

    block_name = block_type + '_' + str(block_idx)
    mixed = Concatenate(name=block_name + '_mixed')(branches)
    up = conv2d_bn(mixed, K.int_shape(x)[3], 1, activation=None,use_bias=True,name=block_name + '_conv')

    x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
               output_shape=K.int_shape(x)[1:],
               arguments={'scale': scale},
               name=block_name)([x, up])
    if activation is not None:
        x = Activation(activation, name=block_name + '_ac')(x)
    return x


def InceptionResNetV2(input_shape=[299,299,3],
                      classes=1000):

    input_shape = [299,299,3]

    img_input = Input(shape=input_shape)

    # 299,299,3 -> 35,35,192
    x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
    x = conv2d_bn(x, 32, 3, padding='valid')
    x = conv2d_bn(x, 64, 3)
    x = MaxPooling2D(3, strides=2)(x)

    x = conv2d_bn(x, 80, 1, padding='valid')
    x = conv2d_bn(x, 192, 3, padding='valid')
    x = MaxPooling2D(3, strides=2)(x)

    # 35,35,192 -> 35,35,320
    branch_0 = conv2d_bn(x, 96, 1)

    branch_1 = conv2d_bn(x, 48, 1)
    branch_1 = conv2d_bn(branch_1, 64, 5)

    branch_2 = conv2d_bn(x, 64, 1)
    branch_2 = conv2d_bn(branch_2, 96, 3)
    branch_2 = conv2d_bn(branch_2, 96, 3)

    branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
    branch_pool = conv2d_bn(branch_pool, 64, 1)
    branches = [branch_0, branch_1, branch_2, branch_pool]
    x = Concatenate(name='mixed_5b')(branches)

    # 10次Inception-ResNet-A block:35 x 35 x 320 -> 35 x 35 x 320
    for block_idx in range(1, 11):
        x = inception_resnet_block(x, scale=0.17, block_type='block35', block_idx=block_idx)

    # Reduction-A block:35 x 35 x 320 -> 17 x 17 x 1088
    branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
    branch_1 = conv2d_bn(x, 256, 1)
    branch_1 = conv2d_bn(branch_1, 256, 3)
    branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
    branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
    branches = [branch_0, branch_1, branch_pool]
    x = Concatenate(name='mixed_6a')(branches)

    # 20次Inception-ResNet-B block: 17 x 17 x 1088 -> 17 x 17 x 1088
    for block_idx in range(1, 21):
        x = inception_resnet_block(x,
                                   scale=0.1,
                                   block_type='block17',
                                   block_idx=block_idx)


    # Reduction-B block: 17 x 17 x 1088 -> 8 x 8 x 2080
    branch_0 = conv2d_bn(x, 256, 1)
    branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
    branch_1 = conv2d_bn(x, 256, 1)
    branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
    branch_2 = conv2d_bn(x, 256, 1)
    branch_2 = conv2d_bn(branch_2, 288, 3)
    branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
    branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
    branches = [branch_0, branch_1, branch_2, branch_pool]
    x = Concatenate(name='mixed_7a')(branches)

    # 10次Inception-ResNet-C block: 8 x 8 x 2080 -> 8 x 8 x 2080
    for block_idx in range(1, 10):
        x = inception_resnet_block(x,
                                   scale=0.2,
                                   block_type='block8',
                                   block_idx=block_idx)
    x = inception_resnet_block(x,
                               scale=1.,
                               activation=None,
                               block_type='block8',
                               block_idx=10)

    # 8 x 8 x 2080 -> 8 x 8 x 1536
    x = conv2d_bn(x, 1536, 1, name='conv_7b')

    x = GlobalAveragePooling2D(name='avg_pool')(x)
    x = Dense(classes, activation='softmax', name='predictions')(x)

    inputs = img_input

    # 创建模型
    model = Model(inputs, x, name='inception_resnet_v2')
    return model

def preprocess_input(x):
    x /= 255.
    x -= 0.5
    x *= 2.
    return x

if __name__ == '__main__':
    model = InceptionResNetV2()
    fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
    weights_path = get_file(fname,BASE_WEIGHT_URL + fname,cache_subdir='models',file_hash='e693bd0210a403b3192acc6073ad2e96')
    model.load_weights(weights_path)

    img_path = 'elephant.jpg'
    img = image.load_img(img_path, target_size=(299, 299))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    x = preprocess_input(x)
    print('Input image shape:', x.shape)

    preds = model.predict(x)
    print('Predicted:', decode_predictions(preds))