forked from Skuldur/facenet-face-recognition
-
Notifications
You must be signed in to change notification settings - Fork 0
/
fr_utils.py
203 lines (176 loc) · 8.58 KB
/
fr_utils.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
#### PART OF THIS CODE IS USING CODE FROM VICTOR SY WANG: https://github.com/iwantooxxoox/Keras-OpenFace/blob/master/utils.py ####
#### THIS FILE IS FROM https://github.com/shahariarrabby/deeplearning.ai/blob/master/COURSE%204%20Convolutional%20Neural%20Networks/Week%2004/Face%20Recognition/fr_utils.py
import tensorflow as tf
import numpy as np
import os
import cv2
from numpy import genfromtxt
from keras.layers import Conv2D, ZeroPadding2D, Activation, Input, concatenate
from keras.models import Model
from keras.layers.normalization import BatchNormalization
from keras.layers.pooling import MaxPooling2D, AveragePooling2D
import h5py
import matplotlib.pyplot as plt
_FLOATX = 'float32'
def variable(value, dtype=_FLOATX, name=None):
v = tf.Variable(np.asarray(value, dtype=dtype), name=name)
_get_session().run(v.initializer)
return v
def shape(x):
return x.get_shape()
def square(x):
return tf.square(x)
def zeros(shape, dtype=_FLOATX, name=None):
return variable(np.zeros(shape), dtype, name)
def concatenate(tensors, axis=-1):
if axis < 0:
axis = axis % len(tensors[0].get_shape())
return tf.concat(axis, tensors)
def LRN2D(x):
return tf.nn.lrn(x, alpha=1e-4, beta=0.75)
def conv2d_bn(x,
layer=None,
cv1_out=None,
cv1_filter=(1, 1),
cv1_strides=(1, 1),
cv2_out=None,
cv2_filter=(3, 3),
cv2_strides=(1, 1),
padding=None):
num = '' if cv2_out == None else '1'
tensor = Conv2D(cv1_out, cv1_filter, strides=cv1_strides, data_format='channels_first', name=layer+'_conv'+num)(x)
tensor = BatchNormalization(axis=1, epsilon=0.00001, name=layer+'_bn'+num)(tensor)
tensor = Activation('relu')(tensor)
if padding == None:
return tensor
tensor = ZeroPadding2D(padding=padding, data_format='channels_first')(tensor)
if cv2_out == None:
return tensor
tensor = Conv2D(cv2_out, cv2_filter, strides=cv2_strides, data_format='channels_first', name=layer+'_conv'+'2')(tensor)
tensor = BatchNormalization(axis=1, epsilon=0.00001, name=layer+'_bn'+'2')(tensor)
tensor = Activation('relu')(tensor)
return tensor
WEIGHTS = [
'conv1', 'bn1', 'conv2', 'bn2', 'conv3', 'bn3',
'inception_3a_1x1_conv', 'inception_3a_1x1_bn',
'inception_3a_pool_conv', 'inception_3a_pool_bn',
'inception_3a_5x5_conv1', 'inception_3a_5x5_conv2', 'inception_3a_5x5_bn1', 'inception_3a_5x5_bn2',
'inception_3a_3x3_conv1', 'inception_3a_3x3_conv2', 'inception_3a_3x3_bn1', 'inception_3a_3x3_bn2',
'inception_3b_3x3_conv1', 'inception_3b_3x3_conv2', 'inception_3b_3x3_bn1', 'inception_3b_3x3_bn2',
'inception_3b_5x5_conv1', 'inception_3b_5x5_conv2', 'inception_3b_5x5_bn1', 'inception_3b_5x5_bn2',
'inception_3b_pool_conv', 'inception_3b_pool_bn',
'inception_3b_1x1_conv', 'inception_3b_1x1_bn',
'inception_3c_3x3_conv1', 'inception_3c_3x3_conv2', 'inception_3c_3x3_bn1', 'inception_3c_3x3_bn2',
'inception_3c_5x5_conv1', 'inception_3c_5x5_conv2', 'inception_3c_5x5_bn1', 'inception_3c_5x5_bn2',
'inception_4a_3x3_conv1', 'inception_4a_3x3_conv2', 'inception_4a_3x3_bn1', 'inception_4a_3x3_bn2',
'inception_4a_5x5_conv1', 'inception_4a_5x5_conv2', 'inception_4a_5x5_bn1', 'inception_4a_5x5_bn2',
'inception_4a_pool_conv', 'inception_4a_pool_bn',
'inception_4a_1x1_conv', 'inception_4a_1x1_bn',
'inception_4e_3x3_conv1', 'inception_4e_3x3_conv2', 'inception_4e_3x3_bn1', 'inception_4e_3x3_bn2',
'inception_4e_5x5_conv1', 'inception_4e_5x5_conv2', 'inception_4e_5x5_bn1', 'inception_4e_5x5_bn2',
'inception_5a_3x3_conv1', 'inception_5a_3x3_conv2', 'inception_5a_3x3_bn1', 'inception_5a_3x3_bn2',
'inception_5a_pool_conv', 'inception_5a_pool_bn',
'inception_5a_1x1_conv', 'inception_5a_1x1_bn',
