-
Notifications
You must be signed in to change notification settings - Fork 2
/
losses.py
196 lines (167 loc) · 6.46 KB
/
losses.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
import numpy as np
import torch
import torch.nn.functional as F
import torch.nn as nn
from torch.autograd import Variable
try:
from itertools import ifilterfalse
except ImportError: # py3k
from itertools import filterfalse as ifilterfalse
# --------------------------- FOCAL LOSSES ---------------------------
class FocalLoss(nn.modules.loss._WeightedLoss):
def __init__(self, weight=None, gamma=2,reduction='mean'):
super(FocalLoss, self).__init__(weight,reduction=reduction)
self.gamma = gamma
self.weight = weight #weight parameter will act as the alpha parameter to balance class weights
def forward(self, input, target):
ce_loss = F.cross_entropy(input, target,reduction=self.reduction, weight=self.weight)
pt = torch.exp(-ce_loss)
focal_loss = ((1 - pt) ** self.gamma * ce_loss).mean()
return focal_loss
# --------------------------- DiceLoss LOSSES ---------------------------
class DiceLoss(nn.Module):
def __init__(self, weight=None, size_average=True):
super(DiceLoss, self).__init__()
def forward(self, inputs, targets):
inputs = F.sigmoid(inputs)
Lovasz = dice_loss(inputs, targets)
return Lovasz
def dice_loss(pred, target):
"""This definition generalize to real valued pred and target vector. This should be differentiable.
pred: tensor with first dimension as batch
target: tensor with first dimension as batch
"""
smooth = 1.
pred, _ = torch.max(pred, dim=1)
# have to use contiguous since they may from a torch.view op
iflat = pred.contiguous().view(-1)
tflat = target.contiguous().view(-1)
intersection = (iflat * tflat).sum()
A_sum = torch.sum(tflat * iflat)
B_sum = torch.sum(tflat * tflat)
return 1 - ((2. * intersection + smooth) / (A_sum + B_sum + smooth) )
# --------------------------- LovaszSoftmax BINARY LOSSES ---------------------------
class LovaszHingeLoss(nn.Module):
def __init__(self, weight=None, size_average=True):
super(LovaszHingeLoss, self).__init__()
def forward(self, inputs, targets):
Lovasz = lovasz_softmax(inputs, targets, per_image=False, ignore=255)
return Lovasz
def flatten_binary_scores(scores, labels, ignore=None):
"""
Flattens predictions in the batch (binary case)
Remove labels equal to 'ignore'
"""
scores = scores.view(-1)
labels = labels.view(-1)
if ignore is None:
return scores, labels
valid = (labels != ignore)
vscores = scores[valid]
vlabels = labels[valid]
return vscores, vlabels
def lovasz_grad(gt_sorted):
"""
Computes gradient of the Lovasz extension w.r.t sorted errors
See Alg. 1 in paper
"""
p = len(gt_sorted)
gts = gt_sorted.sum()
intersection = gts - gt_sorted.float().cumsum(0)
union = gts + (1 - gt_sorted).float().cumsum(0)
jaccard = 1. - intersection / union
if p > 1: # cover 1-pixel case
jaccard[1:p] = jaccard[1:p] - jaccard[0:-1]
return jaccard
#=====
#Multi-class Lovasz loss
#=====
def lovasz_softmax(probas, labels, classes='present', per_image=False, ignore=None):
"""
Multi-class Lovasz-Softmax loss
probas: [B, C, H, W] Variable, class probabilities at each prediction (between 0 and 1).
Interpreted as binary (sigmoid) output with outputs of size [B, H, W].
labels: [B, H, W] Tensor, ground truth labels (between 0 and C - 1)
classes: 'all' for all, 'present' for classes present in labels, or a list of classes to average.
per_image: compute the loss per image instead of per batch
ignore: void class labels
"""
if per_image:
loss = mean(lovasz_softmax_flat(*flatten_probas(prob.unsqueeze(0), lab.unsqueeze(0), ignore), classes=classes)
for prob, lab in zip(probas, labels))
else:
loss = lovasz_softmax_flat(*flatten_probas(probas, labels, ignore), classes=classes)
return loss
def lovasz_softmax_flat(probas, labels, classes='present'):
"""
Multi-class Lovasz-Softmax loss
probas: [P, C] Variable, class probabilities at each prediction (between 0 and 1)
labels: [P] Tensor, ground truth labels (between 0 and C - 1)
classes: 'all' for all, 'present' for classes present in labels, or a list of classes to average.
"""
if probas.numel() == 0:
# only void pixels, the gradients should be 0
return probas * 0.
C = probas.size(1)
losses = []
class_to_sum = list(range(C)) if classes in ['all', 'present'] else classes
for c in class_to_sum:
fg = (labels == c).float() # foreground for class c
if (classes is 'present' and fg.sum() == 0):
continue
if C == 1:
if len(classes) > 1:
raise ValueError('Sigmoid output possible only with 1 class')
class_pred = probas[:, 0]
else:
class_pred = probas[:, c]
errors = (Variable(fg) - class_pred).abs()
errors_sorted, perm = torch.sort(errors, 0, descending=True)
perm = perm.data
fg_sorted = fg[perm]
losses.append(torch.dot(errors_sorted, Variable(lovasz_grad(fg_sorted))))
return mean(losses)
def flatten_probas(probas, labels, ignore=None):
"""
Flattens predictions in the batch
"""
if probas.dim() == 3:
# assumes output of a sigmoid layer
B, H, W = probas.size()
probas = probas.view(B, 1, H, W)
B, C, H, W = probas.size()
probas = probas.permute(0, 2, 3, 1).contiguous().view(-1, C) # B * H * W, C = P, C
labels = labels.view(-1)
if ignore is None:
return probas, labels
valid = (labels != ignore)
vprobas = probas[valid.nonzero().squeeze()]
vlabels = labels[valid]
return vprobas, vlabels
def xloss(logits, labels, ignore=None):
"""
Cross entropy loss
"""
return F.cross_entropy(logits, Variable(labels), ignore_index=255)
# --------------------------- HELPER FUNCTIONS ---------------------------
def isnan(x):
return x != x
def mean(l, ignore_nan=False, empty=0):
"""
nanmean compatible with generators.
"""
l = iter(l)
if ignore_nan:
l = ifilterfalse(isnan, l)
try:
n = 1
acc = next(l)
except StopIteration:
if empty == 'raise':
raise ValueError('Empty mean')
return empty
for n, v in enumerate(l, 2):
acc += v
if n == 1:
return acc
return acc / n