/
losses_intensity_weight.py
142 lines (118 loc) · 5.27 KB
/
losses_intensity_weight.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
from __future__ import print_function
import torch
import torch.nn as nn
def compute_covariance(input_data):
"""
Compute Covariance matrix of the input data
"""
n = input_data.size(0) # batch_size
# Check if using gpu or cpu
if input_data.is_cuda:
device = torch.device('cuda')
else:
device = torch.device('cpu')
id_row = torch.ones(n).resize(1, n).to(device=device)
sum_column = torch.mm(id_row, input_data)
mean_column = torch.div(sum_column, n)
term_mul_2 = torch.mm(mean_column.t(), mean_column)
d_t_d = torch.mm(input_data.t(), input_data)
c = torch.add(d_t_d, (-1 * term_mul_2)) * 1 / (n - 1)
return c
def covariance_loss(z1: torch.Tensor, z2: torch.Tensor) -> torch.Tensor:
"""Computes covariance loss given batch of projected features z1 from view 1 and
projected features z2 from view 2.
Args:
z1 (torch.Tensor): NxD Tensor containing projected features from view 1.
z2 (torch.Tensor): NxD Tensor containing projected features from view 2.
Returns:
torch.Tensor: covariance regularization loss.
"""
N, D = z1.size()
z1 = z1 - z1.mean(dim=0)
z2 = z2 - z2.mean(dim=0)
cov_z1 = (z1.T @ z1) / (N - 1)
cov_z2 = (z2.T @ z2) / (N - 1)
diag = torch.eye(D, device=z1.device)
cov_loss = cov_z1[~diag.bool()].pow_(2).sum() / D + cov_z2[~diag.bool()].pow_(2).sum() / D
return cov_loss
class DCCLoss(nn.Module):
"""Supervised Contrastive Learning: https://arxiv.org/pdf/2004.11362.pdf.
It also supports the unsupervised contrastive loss in SimCLR"""
def __init__(self, temperature=0.07, contrast_mode='all',
base_temperature=0.07):
super(SupConLoss, self).__init__()
self.temperature = temperature
self.contrast_mode = contrast_mode
self.base_temperature = base_temperature
def forward(self, features, labels=None, mask=None, image_weight=None):
"""Compute loss for model. If both `labels` and `mask` are None,
it degenerates to SimCLR unsupervised loss:
https://arxiv.org/pdf/2002.05709.pdf
Args:
features: hidden vector of shape [bsz, n_views, ...].
labels: ground truth of shape [bsz].
mask: contrastive mask of shape [bsz, bsz], mask_{i,j}=1 if sample j
has the same class as sample i. Can be asymmetric.
Returns:
A loss scalar.
"""
device = (torch.device('cuda')
if features.is_cuda
else torch.device('cpu'))
if len(features.shape) < 3:
raise ValueError('`features` needs to be [bsz, n_views, ...],'
'at least 3 dimensions are required')
if len(features.shape) > 3:
features = features.view(features.shape[0], features.shape[1], -1)
batch_size = features.shape[0]
if labels is not None and mask is not None:
raise ValueError('Cannot define both `labels` and `mask`')
elif labels is None and mask is None:
mask = torch.eye(batch_size, dtype=torch.float32).to(device)
elif labels is not None:
labels = labels.contiguous().view(-1, 1)
if labels.shape[0] != batch_size:
raise ValueError('Num of labels does not match num of features')
mask = torch.eq(labels, labels.T).float().to(device)
else:
mask = mask.float().to(device)
contrast_count = features.shape[1]
contrast_feature = torch.cat(torch.unbind(features, dim=1), dim=0)
# tmp = compute_covariance(contrast_feature)
convar_loss = covariance_loss(torch.unbind(features, dim=1)[0], torch.unbind(features, dim=1)[1])
if self.contrast_mode == 'one':
anchor_feature = features[:, 0]
anchor_count = 1
elif self.contrast_mode == 'all':
anchor_feature = contrast_feature
anchor_count = contrast_count
else:
raise ValueError('Unknown mode: {}'.format(self.contrast_mode))
# compute logits
anchor_dot_contrast = torch.div(
torch.matmul(anchor_feature, contrast_feature.T),
self.temperature)
# self_covariance = compute_covariance(torch.matmul(anchor_feature, contrast_feature.T))
# for numerical stability
logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
logits = anchor_dot_contrast - logits_max.detach()
# tile mask
mask = mask.repeat(anchor_count, contrast_count)
# mask-out self-contrast cases
logits_mask = torch.scatter(
torch.ones_like(mask),
1,
torch.arange(batch_size * anchor_count).view(-1, 1).to(device),
0
)
mask = mask * logits_mask
# * self_covariance
# compute log_prob
exp_logits = torch.exp(logits * image_weight) * logits_mask
log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True))
# compute mean of log-likelihood over positive
mean_log_prob_pos = (mask * log_prob).sum(1) / mask.sum(1)
# loss
loss = - (self.temperature / self.base_temperature) * mean_log_prob_pos
loss = loss.view(anchor_count, batch_size).mean()
return loss