This repository has been archived by the owner on Oct 20, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 15
/
model.py
252 lines (203 loc) · 10.1 KB
/
model.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
import math
import numpy as np
import tensorflow as tf
from enum import Enum, unique
@unique
class InputType(Enum):
TENSOR = 1
BASE64_JPEG = 2
class OpenNsfwModel:
"""Tensorflow implementation of Yahoo's Open NSFW Model
Original implementation:
https://github.com/yahoo/open_nsfw
Weights have been converted using caffe-tensorflow:
https://github.com/ethereon/caffe-tensorflow
"""
def __init__(self):
self.weights = {}
self.bn_epsilon = 1e-5 # Default used by Caffe
def build(self, weights_path="open_nsfw-weights.npy",
input_type=InputType.TENSOR):
self.weights = np.load(weights_path, encoding="latin1",allow_pickle=True).item()
self.input_tensor = None
if input_type == InputType.TENSOR:
self.input = tf.placeholder(tf.float32,
shape=[None, 224, 224, 3],
name="input")
self.input_tensor = self.input
elif input_type == InputType.BASE64_JPEG:
from image_utils import load_base64_tensor
self.input = tf.placeholder(tf.string, shape=(None,), name="input")
self.input_tensor = load_base64_tensor(self.input)
else:
raise ValueError("invalid input type '{}'".format(input_type))
x = self.input_tensor
x = tf.pad(x, [[0, 0], [3, 3], [3, 3], [0, 0]], 'CONSTANT')
x = self.__conv2d("conv_1", x, filter_depth=64,
kernel_size=7, stride=2, padding='valid')
x = self.__batch_norm("bn_1", x)
x = tf.nn.relu(x)
x = tf.layers.max_pooling2d(x, pool_size=3, strides=2, padding='same')
x = self.__conv_block(stage=0, block=0, inputs=x,
filter_depths=[32, 32, 128],
kernel_size=3, stride=1)
x = self.__identity_block(stage=0, block=1, inputs=x,
filter_depths=[32, 32, 128], kernel_size=3)
x = self.__identity_block(stage=0, block=2, inputs=x,
filter_depths=[32, 32, 128], kernel_size=3)
x = self.__conv_block(stage=1, block=0, inputs=x,
filter_depths=[64, 64, 256],
kernel_size=3, stride=2)
x = self.__identity_block(stage=1, block=1, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__identity_block(stage=1, block=2, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__identity_block(stage=1, block=3, inputs=x,
filter_depths=[64, 64, 256], kernel_size=3)
x = self.__conv_block(stage=2, block=0, inputs=x,
filter_depths=[128, 128, 512],
kernel_size=3, stride=2)
x = self.__identity_block(stage=2, block=1, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=2, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=3, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=4, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__identity_block(stage=2, block=5, inputs=x,
filter_depths=[128, 128, 512], kernel_size=3)
x = self.__conv_block(stage=3, block=0, inputs=x,
filter_depths=[256, 256, 1024], kernel_size=3,
stride=2)
x = self.__identity_block(stage=3, block=1, inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = self.__identity_block(stage=3, block=2, inputs=x,
filter_depths=[256, 256, 1024],
kernel_size=3)
x = tf.layers.average_pooling2d(x, pool_size=7, strides=1,
padding="valid", name="pool")
x = tf.reshape(x, shape=(-1, 1024))
self.logits = self.__fully_connected(name="fc_nsfw",
inputs=x, num_outputs=2)
self.predictions = tf.nn.softmax(self.logits, name="predictions")
"""Get weights for layer with given name
"""
def __get_weights(self, layer_name, field_name):
if not layer_name in self.weights:
raise ValueError("No weights for layer named '{}' found"
.format(layer_name))
w = self.weights[layer_name]
if not field_name in w:
raise (ValueError("No entry for field '{}' in layer named '{}'"
.format(field_name, layer_name)))
return w[field_name]
"""Layer creation and weight initialization
"""
def __fully_connected(self, name, inputs, num_outputs):
return tf.layers.dense(
inputs=inputs, units=num_outputs, name=name,