'inception_5b_3x3_conv1', 'inception_5b_3x3_conv2', 'inception_5b_3x3_bn1', 'inception_5b_3x3_bn2',
'inception_5b_pool_conv', 'inception_5b_pool_bn',
'inception_5b_1x1_conv', 'inception_5b_1x1_bn',
'dense_layer'
]
conv_shape = {
'conv1': [64, 3, 7, 7],
'conv2': [64, 64, 1, 1],
'conv3': [192, 64, 3, 3],
'inception_3a_1x1_conv': [64, 192, 1, 1],
'inception_3a_pool_conv': [32, 192, 1, 1],
'inception_3a_5x5_conv1': [16, 192, 1, 1],
'inception_3a_5x5_conv2': [32, 16, 5, 5],
'inception_3a_3x3_conv1': [96, 192, 1, 1],
'inception_3a_3x3_conv2': [128, 96, 3, 3],
'inception_3b_3x3_conv1': [96, 256, 1, 1],
'inception_3b_3x3_conv2': [128, 96, 3, 3],
'inception_3b_5x5_conv1': [32, 256, 1, 1],
'inception_3b_5x5_conv2': [64, 32, 5, 5],
'inception_3b_pool_conv': [64, 256, 1, 1],
'inception_3b_1x1_conv': [64, 256, 1, 1],
'inception_3c_3x3_conv1': [128, 320, 1, 1],
'inception_3c_3x3_conv2': [256, 128, 3, 3],
'inception_3c_5x5_conv1': [32, 320, 1, 1],
'inception_3c_5x5_conv2': [64, 32, 5, 5],
'inception_4a_3x3_conv1': [96, 640, 1, 1],
'inception_4a_3x3_conv2': [192, 96, 3, 3],
'inception_4a_5x5_conv1': [32, 640, 1, 1,],
'inception_4a_5x5_conv2': [64, 32, 5, 5],
'inception_4a_pool_conv': [128, 640, 1, 1],
'inception_4a_1x1_conv': [256, 640, 1, 1],
'inception_4e_3x3_conv1': [160, 640, 1, 1],
'inception_4e_3x3_conv2': [256, 160, 3, 3],
'inception_4e_5x5_conv1': [64, 640, 1, 1],
'inception_4e_5x5_conv2': [128, 64, 5, 5],
'inception_5a_3x3_conv1': [96, 1024, 1, 1],
'inception_5a_3x3_conv2': [384, 96, 3, 3],
'inception_5a_pool_conv': [96, 1024, 1, 1],
'inception_5a_1x1_conv': [256, 1024, 1, 1],
'inception_5b_3x3_conv1': [96, 736, 1, 1],
'inception_5b_3x3_conv2': [384, 96, 3, 3],
'inception_5b_pool_conv': [96, 736, 1, 1],
'inception_5b_1x1_conv': [256, 736, 1, 1],
}
def load_weights_from_FaceNet(FRmodel):
# Load weights from csv files (which was exported from Openface torch model)
weights = WEIGHTS
weights_dict = load_weights()
# Set layer weights of the model
for name in weights:
if FRmodel.get_layer(name) != None:
FRmodel.get_layer(name).set_weights(weights_dict[name])
elif model.get_layer(name) != None:
model.get_layer(name).set_weights(weights_dict[name])
def load_weights():
# Set weights path
dirPath = './weights'
fileNames = filter(lambda f: not f.startswith('.'), os.listdir(dirPath))
paths = {}
weights_dict = {}
for n in fileNames:
paths[n.replace('.csv', '')] = dirPath + '/' + n
for name in WEIGHTS:
if 'conv' in name:
conv_w = genfromtxt(paths[name + '_w'], delimiter=',', dtype=None)
conv_w = np.reshape(conv_w, conv_shape[name])
conv_w = np.transpose(conv_w, (2, 3, 1, 0))
conv_b = genfromtxt(paths[name + '_b'], delimiter=',', dtype=None)
weights_dict[name] = [conv_w, conv_b]
elif 'bn' in name:
bn_w = genfromtxt(paths[name + '_w'], delimiter=',', dtype=None)
bn_b = genfromtxt(paths[name + '_b'], delimiter=',', dtype=None)
bn_m = genfromtxt(paths[name + '_m'], delimiter=',', dtype=None)
bn_v = genfromtxt(paths[name + '_v'], delimiter=',', dtype=None)
weights_dict[name] = [bn_w, bn_b, bn_m, bn_v]
elif 'dense' in name:
dense_w = genfromtxt(dirPath+'/dense_w.csv', delimiter=',', dtype=None)
dense_w = np.reshape(dense_w, (128, 736))
dense_w = np.transpose(dense_w, (1, 0))
dense_b = genfromtxt(dirPath+'/dense_b.csv', delimiter=',', dtype=None)
weights_dict[name] = [dense_w, dense_b]
return weights_dict
def load_dataset():
train_dataset = h5py.File('datasets/train_happy.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_happy.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
def img_path_to_encoding(image_path, model):
img1 = cv2.imread(image_path, 1)
return img_to_encoding(img1, model)
def img_to_encoding(image, model):
image = cv2.resize(image, (96, 96))
img = image[...,::-1]
img = np.around(np.transpose(img, (2,0,1))/255.0, decimals=12)
x_train = np.array([img])
embedding = model.predict_on_batch(x_train)
return embedding