-
Notifications
You must be signed in to change notification settings - Fork 424
/
verifacation.py
170 lines (147 loc) · 7.48 KB
/
verifacation.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
"""Helper for evaluation on the Labeled Faces in the Wild dataset
"""
# MIT License
#
# Copyright (c) 2016 David Sandberg
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import numpy as np
from sklearn.model_selection import KFold
from sklearn.decomposition import PCA
import sklearn
from scipy import interpolate
import datetime
import mxnet as mx
def calculate_roc(thresholds, embeddings1, embeddings2, actual_issame, nrof_folds=10, pca=0):
assert (embeddings1.shape[0] == embeddings2.shape[0])
assert (embeddings1.shape[1] == embeddings2.shape[1])
nrof_pairs = min(len(actual_issame), embeddings1.shape[0])
nrof_thresholds = len(thresholds)
k_fold = KFold(n_splits=nrof_folds, shuffle=False)
tprs = np.zeros((nrof_folds, nrof_thresholds))
fprs = np.zeros((nrof_folds, nrof_thresholds))
accuracy = np.zeros((nrof_folds))
best_thresholds = np.zeros((nrof_folds))
indices = np.arange(nrof_pairs)
# print('pca', pca)
if pca == 0:
diff = np.subtract(embeddings1, embeddings2)
dist = np.sum(np.square(diff), 1)
for fold_idx, (train_set, test_set) in enumerate(k_fold.split(indices)):
# print('train_set', train_set)
# print('test_set', test_set)
if pca > 0:
print('doing pca on', fold_idx)
embed1_train = embeddings1[train_set]
embed2_train = embeddings2[train_set]
_embed_train = np.concatenate((embed1_train, embed2_train), axis=0)
# print(_embed_train.shape)
pca_model = PCA(n_components=pca)
pca_model.fit(_embed_train)
embed1 = pca_model.transform(embeddings1)
embed2 = pca_model.transform(embeddings2)
embed1 = sklearn.preprocessing.normalize(embed1)
embed2 = sklearn.preprocessing.normalize(embed2)
# print(embed1.shape, embed2.shape)
diff = np.subtract(embed1, embed2)
dist = np.sum(np.square(diff), 1)
# Find the best threshold for the fold
acc_train = np.zeros((nrof_thresholds))
for threshold_idx, threshold in enumerate(thresholds):
_, _, acc_train[threshold_idx] = calculate_accuracy(threshold, dist[train_set], actual_issame[train_set])
best_threshold_index = np.argmax(acc_train)
# print('best_threshold_index', best_threshold_index, acc_train[best_threshold_index])
best_thresholds[fold_idx] = thresholds[best_threshold_index]
for threshold_idx, threshold in enumerate(thresholds):
tprs[fold_idx, threshold_idx], fprs[fold_idx, threshold_idx], _ = calculate_accuracy(threshold,
dist[test_set],
actual_issame[
test_set])
_, _, accuracy[fold_idx] = calculate_accuracy(thresholds[best_threshold_index], dist[test_set],
actual_issame[test_set])
tpr = np.mean(tprs, 0)
fpr = np.mean(fprs, 0)
return tpr, fpr, accuracy, best_thresholds
def calculate_accuracy(threshold, dist, actual_issame):
predict_issame = np.less(dist, threshold)
tp = np.sum(np.logical_and(predict_issame, actual_issame))
fp = np.sum(np.logical_and(predict_issame, np.logical_not(actual_issame)))
tn = np.sum(np.logical_and(np.logical_not(predict_issame), np.logical_not(actual_issame)))
fn = np.sum(np.logical_and(np.logical_not(predict_issame), actual_issame))
tpr = 0 if (tp + fn == 0) else float(tp) / float(tp + fn)
fpr = 0 if (fp + tn == 0) else float(fp) / float(fp + tn)
acc = float(tp + tn) / dist.size
return tpr, fpr, acc
def calculate_val(thresholds, embeddings1, embeddings2, actual_issame, far_target, nrof_folds=10):
'''
Copy from [insightface](https://github.com/deepinsight/insightface)
:param thresholds:
:param embeddings1:
:param embeddings2:
:param actual_issame:
:param far_target:
:param nrof_folds:
:return:
'''
assert (embeddings1.shape[0] == embeddings2.shape[0])
assert (embeddings1.shape[1] == embeddings2.shape[1])
nrof_pairs = min(len(actual_issame), embeddings1.shape[0])
nrof_thresholds = len(thresholds)
k_fold = KFold(n_splits=nrof_folds, shuffle=False)
val = np.zeros(nrof_folds)
far = np.zeros(nrof_folds)
diff = np.subtract(embeddings1, embeddings2)
dist = np.sum(np.square(diff), 1)
indices = np.arange(nrof_pairs)
for fold_idx, (train_set, test_set) in enumerate(k_fold.split(indices)):
# Find the threshold that gives FAR = far_target
far_train = np.zeros(nrof_thresholds)
for threshold_idx, threshold in enumerate(thresholds):
_, far_train[threshold_idx] = calculate_val_far(threshold, dist[train_set], actual_issame[train_set])
if np.max(far_train) >= far_target:
f = interpolate.interp1d(far_train, thresholds, kind='slinear')
threshold = f(far_target)
else:
threshold = 0.0
val[fold_idx], far[fold_idx] = calculate_val_far(threshold, dist[test_set], actual_issame[test_set])
val_mean = np.mean(val)
far_mean = np.mean(far)
val_std = np.std(val)
return val_mean, val_std, far_mean
def calculate_val_far(threshold, dist, actual_issame):
predict_issame = np.less(dist, threshold)
true_accept = np.sum(np.logical_and(predict_issame, actual_issame))
false_accept = np.sum(np.logical_and(predict_issame, np.logical_not(actual_issame)))
n_same = np.sum(actual_issame)
n_diff = np.sum(np.logical_not(actual_issame))
val = float(true_accept) / float(n_same)
far = float(false_accept) / float(n_diff)
return val, far
def evaluate(embeddings, actual_issame, nrof_folds=10, pca=0):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
tpr, fpr, accuracy, best_thresholds = calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), nrof_folds=nrof_folds, pca=pca)
# thresholds = np.arange(0, 4, 0.001)
# val, val_std, far = calculate_val(thresholds, embeddings1, embeddings2,
# np.asarray(actual_issame), 1e-3, nrof_folds=nrof_folds)
# return tpr, fpr, accuracy, best_thresholds, val, val_std, far
return tpr, fpr, accuracy, best_thresholds