-
Notifications
You must be signed in to change notification settings - Fork 0
/
metrics.py
203 lines (173 loc) · 7.85 KB
/
metrics.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
from __future__ import print_function
from __future__ import division
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import Parameter
import math
import torch
import torch.nn as nn
class CenterLoss(nn.Module):
"""Center loss.
Reference:
Wen et al. A Discriminative Feature Learning Approach for Deep Face Recognition. ECCV 2016.
Args:
num_classes (int): number of classes.
feat_dim (int): feature dimension.
"""
def __init__(self, num_classes=10, feat_dim=2, use_gpu=True):
super(CenterLoss, self).__init__()
self.num_classes = num_classes
self.feat_dim = feat_dim
self.use_gpu = use_gpu
if self.use_gpu:
self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim).cuda())
else:
self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim))
def forward(self, x, labels):
"""
Args:
x: feature matrix with shape (batch_size, feat_dim).
labels: ground truth labels with shape (batch_size).
"""
batch_size = x.size(0)
distmat = torch.pow(x, 2).sum(dim=1, keepdim=True).expand(batch_size, self.num_classes) + \
torch.pow(self.centers, 2).sum(dim=1, keepdim=True).expand(self.num_classes, batch_size).t()
distmat.addmm_(1, -2, x, self.centers.t())
classes = torch.arange(self.num_classes).long()
if self.use_gpu: classes = classes.cuda()
labels = labels.unsqueeze(1).expand(batch_size, self.num_classes)
mask = labels.eq(classes.expand(batch_size, self.num_classes))
dist = distmat * mask.float()
loss = dist.clamp(min=1e-12, max=1e+12).sum() / batch_size
return loss
class ArcMarginProduct(nn.Module):
r"""Implement of large margin arc distance: :
Args:
in_features: size of each input sample
out_features: size of each output sample
s: norm of input feature
m: margin
cos(theta + m)
"""
def __init__(self, in_features, out_features, s=10.0, m=0.50, easy_margin=False):
super(ArcMarginProduct, self).__init__()
self.in_features = in_features
self.out_features = out_features
self.s = s
self.m = m
self.weight = Parameter(torch.FloatTensor(out_features, in_features))
nn.init.xavier_uniform_(self.weight)
self.easy_margin = easy_margin
self.cos_m = math.cos(m)
self.sin_m = math.sin(m)
self.th = math.cos(math.pi - m)
self.mm = math.sin(math.pi - m) * m
def forward(self, input, label):
# --------------------------- cos(theta) & phi(theta) ---------------------------
cosine = F.linear(F.normalize(input), F.normalize(self.weight))
sine = torch.sqrt((1.0 - torch.pow(cosine, 2)).clamp(0, 1))
phi = cosine * self.cos_m - sine * self.sin_m
if self.easy_margin:
phi = torch.where(cosine > 0, phi, cosine)
else:
phi = torch.where(cosine > self.th, phi, cosine - self.mm)
# --------------------------- convert label to one-hot ---------------------------
# one_hot = torch.zeros(cosine.size(), requires_grad=True, device='cuda')
one_hot = torch.zeros(cosine.size(), device='cuda')
one_hot.scatter_(1, label.view(-1, 1).long(), 1)
# -------------torch.where(out_i = {x_i if condition_i else y_i) -------------
output = (one_hot * phi) + ((1.0 - one_hot) * cosine) # you can use torch.where if your torch.__version__ is 0.4
output *= self.s
# print(output)
return output
class AddMarginProduct(nn.Module):
r"""Implement of large margin cosine distance: :
Args:
in_features: size of each input sample
out_features: size of each output sample
s: norm of input feature
m: margin
cos(theta) - m
"""
def __init__(self, in_features, out_features, s=30.0, m=0.40):
super(AddMarginProduct, self).__init__()
self.in_features = in_features
self.out_features = out_features
self.s = s
self.m = m
self.weight = Parameter(torch.FloatTensor(out_features, in_features))
nn.init.xavier_uniform_(self.weight)
def forward(self, input, label):
# --------------------------- cos(theta) & phi(theta) ---------------------------
cosine = F.linear(F.normalize(input), F.normalize(self.weight))
phi = cosine - self.m
# --------------------------- convert label to one-hot ---------------------------
one_hot = torch.zeros(cosine.size(), device='cuda')
# one_hot = one_hot.cuda() if cosine.is_cuda else one_hot
one_hot.scatter_(1, label.view(-1, 1).long(), 1)
# -------------torch.where(out_i = {x_i if condition_i else y_i) -------------
output = (one_hot * phi) + ((1.0 - one_hot) * cosine) # you can use torch.where if your torch.__version__ is 0.4
output *= self.s
# print(output)
return output
def __repr__(self):
return self.__class__.__name__ + '(' \
+ 'in_features=' + str(self.in_features) \
+ ', out_features=' + str(self.out_features) \
+ ', s=' + str(self.s) \
+ ', m=' + str(self.m) + ')'
class SphereProduct(nn.Module):
r"""Implement of large margin cosine distance: :
Args:
in_features: size of each input sample
out_features: size of each output sample
m: margin
cos(m*theta)
"""
def __init__(self, in_features, out_features, m=4):
super(SphereProduct, self).__init__()
self.in_features = in_features
self.out_features = out_features
self.m = m
self.base = 1000.0
self.gamma = 0.12
self.power = 1
self.LambdaMin = 5.0
self.iter = 0
self.weight = Parameter(torch.FloatTensor(out_features, in_features))
nn.init.xavier_uniform(self.weight)
# duplication formula
self.mlambda = [
lambda x: x ** 0,
lambda x: x ** 1,
lambda x: 2 * x ** 2 - 1,
lambda x: 4 * x ** 3 - 3 * x,
lambda x: 8 * x ** 4 - 8 * x ** 2 + 1,
lambda x: 16 * x ** 5 - 20 * x ** 3 + 5 * x
]
def forward(self, input, label):
# lambda = max(lambda_min,base*(1+gamma*iteration)^(-power))
self.iter += 1
self.lamb = max(self.LambdaMin, self.base * (1 + self.gamma * self.iter) ** (-1 * self.power))
# --------------------------- cos(theta) & phi(theta) ---------------------------
cos_theta = F.linear(F.normalize(input), F.normalize(self.weight))
cos_theta = cos_theta.clamp(-1, 1)
cos_m_theta = self.mlambda[self.m](cos_theta)
theta = cos_theta.data.acos()
k = (self.m * theta / 3.14159265).floor()
phi_theta = ((-1.0) ** k) * cos_m_theta - 2 * k
NormOfFeature = torch.norm(input, 2, 1)
# --------------------------- convert label to one-hot ---------------------------
one_hot = torch.zeros(cos_theta.size())
one_hot = one_hot.cuda() if cos_theta.is_cuda else one_hot
one_hot.scatter_(1, label.view(-1, 1), 1)
# --------------------------- Calculate output ---------------------------
output = (one_hot * (phi_theta - cos_theta) / (1 + self.lamb)) + cos_theta
output *= NormOfFeature.view(-1, 1)
return output
def __repr__(self):
return self.__class__.__name__ + '(' \
+ 'in_features=' + str(self.in_features) \
+ ', out_features=' + str(self.out_features) \
+ ', m=' + str(self.m) + ')'