kernel_initializer=tf.constant_initializer(
self.__get_weights(name, "weights"), dtype=tf.float32),
bias_initializer=tf.constant_initializer(
self.__get_weights(name, "biases"), dtype=tf.float32))
def __conv2d(self, name, inputs, filter_depth, kernel_size, stride=1,
padding="same", trainable=False):
if padding.lower() == 'same' and kernel_size > 1:
if kernel_size > 1:
oh = inputs.get_shape().as_list()[1]
h = inputs.get_shape().as_list()[1]
p = int(math.floor(((oh - 1) * stride + kernel_size - h)//2))
inputs = tf.pad(inputs,
[[0, 0], [p, p], [p, p], [0, 0]],
'CONSTANT')
else:
raise Exception('unsupported kernel size for padding: "{}"'
.format(kernel_size))
return tf.layers.conv2d(
inputs, filter_depth,
kernel_size=(kernel_size, kernel_size),
strides=(stride, stride), padding='valid',
activation=None, trainable=trainable, name=name,
kernel_initializer=tf.constant_initializer(
self.__get_weights(name, "weights"), dtype=tf.float32),
bias_initializer=tf.constant_initializer(
self.__get_weights(name, "biases"), dtype=tf.float32))
def __batch_norm(self, name, inputs, training=False):
return tf.layers.batch_normalization(
inputs, training=training, epsilon=self.bn_epsilon,
gamma_initializer=tf.constant_initializer(
self.__get_weights(name, "scale"), dtype=tf.float32),
beta_initializer=tf.constant_initializer(
self.__get_weights(name, "offset"), dtype=tf.float32),
moving_mean_initializer=tf.constant_initializer(
self.__get_weights(name, "mean"), dtype=tf.float32),
moving_variance_initializer=tf.constant_initializer(
self.__get_weights(name, "variance"), dtype=tf.float32),
name=name)
"""ResNet blocks
"""
def __conv_block(self, stage, block, inputs, filter_depths,
kernel_size=3, stride=2):
filter_depth1, filter_depth2, filter_depth3 = filter_depths
conv_name_base = "conv_stage{}_block{}_branch".format(stage, block)
bn_name_base = "bn_stage{}_block{}_branch".format(stage, block)
shortcut_name_post = "_stage{}_block{}_proj_shortcut" \
.format(stage, block)
shortcut = self.__conv2d(
name="conv{}".format(shortcut_name_post), stride=stride,
inputs=inputs, filter_depth=filter_depth3, kernel_size=1,
padding="same"
)
shortcut = self.__batch_norm("bn{}".format(shortcut_name_post),
shortcut)
x = self.__conv2d(
name="{}2a".format(conv_name_base),
inputs=inputs, filter_depth=filter_depth1, kernel_size=1,
stride=stride, padding="same",
)
x = self.__batch_norm("{}2a".format(bn_name_base), x)
x = tf.nn.relu(x)
x = self.__conv2d(
name="{}2b".format(conv_name_base),
inputs=x, filter_depth=filter_depth2, kernel_size=kernel_size,
padding="same", stride=1
)
x = self.__batch_norm("{}2b".format(bn_name_base), x)
x = tf.nn.relu(x)
x = self.__conv2d(
name="{}2c".format(conv_name_base),
inputs=x, filter_depth=filter_depth3, kernel_size=1,
padding="same", stride=1
)
x = self.__batch_norm("{}2c".format(bn_name_base), x)
x = tf.add(x, shortcut)
return tf.nn.relu(x)
def __identity_block(self, stage, block, inputs,
filter_depths, kernel_size):
filter_depth1, filter_depth2, filter_depth3 = filter_depths
conv_name_base = "conv_stage{}_block{}_branch".format(stage, block)
bn_name_base = "bn_stage{}_block{}_branch".format(stage, block)
x = self.__conv2d(
name="{}2a".format(conv_name_base),
inputs=inputs, filter_depth=filter_depth1, kernel_size=1,
stride=1, padding="same",
)
x = self.__batch_norm("{}2a".format(bn_name_base), x)
x = tf.nn.relu(x)
x = self.__conv2d(
name="{}2b".format(conv_name_base),
inputs=x, filter_depth=filter_depth2, kernel_size=kernel_size,
padding="same", stride=1
)
x = self.__batch_norm("{}2b".format(bn_name_base), x)
x = tf.nn.relu(x)
x = self.__conv2d(
name="{}2c".format(conv_name_base),
inputs=x, filter_depth=filter_depth3, kernel_size=1,
padding="same", stride=1
)
x = self.__batch_norm("{}2c".format(bn_name_base), x)
x = tf.add(x, inputs)
return tf.nn.relu(x)